Expert opinion and product quality: evidence from New York City restaurants.
Gergaud, Olivier ; Storchmann, Karl ; Verardi, Vincenzo 等
I. INTRODUCTION
In the presence of information asymmetries consumers often rely on
expert opinion to guide their purchase decision. An increasing body of
economic literature analyzes the effect of critical assessments on
prices and quantity consumed for a wide variety of experience goods such
as wine, movies, hotel rooms, or books. All of these papers analyze the
outcome of influenced quality perception of consumers.
This study is less focused on the question whether expert opinion
impacts quantity or price of the good in question but rather examines
consumers' quality perceptions and their possible changes directly.
We analyze whether suddenly appearing expert opinion, on a market with
long-standing published consumer-assessed quality evaluations, can alter
consumers' quality perception and subsequently change prices. Will
consumers stick to their original assessments or will they herd toward
the expert's opinion?
We investigate this question by referring to restaurants in New
York City. As the undisputedly leading restaurant guide, (1) Zagat has
rated New York City's restaurants since 1979. Zagat publishes its
guidebook once a year by drawing on consumer surveys. It, therefore,
reflects local residents' restaurant preferences, which, until
2005, had been only scantly influenced by experts. There had not been
any expert guides to New York City restaurants before 2005. Nationwide
expert guides such as the Mobil Travel Guides, Fodor, or the AAA
TourBook series, for various reasons, had never had any mentionable
impact on New York City diners (Davis 2012; Ferguson 2008). Although the
New York Times has published weekly reviews and assigned quality ratings
to local restaurants since 1963, the number of reviews has hardly
exceeded 50 per year--mostly focused on new openings. In comparison,
Zagat reviews about 2,000 restaurants per year. This and the fact that
the reviews are spread over about 50 New York Times issues substantially
limited its influence and never challenged Zagat's position. (2)
In November 2005, however, with the first release of the red
Michelin Guide New York City, the first one ever for the United States,
Zagat faced serious competition. In its first year, Michelin reviewed
471 restaurants and sold more than 100,000 copies (Krummert 2006). In
contrast to Zagat, Michelin relies on experts, that is, five anonymous
professional test eaters. According to Ferguson, while Zagat is a
plebiscite, Michelin is a tribunal (Ferguson 2008).
Although the advent of the Michelin Guide was excitingly
anticipated in New York, (3) when it finally appeared the results were
met with surprise, even with dismay. Many of the city's
well-regarded restaurants were not awarded a Michelin star while others
received unexpected honors (e.g., Cuozzo 2005a; Fabricant 2005b; Kurutz
2005). The press detected a bias toward French-owned venues and the New
York Post even called the Michelin Guide the "idiot's
guide" (Cuozzo 2005b). "After learning that Babbo had received
[only] one star, Mario Batali (4) said he didn't think New Yorkers
would give much credence to the guide. He was not happy with that
ranking, the same as for the Spotted Pig, of which he is a part-owner.
'They're blowing it', he said. 'They can't put
the Spotted Pig on the same level as Babbo"' (Fabricant
2005b).
What credence did New Yorkers give to the Michelin Guidel When
tackling this question we do not analyze who of the two assessments,
consumer or expert ratings, are closer to (unobserved) "true
quality." (5) Instead, we analyze whether Zagat ratings have
responded to Michelin quality assessments and employ a
difference-in-differences approach for the years 2003, that is, two
years before the first New York City Michelin edition, and 2006, one
year after its publication. We refer to various ZIP-code level
demographic variables, such as the number of wine stores per capita and
the local incidence of the treatment (measured as percent of restaurants
treated in a region) as instruments for the restaurant treatment (i.e.,
being Michelin reviewed). In order to assess the robustness of our
findings we also employ a propensity score matching (PSM) approach which
is aimed at isolating the treatment effect and purge it from other
confounding factors.
We find significant Michelin treatment effects on food quality as
well as on decor. However, it is a priori unclear whether these effects
are based on demand-side imaginations or whether the reviewed
restaurants have in fact invested in food, decor, and service
enhancements. We analyze restaurant nonfood investments by referring to
Wine Spectator wine list awards and find that Michelin-reviewed
restaurants are significantly more likely to invest in their wine list
than others suggesting that quality improvements are real and not
consumer-imagined.
We also find evidence of Michelin-induced price effects. When using
an ordered 0-1-2-3-4 treatment variable we find a marginal price effect
of 31%-33% per Michelin tier (0: not in Michelin, 1: reviewed, 2: one
star, 3: two stars, 4: three stars). The price increases of
Michelin-reviewed restaurants are based on quality improvements for
food, decor, and service. However, the market appears to punish
restaurants that justify price increases mainly with decor and service
improvements. We find that the odds of going out of business are higher
for expensive decor- and service-focused venues. In contrast,
Michelin-reviewed restaurants that focus on food quality improvements
are significantly less likely to close down in subsequent years.
The remainder of this article is organized as follows. Section II
provides a review of the related theoretical and empirical literature.
In Section III, we present our data and in Section IV we outline our
econometric approach. Section V reports the results of our
difference-indifferences approach and draws conclusions; In Section VI,
we use a PSM approach and compare the findings with those from Section
V. Section VII summarizes the main findings and discusses some
implications.
II. LITERATURE
This study is aimed at analyzing whether, against the background of
well-established and relatively stable peer reviews and quality
perceptions, suddenly appearing expert opinion can exert authoritative
influence on consumers and/or producers.
As New York City's leading restaurant guide, Zagat has
published consumer reviews of restaurants for more than three decades.
Zagat's critical evaluation of a restaurant's food, service,
and decor are solely based on consumer reviews. Only in 2006, these
consumer ratings faced the considerable competition by expert
assessments, that is, the first publication of the New York City
Michelin Guide. Michelin only rates the food of a restaurant and
oftentimes disagrees with consumer preferences. In this article, we are
not interested in whether experts are biased or fallible (see, e.g.,
Ashenfelter, Goldstein, and Riddell 2010; Hodgson 2008, 2009), or what
"true quality" is. Instead, we examine whether the arrival of
expert opinion affects perceived product quality--either due to producer
efforts (supply) or due to changes in consumer evaluations (demand).
Answering this question is of general economic interest as it applies to
all markets with information asymmetries.
Beginning in the 1970s, there is an extensive body of literature on
the impact of information on markets with asymmetric information. In
contrast, analyses of consumer responses to private and public
information, expert opinion, and the respective framing environment are
of more recent nature.
A. Asymmetric Information, Markets and Producers
Beginning with the analyses of Nelson (1970, 1974) most of the
early literature on information asymmetric information was theoretical
in nature and focused on the firm and its scope of quality signaling
through advertising, warranties, reputation, or pricing (e.g., Bagwell
and Riordan 1991; Milgrom and Roberts 1986; Schmalensee 1978; Shapiro
1983; Tirole 1996; Wolinsky 1983).
Bagwell and Riordan (1991) assume that the credibility and
magnitude of signaling quality through prices declines as consumers
become increasingly informed. When only a few consumers are informed,
high-quality products signal their true characteristics through prices
above the full information level. However, as an increasing number of
consumers become informed, prices converge toward the full information
level. Numerous empirical papers have analyzed the relationship between
firms' signaling and the consumer information from an economic and
a marketing perspective for various goods (e.g., Caves and Greene 1996;
Curry and Riesz 1988; Heffetz and Shayo 2009; Riesz 1978; Schnabel and
Storchmann 2010; Tellis and Wernerfelt 1987). In particular, with
respect to expert opinion, Roberts and Reagans (2007) show that the
price-quality relationship of New World wines strengthens with growing
critical exposure at the firm level.
Related to our analysis, Rosenman and Wilson (1991) show that
consumers infer product quality on the cherry market by referring to
producer characteristics, that is, proxy variables. Likewise, consumers
may assume that a restaurant's ambience or the quality of its
service serves as a proxy variable for its food quality, which may
justify restaurant investments in nonfood characteristics--such as
decor.
B. Consumers
There is a growing body of consumer-related literature focusing on
the role of peers and experts on consumer learning. All of these
analyses draw on the assumption that the decisions of other consumers or
the assessment of experts contain choice-relevant information. The
literature on the influence of peers or "social learning" on
individual decisions is based on informal approaches in the
psychological literature (e.g., Bandura 1977; Deutsch and Gerard 1955).
For instance, Becker (1991) develops a formal model in which the demand
for a good, here a restaurant meal, depends positively on its aggregate
quantity demanded, that is, on peer demand. Banerjee (1992) and
Bikhchandani, Hirshleifer, and Welch (1992, 1998) describe localized
conformity, fashions, and "herd behavior" as the result of
informational cascades where the decision of an individual is influenced
by the actions of other individuals before him. As, in these models, the
individual is willing to give up his private information and only
follows the preceding peers, the peers' actions do not contain any
information and the resulting equilibrium may be inefficient.
McFadden and Train (1996) hypothesize that consumers learn from
other consumers but still utilize their private information. They
formalize consumer learning about a new good's quality through a
rational decision process between learning from own experience and from
the experience of their peers. (6) Morris and Shin (2002) show that,
even when agents have private information, they might overreact to
expert opinion and devalue their private information.
On the empirical side, Salganik, Dodds, and Watts (2006) created an
artificial "music market" in which participants downloaded
previously unknown songs. When providing the treatment group of users
with information about other users' music ratings, social learning
is a strong determinant of a song's success. Moretti (2011)
empirically examines social learning for movie sales from 1982 to 2000.
He analyzes movie sales over time compared to prior expectations,
measured by the number of screens dedicated to a movie in its opening
weekend, and finds a reinforcing pattern. When a movie exceeds
expectations in its opening week consumers update their expectations
leading to further increasing sales and so on. Liu (2006) finds similar
results for word-of-mouth effects on movie sales by referring to
consumers' internet postings. Cai, Chen, and Fang (2009) set up a
randomized natural held experiment in which they assess consumer choices
of restaurant menu items. If provided with a (made up) list of
"last week's top five selling dishes," consumers tend to
follow their peers' consumption. Similarly, Anderson and Magruder
(2012) show that positive consumer evaluations of restaurants on
Yelp.com induce higher table reservations.
C. Experts
In addition to the literature on social learning from peers, there
are also numerous papers that confirm the influence of experts on
markets. The effect of experts on market outcomes is hard to measure
because expert reviews and "true quality" are often closely
correlated. Hence, most studies draw on natural (or real) experiments or
make statistical inferences to disentangle the two.
For instance, Ginsburgh (2003) reports that experts significantly
determine the market success of movies (through Oscars) and, to a lesser
degree, of books (through the Pulitzer Prize). Reinstein and Snyder
(2005) examine the impact of critical reviews on movie box revenues and
also find positive effects of favorable reviews. Ginsburgh and van Ours
(2003) analyze the Queen Elizabeth piano competition in Belgium and find
that musicians who are successful in the competition will be rewarded by
subsequent market success. Similarly, experts affect sales prices for
paintings at art auctions by publishing presale estimates in auction
catalogues (Bauwens and Ginsburgh 2000).
Hadj Ali, Lecocq, and Visser (2008) analyze the effect of critical
points awarded by wine writer Robert Parker on the en primeur price of
Bordeaux wine. They find Parker points to have a significant but small
effect on wine prices. Dubois and Nauges (2010) also study the effect of
Parker points on en primeur prices of Bordeaux wines. They employ a
structural empirical approach to disentangle the effect of experts'
grades and unobserved quality on the wine price and find a significant
"Parker effect." Closer related to our research, Gergaud,
Montano, and Verardi (2007) find a substantial influence of expert
ratings, measured by Guide Michelin stars, on Paris restaurant menu
prices.
In contrast to price analyses, there are only a few papers that
examine the impact of expert opinion on quantity consumed. Drawing on a
field experiment in wine retail stores, Hilger, Rafert, and Villas-Boas
(2011) show that favorable expert reviews have a positive influence on
quantity consumed, independent of quality. However, wines that obtained
below-average ratings exhibit a decrease in demand. Friberg and
Gronqvist (2012) analyze the impact of expert opinion on quantity
consumed by referring to the Swedish wine market. They find a
substantial and long-lasting effect (more than 20 weeks) of positive
reviews. In addition, they also find positive demand effects of neutral
reviews and no negative effects of unfavorable reviews.
D. Framing
However, consumers' quality perception is not only influenced
by own or others' experience but is also responsive to the
respective consumption environment. There is plenty of evidence that
consumers make contextual inferences (Kamenica 2008) and are sensitive
to the framing of the decision situation (e.g., Tversky and Kahneman
1981). For instance, North, Hargreaves, and McKendrick (1999) show that
consumers respond to the kind of music played in a wine store. When
French music was played, customers bought more than thrice as many
French wines than German wines. When German music was played the
opposite was true. Wansink, Just, and Payne (2009) report that the
quantity of food we eat is only partially determined by what we were
planning on consuming. Environmental factors such as package size, plate
size and shape, lighting, and variety affect our food consumption volume
far more than we realize. Plassmann et al. (2008) draw on brain scans
and show that changes in the price of a product can affect neural
representations of experienced pleasantness.
Similarly, experts may also be affected by framing variables. For
instance, for the restaurant sector, Chossat and Gergaud (2003) show
that experts, although claiming to assess food quality only, may also be
influenced by nonfood framing elements, such as the decor of the venue
or the choice of wines in the cellar.
III. DATA
We are interested in assessing whether consumers' restaurant
quality perceptions, that is, Zagat ratings, have been influenced by the
publication of Michelin expert opinion in 2005. The dataset we employ
covers all New York City restaurants considered in both the 2003 and
2006 Zagat Surveys. These years correspond to two years before and one
year after the first publication of the NYC Michelin. We draw on 2003
instead of 2004 data to rule out that our results are influenced by
possible Michelin announcement effects on consumer assessments or on
restaurant efforts. (7)
In the 2004 issue (which was published in 2003), Zagat published a
total of 1,918 restaurant reviews based on the ratings of almost 26,000
reviewers (Zagat Survey 2003). In the 2007 issue, published in 2006, it
rated 2,014 establishments based on reports of 31,604 restaurant-goers
(Zagat Survey 2006). After removing all chain restaurants from this
list, we are left with 1,518 observations. Zagat provides an average
consumer-reported price charged for a reference dinner including one
drink and tip for each restaurant. It also provides information on the
consumer-perceived quality of food, decor, and service on a scale
ranging from 0 to 30 points separately for each category. In addition,
Zagat lists some 90 different ethnic cuisine styles (8) that we bundled
into nine broad categories to avoid singletons: Africa, Asia, Central
America, Eastern Europe, Middle East, North America, South American,
Western Europe, and Other.
Our treatment group consists of 471 nonrandomly selected
restaurants that were reviewed in the first Michelin Guide, 2006 edition
(Michelin Travel Publications 2005). In contrast to Zagat, the Michelin
Guide claims to review the quality of food only; neither decor nor
service quality should affect its rating. (9) Michelin rates a
restaurant's food quality on a scale from zero to three stars.
Table 1 reports the descriptive statistics for food, service, and
decor quality as well as for prices. When looking at all restaurants, we
see that all quality categories have improved from 2003 to 2006. The
average meal price (including a drink a tip) has increased from $38.14
to $40.69. Table 1 reports the same data also separately for both
treatment and control group for 2003 and 2006. Expectedly, the treatment
group was rated higher than the control group in each category, that is,
food, service, and decor. This is true before as well as after the
treatment. In addition, the mean values for each group and category
remained virtually unchanged between 2003 and 2006. In contrast, the
average price of the restaurants in the treatment group grew
significantly after the Michelin review. In addition, the dispersion,
measured by the coefficient of variation (CV) (10) within each quality
category tends to be slightly lower in the treatment group before and
after the treatment. For 2003, this also applies to the price
dispersion. After the treatment, however, the reviewed restaurants
experienced a substantial increase in price dispersion: the CV of prices
grew from 34.1% to 53.5%, suggesting a considerable injection of noise
caused by published expert opinions.
In Table 2, we show the percentage growth rates from 2003 to 2006
in each quality category and in prices separately for treatment and
control group. Although these numbers are uncontrolled for effects such
as food ethnicity, they still convey a few interesting developments.
First, while we find a perceived food quality improvement for nontreated
restaurants of 2.99%, the treatment group exhibits a small decline.
Second, and despite the lack in food enhancement, the treatment group
shows a substantial price increase of 10.38% while there is only a 2.87%
increase for unreviewed restaurants.
This overview, however, disregards any influence of variables such
as food ethnicity (cuisine categories), restaurant location, operating
hours, or payment options. In the following section, we will thus employ
an econometric model to analyze the Michelin effect on the restaurant
quality categories food, service, and decor, as well as on restaurant
meal prices.
IV. ECCONOMETRIC METHODOLOGY
Our econometric analysis relies on three difference-in-differences
models, one for each category, that is, food, service, and decor, in
order to assess whether the mere inclusion in the Michelin guide
affected consumer quality assessments. We estimate the following
equation:
(1) [MATHEMATICAL EXPRESSION NOT REPRODUCIBLE IN ASCII]
where i denotes individual restaurants and t denotes time.
[Q.sub.t] is a measure of quality of food, service, or decor,
respectively, measured in period t (i.e., 2006); similarly, [Q.sub.t-1]
stands for the quality variables in the prior period, that is, 2003.
Introducing the lagged dependent variable accounts for the persistence
of quality over time. [Mich.sub.i] is a dummy variable that takes on the
value one if the restaurant was reviewed in the 2006 Michelin guide
(first edition, published in 2005) and zero otherwise. After is a time
dummy that equals one in the period following the introduction of the
guide and zero before. [Mich.sub.i] X [After.sub.t] is the interaction
term between the two and measures whether Q has changed differently for
those who have been introduced in the guide compared to those who have
not (control group). It is also known as the difference-in-differences
term. [X.sub.it] is a matrix of control variables such as food ethnicity
and some characteristics at the restaurant level (accepts credit card,
open after 11 p.m., open on Sundays, limited number of reviews). (11)
Obviously, the treatment, that is, being considered in the Michelin
guide, is not random and independent of the quality of food (or service
or decor, respectively) as reported by consumers in the Zagat guide. We,
therefore, suspect an endogeneity bias. To remedy this shortcoming, we
instrument the treatment itself. Given the geographical clustering of
Michelin-reviewed restaurants, we use the percentage of treated
restaurants in the neighborhood as instruments.
The map provided in Figure 1 shows that all Michelin-reviewed
restaurants are either in one of two geographical clusters in Manhattan
or in two less concentrated groups in Queens and Brooklyn. (12) This
spatial concentration suggests that the likelihood of being considered
in the Michelin guide is not independent of a restaurant's
geographical location. We exploit this fact and employ a geographical
location variable to instrument for being reviewed by the Michelin
guide.
In addition to the geographical location of the restaurant, we also
explore other possible instruments for the Michelin treatment. We
examine ZIP-code level data of various demographic and economic data
that may serve as appropriate instruments for the treatment variable.
(13) In particular, we employ size and racial composition of the
population, per capita income, population share under the poverty line,
share of full-service restaurants as well as the number of wine and
liquor stores per capita. For the instrument selection, we hypothesize
that Michelin-reviewed restaurants are above-average expensive and
depend on a well-off clientele. We thus assume that Michelin restaurants
predominantly locate in upscale neighborhoods with high per capita
incomes and low poverty rates. Similarly, we expect the likelihood of
being Michelin reviewed to be positively related to the number of
full-service venues (i.e., inversely related to the number of fast food
outlets) and the number of wine stores. The latter draws on the fact
that New York State stipulates that wine and liquor can only be sold in
state-licensed wine and liquor stores. In contrast, beer is usually sold
in supermarkets and convenience stores and must not be sold in wine and
liquor stores.
In other words, we assume a direct relation between the regional
concentration of Michelin restaurants and their environment
(wealth/poverty and interest of the local population for fine wine and
food). In addition, as all restaurants in the sample were already
established when the Michelin guide was introduced, the instruments
should be exogenous.
As will be shown later, the statistical tests tend to strongly
support our intuition and show that our instruments are neither weak nor
endogenous.
A. Defining Neighbors and Instruments
In order to define neighbors, we identify the geographical
coordinates of all restaurants (14) and compute the distance between all
pairs of observations. The smallest maximum distance between two
restaurants in the dataset is 31.3 km, the largest minimum distance is
3.4 km and the general average distance between two restaurants is 5.9
km. (15) We attribute proximity spatial weights as follows:
[MATHEMATICAL EXPRESSION NOT REPRODUCIBLE IN ASCII]
where (i,j) denotes a pair of locations, [d.sub.ij] stands for the
Euclidean distance between restaurant i and j, [l.sub.b] and [u.sub.b]
denote the lower and upper bound of the specified distance band,
respectively, and/ is a positive friction parameter that is set
exogenously. The friction parameter determines the rate of devaluation
for neighbors compared to the geographic distance. A parameter value of
one denotes that the importance of the neighborhood effect is linearly
decaying in distance. A friction parameter larger than one suggests that
neighborhood effects decline faster than the geographic distance and
vice versa.
[FIGURE 1 OMITTED]
As in New York City, the monetary transportation cost is virtually
independent of distance traveled while time spent depends on distance,
we set the friction parameter equal to 0.8 suggesting below-proportional
neighbor depreciations compared to the geographic distance. However, our
empirical results are not overly sensitive to different parameter
values. We tried different values for this friction parameter and the
estimated coefficients were mostly unaffected. We selected 0.8 as it
provides the strongest and most exogenous instruments.
Finally, the values in the weighting matrix are standardized in
order to ensure that the sum of all elements per row equals one. A
restaurant i is considered a neighbor of restaurant j if the distance
between i and j does not exceed 10 km (i.e,, [l.sub.b] = 0 and [u.sub.b]
= 10). (16)
We can now calculate the average number of Michelin restaurants in
the neighborhood of each restaurant (weighted by the distance) by
multiplying the weighting matrix (W) by the vector identifying the
Michelin restaurants. In other words, the frequency of "Michelin
restaurants" in the neighborhood of each restaurant is defined by W
x Mich (vector WMich). This variable is the first instrument we use for
the treatment. The second instrument we consider, provided by Zagat, is
a dummy variable that is equal to one if only a small number of
customers reviewed the restaurant (Low2003). We hypothesize that
Michelin can afford to disregard unknown restaurants. However,
restaurants with a large number of customer reviews may enjoy an
increased likelihood of being selected in the guide. As Zagat refers to
the number of 2003 reviews, that is, well before the announcement of the
Michelin launch, we deem this variable exogenous.
To summarize, the endogenous right-handside variables are Mich and
(Mich x After). The available instruments are WMich, WMich interacted
with After (which is exogenous) and Low2003. As we employ more
instruments than we have endogenous variables we test for their
redundancy, over-identification (i.e., exogeneity), and weakness. We
perform these tests for each model, that is, for food, decor, and
service, by drawing on the Hansen J-statistic for over-identifying
restrictions (exogeneity test), the Kleibergen-Paap rk LM statistic
(relevance test), and the Kleibergen-Paap rk Wald F statistic (weakness
test).
Note, we do not employ restaurant fixed effects. In general,
difference-in-differences models may suffer from omitted variable bias
(OVB) when an omitted variable is correlated with both treatment and
outcome. The OVB could be significantly alleviated by including
restaurant fixed effects that capture all time-invariant determinants.
In our case, however, strict restaurant fixed effects pose a problem as
our instruments also include a considerable time invariant component. As
we hypothesize that the treatment is crucially driven by locational
reasoning (causing Michelin clusters), employing a fixed effect model
would significantly lower the computed treatment effect (i.e., cut out
some of the signal but keep the noise) and render our instruments
invalid. In fact, when running a FE-IV model the Kleibergen-Paap rk (LM
statistic) suggests that we cannot reject the null that our model is
underidentified. We, therefore, decided to stick with the standard
difference-in-differences model controlling for all characteristics that
are available to us. We also include lagged dependent variables, which
account for a large fraction of restaurant fixed effects, but certainly
not all. Finally, we contrast the difference-in-differences approach
with various other methods.
V. RESULTS
A. Impact on Quality
Full Sample. Table 3 reports the ordinary least squares (OLS)
results of the model described in Equation (1) with respect to the
quality of food, service, and decor. In the first three columns, we
model the treatment with a simple dummy variable, where 1 denotes
Michelin reviewed and 0 otherwise.
Ideally, we would like to calculate the impact of each Michelin
assessment level, that is, no star, one star, two stars, and three
stars. This, however, requires more valid instruments than are
available. We, therefore, resort to an ordered treatment variable that
takes on the value 0 for not reviewed, 1 for reviewed but no Michelin
star, 2 for one star, 3 for two stars, and 4 for three stars. The
ordered variable thus postulates a constant marginal effect of each
additional Michelin star on the various quality variables. We report the
respective results in the three right columns of Table 3.
Both model variants yield virtually identical results and show
significant treatment effects (Mich x After) on food, decor, and
service. For instance, the dummy treatment suggests that being Michelin
reviewed leads to a 10% increase in perceived food quality, an 18%
increase in decor, and a 12% increase in service quality.
However, these results are not generally supported when using
instruments. As shown in Table 4, we find positive treatment effects for
all quality categories. But the interacted term (Mich X After) is
statistically significant only for decor, suggesting that
Michelin-reviewed restaurants invest only in their decor but not in
their food quality. If consumers deem decor a proxy variable for food
quality this would be in line with Rosenman and Wilson (1991).
When comparing the OLS and two-stage least squares (2SLS) for food
in Tables 3 and 4 we find that the coefficient for the interacted
variable we are mainly interested in (i.e., Mich x After) is positive
and significant in the OLS estimation while not significant (but still
positive) in the 2SLS estimation. While the lack of significance could
be due to the inefficiency of the 2SLS estimation, we also see that the
point estimate decreases by approximately 50% (from 0.1 to 0.05). This
suggests an upward bias in the OLS estimates which was corrected by the
2SLS model. We, therefore, conclude that the Michelin effect on food
quality was fairly moderate (i.e., we do not reject that it is zero). We
find a similar pattern for the service variable. However, the 2SLS Mich
x After coefficient for decor is significant and substantially larger
than the OLS coefficient (0.18 compared to 0.39) suggesting that the OLS
estimates are downward biased.
In Table 4, we also report the results of various tests for
overidentifying restrictions (exogeneity), relevance, and weakness of
our instruments. Note that we chose different combinations of
instruments depending on the resulting test statistics and that we
instrument both Mich and Mich x After.
All first-stage estimates are provided in Table A1. The variable
"limited number of reviews" refers to a restaurant's
(quantitative) unpopularity. The geography variable, as described above,
denotes the regional concentration of reviewed restaurants; the number
of wine stores, the share of population below the poverty line and the
share of full service restaurants are by ZIP code and reflect various
aspects of neighborhood desirability. In general, restaurants that do
not accept credit cards, are open after 11 p.m., and are located in a
restaurant cluster are more likely to be Michelin reviewed than others.
When instrumenting the ordered Michelin variable we also find adverse
effect of high-poverty shares in the neighborhood. In contrast, the
density of wine stores per ZIP code does not exert any significant
effect.
For the food variable, we calculate the Hansen 7-statistic to check
for overidentifying restrictions of the instruments. The resulting value
of 4.674 is well below the critical [chi square] value for three degrees
of freedom (7.815). We hence do not reject the null hypothesis that the
instruments are exogenous. To check for the relevance of the
instruments, we rely on the Kleibergen-Paap rk LM statistic, which
equals 30.75 for the food model. This value is well above the critical
[chi square] value for four degrees of freedom, which is 9.488.
Therefore, we reject the null that the model is underidentified.
Finally, we test whether our instrument sets are weak drawing on the
formal test suggested by Stock and Yogo (2005) who propose a procedure
testing for the null hypothesis that the bias of 2SLS is some fraction
of the OLS bias. For instance, if the bias of 2SLS is less than 10% of
the OLS bias, the instrumental variable (IV) estimator has reduced the
OLS bias by more than 90%. Table 5 reports the maximal IV relative bias
for the 2SLS estimator. Drawing on the Kleibergen-Paap rk Wald F
statistic, we find a value of 7.618 for the food model which is lower
(larger) than the critical value of 8.78 (5.91) tabulated by Stock and
Yogo (2005) for a 20% (10%) maximal IV relative bias. We find similar
results for the service and decor equations suggesting that the 2SLS
estimator results in bias reductions between 80 and more than 95%. We
report the results for the ordered treatment variable in the three right
columns of Table 4. Overall, the findings are very similar to those when
using a dummy treatment variable.
Restricted Paired Sample. So far, our 2SLS results suggest that, in
response to being Michelin reviewed, restaurants' perceived decor
quality has significantly improved, whereas there is no discernable
effect on food quality. However, conclusions need to be interpreted with
care as our full sample is not only comprised of restaurants that were
in business in 2003 as well as in 2006. It also includes restaurants
that closed down before 2006 and of new births that did not exist in
2003. (17) In order to assess whether our results are biased due to
restaurant closures or new births we also run Equation (1) on a sample
that is restricted to restaurants that were in business in both years,
2003 and 2006. Our further analysis is thus confined to perfect pairs.
Table 5 reports the results of the OLS models run on the restricted
paired sample. Except for the number of observations, the restricted
sample is almost 1000 observations smaller, we do not detect any
considerable difference to the results shown in Table 3. Even all
marginal effects are of almost identical size.
The 2SLS equation for the restricted paired sample, shown in Table
6, is, however, very different from its counterpart in Table 4. (18)
While the full sample 2SLS equation suggests only decor improvements
(either perceived or real), the same equation run on the restricted
sample suggests only food improvements. The Michelin effects on decor
and service are insignificant. These results hold also for the ordered
treatment variable. The test results provided at the bottom of the table
suggest that our instruments are neither endogenous, nor irrelevant, nor
weak. The puzzling difference between the 2SLS models run on two
different samples must be due to the characteristics of restaurants that
are present only in one of the two years, notably restaurants that
closed down between 2003 and 2006. The difference in treatment effects
for the two samples suggests that restaurants that closed down before
2006 improved their decor quality but not their food quality. In
contrast, surviving restaurants show significant food improvements, but
no perceived decor or service enhancements.
In Table 7, we show two simple probit equations on restaurant
closures in 2007. While restaurants that are open on Sundays and after
11 p.m. are less likely to go out of business, being a Middle Eastern
restaurant increases the odds of shutting down. In addition, and more
interesting for this study, the results in Table 8 also suggest that
high food quality lowers the odds of closing down while high decor marks
have the opposite effect. This appears to square with the differences
between the full and restricted samples in Tables 4 and 6. The decor
effect of the Michelin treatment in Table 4 dominates the food effect
because the sample includes nonsurviving restaurants, whereas the
restricted sample does not. In addition, as shown in column (2) of Table
7, being Michelin-reviewed by itself lowers the odds of closing down.
Apparently, a Michelin review, which is per se good for a
restaurant's odds of survival, opens up two strategy paths.
Restaurants that improve their (perceived) food quality can further
secure their survival, while restaurants that only improve their decor
and service quality are less likely to survive.
Base Year Choice and Dynamics. We chose the base year 2003, that
is, two years before the treatment, to avoid potential disturbances by
Michelin announcement effects. Similar to Table 6, Table 8 shows the
results of a 2SLS model run on the restricted sample. However, instead
of 2003, we now refer to 2004 as the base year. In general, the results
of Tables 6 and 8 are very similar for almost all variables. The only
difference is that by referring to 2004 the treatment effect on decor
grows and becomes significant at the 5% level. In contrast, the
treatment effect on perceived food quality drops from a coefficient of
0.20 (base year 2003) to 0.15 (base year 2004). The latter is in line
with an announcement effect and suggests that restaurants were on
different trend paths even before the treatment. That is, between 2003
and 2004, Michelin-reviewed restaurants improved their food quality by
more than unreviewed venues leading to a smaller treatment effect when
referring to the base year 2004.
The opposite is true for decor. The increase in the treatment
effect for the 2004 base year suggests that the decor difference between
reviewed and unreviewed restaurants was smaller in 2004 than in 2003.
This can be due to a "decoring-up" of all restaurants,
especially by unreviewed restaurants, in expectation of the Michelin
review.
From a restaurateur's perspective, this strategy may be
sensible as Chossat and Gergaud (2003) and Gergaud et al. (2007) show
that Michelin evaluations in France are not solely driven by food
quality but also influenced by nonfood characteristics such as decor and
service. Johnson et al. (2005) interviewed chef-owners of
Michelin-starred restaurants in France, Belgium, Switzerland, and the UK
and report that receiving a Michelin star places enormous pressure on
the owner. Massive efforts and investments are due in order to retain
the recently gained (first, second, or third) Michelin star. As these
investments include service and decor it appears to be commonly
understood among restaurateurs that Michelin ratings--in contrast to
their claim--are influenced by service and decor. These findings suggest
that the higher service and decor quality may not be imagined by
consumers but may rather be the result of the owner's effort.
Investments in service and decor are expensive and may only be
justified if they yield higher revenue. There is some anecdotal evidence
that Michelin stars demand a premium and are thus worth being retained.
Eric Ripert, chef and owner of Le Bernardin, one of only three New York
City restaurants that received three Michelin stars in 2006, reports
revenue increases of at least 15% (Davis 2012). Johnson et al. (2005)
find similar values for European Michelin-starred venues. In an analysis
of French Michelin-reviewed restaurants from 1970 to 1994 Snyder and
Cotter (1998) find a close relationship between investments, especially
in ambience, Michelin stars, and prices. In particular, the loss of a
Michelin star is often predated by receding investments and lower
prices. Similar findings are reported by Gergaud et al. (2007) for
restaurants in Paris.
However, and as shown in Table 8, decoring and servicing-up without
improved food quality may be at the expense of the future survival of
the restaurant, especially for an unreviewed venue.
B. Impact on Prices
In Table 9, we show the impact of the Michelin treatment on menu
prices. The model specification is identical with the one for the Zagat
quality assessments (see Equation (1)); we only substituted the
logarithm of menu prices for the Zagat variable as dependent variable.
The tests for overidentifying restrictions, underidentification, and
weak identification for the selected instruments are reported at the
bottom of the table. When employing a simple 1-0 dummy variable for the
inclusion in the Michelin Guide we find treatment-induced price
increases of approximately 40%. When using an ordered 0-1-2-3-4
treatment variable we find a marginal effect of approximately 30% per
tier (reviewed, 1 star, 2 stars, and 3 stars). Note that the price
reported by Zagat includes a drink and tip.
We are further interested in examining whether these price
increases are related to food, service, or decor quality improvements
and whether there is a difference between Michelin-reviewed and
unreviewed restaurants. We select all unique restaurants for which we
have price and quality data for 2003 and 2006, and regress the nominal
price difference on the respective quality difference, a constant term,
and various time-invariant control variables:
(2) ([P.sub.2006,i] - [P.sub.2003,i]) = [[beta].sub.0] +
[[beta].sub.1] X ([Q.sub.k,2006,i] - [Q.sub.k,2003,i]) + [n.summation
over (m=1)][[beta].sub.m][F.sub.i]
where P denotes price, Q quality, k the specific quality variable,
that is, food, decor, or service, and i the individual restaurant. F is
a vector of time-invariant variables such as food ethnicity fixed
effects, open after 11 a.m.. closed on Sunday, no credit cards accepted,
and low response rate.
In this fashion, we run 12 different regressions; Table 10 displays
the results. In the columns denoted "All," we draw on 702
unreviewed and 331 Michelin-reviewed restaurants. For the group of
unreviewed restaurants, we do not find any significant effects of food,
service, and decor quality changes. In contrast, the prices of
Michelin-reviewed restaurants exhibit significant price responses to all
quality changes. The corresponding marginal effects suggest that quality
improvements by one point cause price increases between $0.38 and $0.54.
These results suggest that the price changes of Michelin-treated
restaurants are linked to changes in the perceived quality of their
food, decor, or service while the prices of untreated restaurants appear
to be uncorrelated to quality changes.
However, when regressing price changes only on changes in one
quality dimension, we disregard possible changes in the other quality
variables and may confound the respective marginal effects when the
various quality changes are correlated. We, therefore, augment our
analysis and restrict our sample to restaurants that exhibited a change
in only one quality variable while keeping the other quality variables
constant. For instance, when regressing price changes on food-quality
changes, we only refer to restaurants for which decor and service have
not changed. The results for this "restricted sample" are also
reported in Table 10. We assume that the two samples, that is,
"All" and "Restricted Sample," are comparatively
similar displaying almost identical mean prices. (19) While this
procedure allows us to isolate the respective quality effects on prices,
our sample size now drops by about 40% due to the fact that most
restaurants experienced changes in more than one quality dimension. The
corresponding results, as reported in the columns "Restricted
Sample" in Table 10, confirm our prior findings for food and
service; the decor effect becomes less significant. Results in Table 10,
therefore, suggest that, while price changes of restaurants that have
not been reviewed by the Michelin guide are detached from quality
changes, menu price changes of M/c/re/m-reviewed restaurants are driven
by food or service quality changes. (20)
In addition, higher prices are not necessarily an indicator for a
restaurant's success. They are set by the supply side and may be
triggered by cost or the wish to use prices as quality signals and may
thus not reflect higher demand. In fact, we have no information about
quantities.
Table 11 presents four probit equations that report the odds of a
restaurant's closure in 2007 as a function of its price. In order
to control for food quality, we partitioned our sample into four
food-quality quartiles of almost identical sample size. The top quartile
(Q1) is comprised of restaurants with a food score of 23 and above, Q2
of 21 and 22-point venues, Q3 of 19- and 20-point venues, and Q4 of
restaurants with 18 points and less. We also included a Michelin dummy,
to examine whether being Michelin-reviewed provides any protection, and
the full set of dummy variables as listed in Table 8.
For the high food-quality segment (Q1), the regressions suggest
that, while being Michelin reviewed provides some protection, high
prices are a significant determinant for restaurants to go out of
business. Note that we include the price variable in its squared form.
That is, the effect of price on shutdowns is not linear but exponential.
In fact, the coefficients for the first quality quartile suggest that a
price of slightly above $100 (including a drink and tip) offsets the
Michelin protection. Both price and Michelin effects decline with food
quality.
C. Investments
We cannot be a priori certain whether the improved quality consumer
ratings of Michelin-reviewed restaurants for service and decor are due
to the demand or the supply side. On the one hand, experts could have
influenced consumer perception. As a result, the food and decor quality
of Michelin-reviewed restaurants would then be seen in a better light
and more appreciated than before. On the other hand, the improved
perceived quality can also be due to actual restaurant investments.
Ideally, we would like to regress restaurant investments in decor
and service, for example, staff per meal served, or money spent on staff
training or decor, on Michelin points. However, as these data are
proprietary and not available to us, we rely on public information to
test whether Michelin-reviewed restaurants in fact invested more than
others.
In particular, we refer to Wine Spectator's Restaurant Wine
List Awards program, which we already mentioned in Section II. Wine
Spectator, the largest wine magazine in the nation, has invited
restaurants to compete for the "Award of Excellence" since
1981. In order to apply, a restaurant has to pay a $250 entry fee and
should submit its wine list along with its menu and information on the
wines' storage conditions. Wine Spectator then selects the winners
according to their merits (for more information, see Wine Spectator
2012). Winners can be in one of three categories. The Award of
Excellence requires wine list offers of at least 100 selections. Higher
achievements are honored with the Best of Award of Excellence (400+
selections) or the Grand Award (1,500+ selections). In 2003 (2006), 9
(5) NYC restaurants received the Grand Award, 28 (52) the Best of Award
of Excellence, and 128 (112) the Award of Excellence. Building a wine
collection that is sufficient to meet Wine Spectator's standards in
quantity and quality can be a substantial investment. For instance, the
Grand Award winner restaurant Veritas has a wine list with more than
3,000 selections and an inventory of 75,000 bottles. At bottle prices
ranging from $25 to $10,000, this is a multi-million dollar investment
even without storage cost.
We, therefore, interpret the win of Wine Spectator Awards of
Excellence as a restaurateur's willingness to invest in nonfood
ambience, which may serve as a good proxy variable for investments in
decor and service. (21) In addition, as restaurants with extensive wine
lists, in many cases, also have special wine waiters (sommeliers) one
may even expect direct wine list-induced service improvements.
Hence, we examine the impact of the Michelin treatment (i.e., being
included in the Guide) on the tier of the wine list award (0 = no award,
1 = Award of Excellence, 2-- Best Award of Excellence, 3 = Grand Award),
if any, and report the results in Table 12. We estimate a two-stage
difference-in-differences model that is almost identical with the one
employed for the Zagat quality assessments and the prices as reported in
Equation (2) and in Tables 4, 6, and 8; we only refer to Wine Spectator
scores as dependent variable. At the first stage, we regress the Mich
and Mich x After variables on the instruments and the exogenous
variables; we then estimate the Wine Spectator scores in a second step.
Since these scores are discrete ranks, we use a maximum likelihood
(ML)-ordered probit model with bootstrapped standard errors as this
equation contains generated regressors coming from the first step. At
the bottom of Table 12, we display overidentifying restriction,
underidentification, and weak identification tests for the selected
instruments.
Table 12 reports two variants of the model. The left column
considers the Michelin treatment as a 0-1 dummy variable, the right
column distinguishes between the Michelin stars awarded (0-1-2-3). In
both variants, we find significant treatment effects suggesting that
Michelin-reviewed restaurants, in fact, are more likely to receive a
Wine Spectator award for their wine list than do others. This appears to
confirm our prior assumption that higher service and decor quality
ratings of Michelin-reviewed restaurants are, in fact, based on
restaurant investment rather than on mere consumer perception.
VI. PROPENSITY SCORE MATCHING
As our treatment group was not selected randomly it is per se
difficult to isolate the treatment effect as the difference in outcomes
between the two groups may be due to pretreatment characteristics. We,
therefore, compare our IV results with those we receive from PSM.
PSM, as first published by Rosenbaum and Rubin (1983), is a
two-step approach. In a first step, we employ a binary model to
calculate the conditional probability of each observation to be assigned
to the treatment group given its pretreatment characteristics
(propensity score). Then, we match treated with untreated observations
based on their respective propensity scores. This way we create a
counterfactual situation and can evaluate the treatment effect for
matches with (almost) identical pretreatment characteristics.
Table 13 reports the probit equation results for the treatment
assignment for the base years 2003 and 2004, respectively. Both models
yield similar results and show that food and decor quality are the
crucial selection determinants.
These propensity scores form the base for the PSM results presented
in Table 14. Note that our calculations draw on the restricted paired
sample, that is, we excluded nonsurviving restaurants as well as new
births. When referring to the base year 2003, we find significant
treatment effects on food quality, Wine Spectator awards, and,
especially, on prices. Overall, when referring to the base year 2003,
the PSM results lend further support to our results from Section V.
However, when referring to 2004 as the base year, we observe a few
changes in coefficient size and significance. First, the food-quality
treatment effects is almost cut in half suggesting that
Michelin-reviewed restaurants did considerably improve their food
quality just before the launch of the first Michelin guide. We find a
similar pattern for prices. The drop in coefficient size and in
particular in significance suggests substantial price increases for
restaurants that were subsequently Michelin reviewed. We thus confirm
the results from the previous chapter and find positive announcement
effect for food and prices. This also underlines our conclusion that
Michelin-reviewed restaurants were on a different trend path than were
unreviewed ones.
This gives rise to the suspicion that expert scores are not only
determined by food quality but also by framing variables such as price
as already suggested by Gergaud et al. (2007) for the Paris Michelin
Guide (see also Section II.D). To analyze this for the New York guide
is, however, beyond the scope of this study.
VII. SUMMARY AND CONCLUSIONS
In this article, we analyze whether consumers' quality
perception and/or producer investment is influenced by newly appearing
expert opinion. We investigate this question by referring to restaurants
in New York City. As the leading restaurant guide, Zagat has rated New
York City's restaurants since 1979 by surveying more than 30,000
restaurant goers per year. In 2005, with the first release of the red
Michelin Guide New York City, Zagat faced a serious competition. In
contrast to Zagat, Michelin relies on expert eaters. Employing a
difference-in-differences approach we analyze whether consumer
assessments (Zagat ratings) have responded to Michelin quality
assessments. Employing a difference-in-differences model for 2003 and
2006, we find significant Michelin-induced perceived quality increases
for food and decor. However, restaurants that only improved their decor
but not their food quality were more likely to go out of business.
Apparently, a Michelin review, which is per se good for a
restaurant's odds of survival, opens up two strategy paths.
Restaurants that improve their (perceived) food quality can further
secure their survival, while restaurants that only improve their decor
quality are less likely to survive.
When changing the base year from 2003 to 2004, that is, when moving
closer to the 2005 treatment, we find that the treatment effect on
perceived food quality drops from a coefficient of 0.20 (base year 2003)
to 0.15 (base year 2004). This is in line with an announcement effect
and suggests that restaurants were on different trend paths even before
the treatment. That is, between 2003 and 2004, Michelin-reviewed
restaurants improved their food quality by more than unreviewed venues
leading to a smaller treatment effect when referring to the base year
2004. The opposite is true for decor. A larger treatment effect for the
2004 base year suggests that especially restaurants that were not
Michelin reviewed "decored up." Both improved decor quality as
well as not being Michelin reviewed contribute to a higher shut down
likelihood.
We also find significant Michelin-induced price effects. As we are
interested in knowing which quality variable induced the price change we
further restricted our sample to venues that only changed one quality
variable (e.g., venues that only improved food while keeping decor and
service constant). Our analysis suggests that improving food leads to
price increases for unreviewed restaurants. In contrast, prices of
treated restaurants only respond to changes in decor and service.
However, higher prices are not necessarily reliable success indicators.
In fact, we find that higher prices are associated with a higher
likelihood of going out of business, especially in the top food quality
segment. This may be due to the close link between decor improvements
and price increases.
In order to test whether the improved food and decor quality is
based on real investments or on consumer-perception only, we examine
each restaurant's wine list investment by referring to Wine
Spectator restaurant wine list awards. We assume Wine Spectator awards
to be a good proxy variable for a restaurateur's willingness to
invest in nonfood ambience. Our analysis shows that Michelin-reviewed
restaurants are significantly more likely to receive wine lists awards
than do others.
When contrasting the difference-in-differences approach with a PSM
model we find, generally, very similar results.
Overall, our results suggest that expert opinion on the New York
City restaurant market opens up two paths for restaurants, improving
food quality or improving decor only. Both strategies are costly and may
raise prices. However, the market is more likely to accept food-induced
price increases than nonfood-induced ones. All other things equal,
decor- and service-oriented restaurants exhibit lower survival rates
than food-focused venues.
ABBREVIATIONS
2SLS: Two-Stage Least Squares
CV: Coefficient of Variation
IV: Instrumental Variable
ML: Maximum Likelihood
OLS: Ordinary Least Squares
OVB: Omitted Variable Bias
PSM: Propensity Score Matching
doi:10.1111/ecin.12178
APPENDIX: FIRST STAGE RESULTS
TABLE A1
First Stage Results for Full Sample
Food Equation Decor Equation
Michelin Michelin Michelin Michelin
dummy ordered dummy ordered
After (2006) 3.75 *** -0.57 *** 0.50 *** -0.61 ***
(12.74) (-3.07) (2.89) (-3.54)
Lagged dependent 1.31 *** -0.03 * 0.26 *** -0.06 ***
(15.38) (-1.73) (7.12) (-5.44)
Open after 11 p.m. -0.05 ** -0.05 *** -0.09 *** -0.04 ***
(-2.47) (-3.40) (-3.91) (-3.34)
No credit cards -0.18 *** -0.08 *** -0.10 *** -0.09 ***
accepted (-6.16) (-5.13) (-3.15) (-5.52)
Closed on Sunday -0.04 -0.04 ** -0.07 * -0.04 **
(-1.29) (-2.07) (-1.89) (-1.98)
Eastern EU 0.09 -0.01 0.01 -0.00
(0.57) (-0.07) (0.09) (-0.01)
Middle East -0.09 -0.13 ** -0.12 -0.13 **
(-1.15) (-2.28) (-1.45) (-2.31)
North America 0.11 0.01 0.02 0.02
(1.61) (0.25) (0.27) (0.37)
South America -0.02 -0.05 -0.06 -0.04
(-0.26) (-0.93) (-0.88) (-0.82)
Central America -0.02 -0.08 -0.08 -0.08
(-0.21) (-1.37) (-0.89) (-1.37)
Asian 0.00 -0.03 -0.01 -0.03
(0.02) (-0.58) (-0.18) (-0.57)
Others 0.07 -0.01 0.02 -0.01
(1.01) (-0.24) (0.24) (-0.24)
Western EU 0.06 -0.01 0.02 -0.00
(0.93) (-0.13) (0.31) (-0.04)
Africa 0.02 -0.03 -0.08 -0.02
(0.17) (-0.37) (-0.51) (-0.27)
Wine stores 0.00 0.00
(1.23) (1.03)
Poverty share -0.13 -0.16 ** -0.10 -0.18 **
(-0.92) (-1.97) (-0.76) (-2.28)
Geography 2.70 *** -0.42 * 3.10 *** -0.09
(2.85) (-1.67) (3.49) (-0.54)
Geography x After 1.26 4.73 *** 1.44 4.54 ***
(1.28) (4.36) (1.52) (4.19)
Limited no. reviews -0.15 *** 0.00 -0.15 *** 0.00
(-6.39) (0.57) (-6.25) (0.34)
Full service rest.
Constant -4.11 *** 0.24 ** -0.84 *** 0.28 ***
(-13.53) (2.55) (-4.37) (4.19)
Observations 2,476 2,476 2,474 2,474
R-squared 0.142 0.199 0.077 0.199
Uncentered R-squared 0.373 0.314 0.326 0.314
Service Equation Price Equation
Michelin Michelin Michelin Michelin
dummy ordered dummy ordered
After (2006) 1.91 *** -0.83 *** 0.94 *** -0.72 ***
(8.11) (-4.71) (5.49) (-4.28)
Lagged dependent 0.74 *** -0.13 *** 0.33 *** -0.08 ***
(11.03) (-6.12) (11.61) (-6.77)
Open after 11 p.m. -0.07 *** -0.05 *** -0.08 *** -0.05 ***
(-3.18) (-3.87) (-3.61) (-3.77)
No credit cards -0.09 *** -0.09 *** -0.06 * -0.10 ***
accepted (-2.92) (-5.69) (-1.89) (-5.95)
Closed on Sunday -0.06 * -0.06 *** -0.05 -0.06 ***
(-1.75) (-2.70) (-1.47) (-2.86)
Eastern EU 0.05 -0.02 0.01 -0.01
(0.34) (-0.18) (0.08) (-0.13)
Middle East -0.09 -0.14 ** -0.11 -0.14 *
(-1.15) (-2.40) (-1.33) (-2.39)
North America 0.06 0.01 0.04 0.01
(0.88) (0.21) (0.55) (0.27)
South America -0.03 -0.06 -0.05 -0.05
(-0.41) (-1.13) (-0.79) (-1.05)
Central America -0.04 -0.09 -0.06 -0.09
(-0.49) (-1.59) (-0.68) (-1.58)
Asian 0.00 -0.04 0.00 -0.04
(0.04) (-0.68) (0.01) (-0.70)
Others 0.05 -0.02 0.03 -0.02
(0.68) (-0.46) (0.47) (-0.44)
Western EU 0.03 -0.01 0.02 -0.01
(0.47) (-0.16) (0.26) (-0.10)
Africa -0.02 -0.05 -0.03 -0.05
(-0.15) (-0.55) (-0.18) (-0.57)
Wine stores
Poverty share
Geography 2.73 *** -0.57 ** 2.65 *** -0.52 **
(2.86) (-2.46) (2.83) (-2.30)
Geography x After 1.39 4.71 *** 1.67 * 4.61 ***
(1.50) (4.47) (1.81) (4.40)
Limited no. reviews -0.17 *** 0.01 -0.13 *** -0.00
(-6.92) (1.14) (-5.20) (-0.69)
Full service rest. 0.20 * 0.17 *** 0.17 0.18 ***
(1.80) (2.60) (1.49) (2.74)
Constant -2.36 *** 0.44 *** -1.39 *** 0.33 ***
(-9.23) (4.55) (-7.14) (4.25)
Observations 2,499 2,499 2,497 2,497
R-squared 0.101 0.203 0.098 0.204
Uncentered R-squared 0.345 0.318 0.343 0.319
Note: Base year 2003; for dummy vs. ordered treatment see text or
Table 3; robust t-statistics in parentheses.
*** p < 0.01; ** p < 0.05; * p < 0.1.
Source: Zagat Restaurant Guide New York City (2003, 2006), Michelin
Travel Publications (2005).
TABLE A2
First Stage Results for Restricted Paired Sample
Food Equation Decor Equation
Michelin Michelin Michelin Michelin
dummy ordered dummy ordered
After (2006) 4.72 *** -0.55 *** 0.80 *** -0.59 ***
(14.26) (-2.66) (5.20) (-3.24)
Lagged dependent 1.64 *** -0.05 * 0.34 *** -0.07 ***
(15.70) (-1.68) (6.67) (-4.71)
Open after 11 p.m. -0.07 ** -0.06 *** -0.10 *** -0.05 ***
(-2.24) (-3.07) (-3.29) (-2.89)
No credit cards -0.23 *** -0.10 *** -0.13 *** -0.11 ***
accepted (-6.01) (-4.67) (-3.19) (-4.76)
Closed on Sunday -0.08 * -0.06 * -0.11 * -0.06 **
(-1.73) (-2.31) (-2.29) (-2.31)
Eastern EU -0.01 -0.11 -0.08 -0.09
(-0.05) (-0.80) (-0.38) (-0.69)
Middle East -0.22 ** -0.23 *** -0.22 * -0.22 ***
(-2.20) (-3.79) (-1.99) (-3.79)
North America 0.07 -0.03 -0.00 -0.02
(0.84) (-0.59) (-0.04) (-0.36)
South America -0.08 -0.09 -0.10 -0.07
(-0.92) (-1.45) (-1.13) (-1.20)
Central America -0.12 -0.14 ** -0.13 -0.13 *
(-1.06) (-2.02) (-1.13) (-1.94)
Asian -0.10 -0.11 * -0.09 -0.10 *
(-1.20) (-1.83) (-0.97) (-1.73)
Others 0.01 -0.06 -0.03 -0.06
(0.15) (-1.13) (-0.33) (-1.06)
Western EU -0.03 -0.08 -0.06 -0.07
(-0.40) (-1.47) (-0.70) (-1.25)
Africa -0.07 -0.11 -0.11 -0.10
(-0.34) (-0.94) (-0.51) (-0.86)
Wine stores 0.01 * 0.00 *
(1.79) (1.93)
Poverty share -0.12 -0.08 -0.17 -0.15
(-0.62) (-0.81) (-0.88) (-1.43)
Geography 2.10 * -0.48 * 3.30 * * -0.14
(1.91) (-1.96) (3.10) (-0.62)
Geography x After 1.49 * 4.53 *** 0.77 4.42 ***
(2.01) (4.01) (1.57) (3.98)
Limited no. reviews -0.13 *** 0.01 -0.12 *** 0.01
(-3.40) (1.12) (-3.10) (0.71)
Full service rest.
Constant -4.89 *** 0.35 *** -0.91 *** 0.40 ***
(-13.12) (2.75) (-3.67) (4.87)
Observations 1,640 1,640 1.640 1,640
R-squared 0.171 0.248 0.102 0.248
Uncentered R-squared 0.459 0.378 0.414 0.378
Service Equation Price Equation
Michelin Michelin Michelin Michelin
dummy ordered dummy ordered
After (2006) 2.48 *** -0.85 *** 1.46 *** -0.69 ***
(9.65) (-4.29) (9.48) (-3.74)
Lagged dependent 0.89 *** -0.16 *** 0.45 *** -0.09 ***
(10.22) (-5.38) (12.23) (-5.58)
Open after 11 p.m. -0.08 *** -0.06 *** -0.10 *** -0.06 ***
(-2.77) (-3.33) (-3.30) (-3.18)
No credit cards -0.12 *** -0.11 *** -0.08 * -0.12 ***
accepted (-3.07) (-4.87) (-1.99) (-4.95)
Closed on Sunday -0.09 * -0.07 *** -0.08 -0.07 ***
(-1.83) (-2.56) (-1.58) (-2.66)
Eastern EU -0.03 -0.11 -0.05 -0.11
(-0.16) (-0.84) (-0.27) (-0.80)
Middle East -0.18 -0.23 *** -0.20 * -0.22 ***
(-1.63) (-3.88) (-1.87) (-3.80)
North America 0.04 -0.03 0.02 -0.03
(0.43) (-0.51) (0.28) (-0.51)
South America -0.06 -0.08 -0.07 -0.08
(-0.68) (-1.38) (-0.90) (-1.32)
Central America -0.09 -0.15 * -0.09 -0.15 **
(-0.77) (-2.10) (-0.82) (-2.08)
Asian -0.07 -0.11 * -0.06 -0.11 *
(-0.79) (-1.79) (-0.65) (-1.82)
Others 0.01 -0.07 0.00 -0.07
(0.14) (-1.19) (0.03) (-1.16)
Western EU -0.04 -0.08 -0.05 -0.07
(-0.49) (-1.35) (-0.63) (-1.29)
Africa -0.08 -0.12 -0.05 -0.12
(-0.36) (-1.00) (-0.22) (-1.06)
Wine stores
Poverty share
Geography 3.25 *** -0.42 * 3.03" * -0.38 *
(3.05) (-1.88) (2.90) (-1.72)
Geography x After 0.52 4.46 *** 0.86 4.37 ***
(1.03) (4.01) (1.48) (3.98)
Limited no. reviews -0.14 *** 0.01 * -0.06 -0.00
(-3.56) (1.65) (-1.57) (-0.11)
Full service rest. 0.29 * 0.17 ** 0.24 0.18 *
(1.92) (2.12) (1.64) (2.26)
Constant -2.81 *** 0.58 *** -1.78 *** 0.42 ***
(-8.57) (4.50) (-7.18) (4.11)
Observations 1,640 1,640 1,638 1,638
R-squared 0.127 0.249 0.132 0.249
Uncentered R-squared 0.430 0.380 0.433 0.379
Note: Base year 2003; for dummy vs. ordered treatment see text or
Table 3; robust t-statistics in parentheses.
*** p < 0.01; ** p < 0.05; * p < 0.1.
Source: Zagat Restaurant Guide New York City (2003, 2006), Michelin
Travel Publications (2005).
REFERENCES
Anderson, M., and J. Magruder. "Learning from the Crowd:
Regression Discontinuity Estimates of the Effects of an Online Review
Database." Economic Journal, 122(563), 2012, 957-89.
Ashenfelter, O., R. Goldstein, and C. Riddell. "Do Expert
Ratings Measure Quality? The Case of Restaurant Wine Lists."
Presentation at the 4th Annual Conference of the American Association of
Wine Economists, UC Davis, Mimeo, 2010.
Bagwell, K., and M. H. Riordan. "High and Declining Prices
Signal Product Quality." American Economic Review, 81, 1991,
224-39.
Bandura, A. Social Learning Theory. Englewood Cliffs, NJ: Prentice
Hall, 1977.
Banerjee, A. "A Simple Model of Herd Behavior." Quarterly
Journal of Economics, 107(3), 1992, 797-817.
Bauwens, L., and V. Ginsburgh. "Art Experts and Auctions. Are
Pre-Sale Estimates Unbiased and Fully Informative?" Louvain
Economic Review, 66, 2000, 131-44.
Becker, G. S. "A Note on Restaurant Pricing and Other Examples
of Social Influences on Price." Journal of Political Economy,
99(5), 1991, 1109-16.
Berry, S., and J. Waldfogel. "Product Quality and Market
Size." Journal of Industrial Economics, 58(1), 2010, 1-31.
Bikhchandani, S., D. Hirshleifer, and I. Welch. "A Theory of
Fads, Fashion, Custom, and Cultural Change as Informational
Cascades." Journal of Political Economy, 100(5), 1992, 992-1026.
--. "Learning from the Behavior of Others: Conformity, Fads,
and Informational Cascades." Journal of Economic Perspectives,
12(3), 1998, 151-70.
Cai, H., Y. Chen, and H. Fang. "Observational Learning:
Evidence from a Randomized Natural Field Experiment." American
Economic Review, 99(3), 2009, 864-82.
Caves, R. E., and D. P. Greene. "Brands' Quality Levels,
Prices, and Advertising Outlays: Empirical Evidence on Signals and
Information Cost." International Journal of Industrial
Organization, 14, 1996, 29-52.
Chossat, V., and O. Gergaud. "Expert Opinion and Gastronomy:
The Recipe for Success." Journal of Cultural Economics, 27, 2003,
127-41.
Cuozzo, S. "A Pinch of Bias Leaves Bitter Taste." New
York Post, November 2, 2005a.
--. "The Idiot's Guide: Michelin Diner Book Bites."
New York Post, November 7, 2005b.
Curry, D. J., and P. C. Riesz. "Prices and Price/Quality
Relationships: A Longitudinal Analysis." Journal of Marketing, 52,
1988, 36-51.
Davis, M. "A Taste of New York: Restaurant Reviews, Food
Discourse, and the Field of Gastronomy in America." Ph.D. thesis
(New York University, 2009). American Association of Wine Economists
AAWE, AAWE Working Paper No. 106, 2012.
Deutsch, M., and H. B. Gerard. "A Study of Normative and
Informational Social Influences upon Individual Judgment." Journal
of Abnormal and Social Psychology, 51, 1955, 629-36.
Dubois, P, and C. Nauges. "Identifying the Effect of
Unobserved Quality and Expert Reviews in the Pricing of Experience
Goods: Empirical Application on Bordeaux Wine." International
Journal of Industrial Organization, 28, 2010, 205-12.
Fabricant, F. "The Tire Man Eats New York." New York
Times, February 23, 2005a.
--. "Is New York Worth a Trip? Oui." New York Times,
November 2, 2005b.
Ferguson, P. P. "Michelin in America." Gastronomica,
8(1), 2008, 49-55.
Friberg, R., and E. Gronqvist. "Do Expert Reviews Affect the
Demand for Wine." American Economic Journal: Applied Economics,
4(1), 2012, 193-211.
Gergaud, O., L. Montano, and V. Verardi. "Stardust over Paris
Gastronomic Restaurants." Journal of Wine Economics, 2(1), 2007,
24-39.
Ginsburgh, V. "Awards, Success and Aesthetic Quality in the
Arts." Journal of Economic Perspectives, 17(2), 2003, 99-111.
Ginsburgh, V., and J. van Ours. "Expert Opinion and
Compensation: Evidence from a Musical Competition." American
Economic Review, 93, 2003, 289-96.
Griliches, Z. "Hybrid Com: An Exploration in the Economics of
Technical Change." Econometrica, 25(4), 1957, 501-22.
Hadj Ali, H., S. Lecocq, and M. Visser. "The Impact of Gurus:
Parker Grades and En Primeur Wine Prices." Economic Journal, 118,
2008, F158-73.
Heffetz, O., and M. Shayo. "How Large Are
Non-Budget-Constraint Effects of Prices on Demand?" American
Economic Journal: Applied Economics, 1(4), 2009, 170-99.
Hilger, J., G. Rafert, and S. Villas-Boas. "Expert Opinion and
the Demand for Experience Goods: An Experimental Approach in the Retail
Wine Market." Review of Economics and Statistics, 93(4), 2011,
1289-96.
Hodgson, R. T. "An Examination of Judge Reliability at a Major
U.S. Wine Competition." Journal of Wine Economics, 3(2), 2008,
105-13.
--. "An Analysis of the Concordance among 13 U.S. Wine
Competitions." Journal of Wine Economics, 4(1), 2009, 1-9.
Johnson, C., B. Surlemont, P. Nicod, and F. Revaz. "Behind the
Stars: A Concise Typology of Michelin Restaurants in Europe."
Cornell Hotel and Restaurant Administration Quarterly, 46(2), 2005,
170-87.
Kamenica, E. "Contextual Inference in Markets: On the
Informational Content of Product Lines." American Economic Review,
98(5), 2008, 2127-49.
Krummert, B. "Making a List, and Checking It Twice."
Restaurant Hospitality, October 31, 2006, p. 30.
Kurutz, S. "Neighborhood Report: Union Square; She's a
Belle of the City, but the French Are Blase." New York Times,
November 13, 2005.
Liu, Y. "Word of Mouth for Movies: Its Dynamics and Impact on
Box Office Revenues." Journal of Marketing, 70(3), 2006, 74-89.
McFadden, D. L., and K. Train. "Learning from Self and
Others." Journal of Political Economy, 104(4), 1996, 684-703.
Michelin Travel Publications. New York City 2006: Selection of
Restaurants and Hotels. Greenville, SC: Michelin Travel Publications,
2005.
Milgrom, P, and J. Roberts. "Price and Advertising Signals of
Product Quality." Journal of Political Economy, 94, 1986, 796-821.
Moretti, E. "Social Learning and Peer Effects in Consumption:
Evidence from Movie Sales." The Review of Economic Studies, 78(1),
2011, 356-93.
Morris, S., and H. S. Shin. "Social Value of Public
Information." American Economic Review, 92(5), 2002, 1521-34.
Nelson, P. "Information and Consumer Behavior." Journal
of Political Economy, 78, 1970, 311-29.
--. "Advertising as Information." Journal of Political
Economy, 81, 1974, 729-54.
North, A., D. Hargreaves, and J. McKendrick. "The Influence of
In-Store Music on Wine Selections." Journal of Applied Psychology,
84(2), 1999, 271-76.
Plassmann, H., J. O'Doherty, B. Shiv, and A. Rangel.
"Marketing Actions Can Modulate Neural Representations of
Experienced Pleasantness." Proceedings of the National Academy of
Sciences of the United States of America, 105(3), 2008, 1050-54.
Reinstein, D. A., and C. M. Snyder. "The Influence of Expert
Reviews on Consumer Demand for Experience Goods: A Case Study of Movie
Critics." Journal of Industrial Economics, 53(1), 2005, 27-51.
Riesz, P. C. "Price Versus Quality in the Market Place."
Journal of Retailing, 58, 1978, 15-28.
Roberts, P, and R. Reagans. "Critical Exposure and
Price-Quality Relationships in the U.S. Market." Journal of Wine
and Economics, 2, 2007, 84-97.
Rosenbaum, P., and D. B. Rubin. "The Central Role of the
Propensity Score in Observational Studies for Causal Effects."
Biometrika, 70(1), 1983, 41-55.
Rosenman, R. R.. and W. W. Wilson. "Quality Differentials and
Prices: Are Cherries Lemons?" Journal of Industrial Economics,
39(6), 1991, 649-58.
Salganik, M. J., P. S. Dodds, and D. J. Watts. "Experimental
Study of Inequality and Unpredictability in an Artificial Cultural
Market." Science, 311, 2006, 854-6.
Schmalensee, R. "A Model of Advertising and Product
Quality." Journal of Political Economy, 86, 1978, 485-503.
Schnabel, H., and K. Storchmann. "Prices as Quality Signals:
Evidence from the Wine Market." Journal of Agricultural & Food
Industrial Organization, 8, 2010, Article 2.
Shapiro, C. "Premiums for High Quality Products as Returns to
Reputation." Quarterly Journal of Economics, 98, 1983, 659-80.
Snyder, W., and M. Cotter. "The Michelin Guide and Restaurant
Pricing Strategies." Journal of Restaurant & Foodservice
Marketing, 3(1), 1998, 51-67.
Stock, J. H., and M. Yogo "Testing for Weak Instruments in
Linear IV Regression," in Identification and Inference for
Econometric Models: Essays in Honor of Thomas Rothenberg, edited by D.
W. K. Andrews and J. H. Stock. Cambridge: Cambridge University Press,
2005, 80-108.
Tellis, G. J., and B. Wernerfelt. "Competitive Price and
Quality under Asymmetric Information." Marketing Science, 6, 1987,
240-53.
Tirole, J. "A Theory of Collective Reputations (with
Applications to the Persistence of Corruption and to Firm
Quality)." Review of Economic Studies, 63, 1996, 1-22.
Tversky, A., and D. Kahneman. "The Framing of Decisions and
the Psychology of Choice." Science, 30(211), 1981, 453-58.
Wansink, B., D. R. Just, and C. R. Payne. "Mindless Eating and
Healthy Heuristics for the Irrational." American Economic Review,
Papers and Proceedings, 99(2), 2009, 165-9.
Wine Spectator. "Restaurant Wine Lists Awards. Entry Guide
2013." 2012. Accessed November 23, 2012. http://
www.winespectator.com/group/show/id/rest_awards_entry _guidelines
Wolinsky, A. "Prices as Signals of Product Quality."
Review of Economic Studies, 50, 1983, 647-58.
Zagat Survey. New York City Restaurants 2004. New York: Zagat
Survey, 2003.
--. New York City Restaurants 2005. New York: Zagat Survey, 2004.
--. New York City Restaurants 2007. New York: Zagat Survey, 2006.
--. New York City Restaurants 2008. New York: Zagat Survey, 2007.
(1.) On average, about 650,000 copies of the New York City guide
are sold per year. In addition, Zagat reports 384,000 unique visitors to
its paid online subscription service for 2008 (Davis 2012).
(2.) For a comprehensive overview of New York City restaurant
reviews, their history, focus, and impact, see Davis (2012).
(3.) See, e.g., Florence Fabricant in the New York Times (Fabricant
2005a).
(4.) Mario Batali, a Rutgers University economics major, is the
chef and owner of New York City icon restaurant Babbo. He is best known
for his Food Network show Motto Mario and his role in Iron Chef America.
(5.) In contrast to national restaurant guides, Zagat ratings
reflect the vote of the local population and are based on a local
reference. Therefore, Zagat ratings are not comparable across cities and
rather denote a local ranking (see also Berry and Waldfogel 2010).
(6.) Peer or social learning models are related to the earlier
literature on technology adoption, where the spreading of new
technologies is based on peer imitation (e.g., Griliches 1957).
(7.) The publication of the first New York City Michelin guide was
announced in February of 2005.
(8.) These categories are the following: Afghan, American New,
American Regional, American Traditional, Argentinean, Asian, Australian,
Austrian, Bakeries, Barbecue, Belgian, Brasserie, Brazilian, Burmese,
Cajun/Creole, Californian, Caribbean, Chinese, Coffeehouses/Dessert,
Coffee Shops/Diners, Colombian, Continental, Cuban, Delis/Sandwich
Shops, Dim Sum, Dominican, Dutch, Eastern European,
Eclectic/International, Egyptian, English, Eritrean, Ethiopian,
Filipino, Fish 'n' Chips, French, French Bistro, French New,
German, Greek, Hamburgers, Health Food, Hot Dogs, Hungarian, Indian,
Indonesian, Irish, Israeli, Italian, Jamaican, Japanese, Jewish, Korean,
Lebanese, Malaysian, Mediterranean, Mexican/Tex-Mex, Middle Eastern,
Moroccan, Noodle Shops, Nuevo Latino, Persian, Peruvian, Pizza, Polish,
Portuguese, Puerto Rican, Russian. Sandwich Shop, Scandinavian,
Scottish, Seafood, Soups, South African, South American, Southem/Soul,
South Western, Spanish, Steakhouses, Swiss, Tapas, Tea Service, Thai,
Tibetan, Tunisian, Turkish, Ukrainian, Vegetarian, Venezuelan, and
Vietnamese.
(9.) The New York Times quotes Jean-Luc Naret, the director of the
Michelin Guides, "Michelin stars refer only to what is on the
plate" (Fabricant 2005a).
(10.) We calculate the CV as standard deviation to the mean, CV =
[sigma]/[mu]
(11.) Zagat reports if a restaurant receives only a low number of
reviews.
(12.) Aside from these clusters, there is only one isolated
Michelin-reviewed restaurant in Forest Hills, Queens.
(13.) There are 176 ZIP codes in New York City.
(14.) The coordinates are available in decimal degrees from
www.maporama.com and are converted into distances (km) to the equator
and to the Greenwich meridian using the formula: distance = (6378.137 x
[pi] x degrees) /180
(15.) The maximum distance between two restaurants is little
informative since it merely reports the spatial spread of restaurants in
New York City. Similarly, the minimum distance is virtually zero for
adjacent restaurants. The largest minimum distance gives us an idea of
the minimal radius needed for all restaurants to have at least one
neighbor. The smallest maximum distance, however, reflects the spatial
spread of restaurants compared to the central restaurant.
(16.) The distance of 10 km was selected to ensure that each
restaurant has at least one neighbor.
(17.) In addition, there are restaurants that operated in both
years but had one dependent or independent variable missing in one of
the years.
(18.) The First Stage results are reported in Table A2.
(19.) There are no statistically significant differences between
the mean prices of the two samples.
(20.) However, as prices are self-reported, we cannot rule out that
the price effect results from structural changes, i.e., due to a higher
restaurant rating diners may substitute more expensive meal items for
less expensive ones.
(21.) Chossat and Gergaud (2003) use comparable data to instrument
Gault-Millau decor ratings.
OLIVIER GERGAUD, KARL STORCHMANN and VINCENZO VERARDI *
* We would like to thank two anonymous reviewers and the editor,
Wesley Wilson, for many helpful comments that have helped to
substantially improve this paper. We are also indebted to seminar
participants at the Free University of Bolzano, University of Reims,
Institut Paul Bocuse, Inra Grenoble (GAEL). Olivier Gergaud gratefully
acknowledges financial support from the European Institute for Social
Sciences and Humanities--Lille Nord de France (Project DEAC--Dynamiques
de l'Economie de l'Art et de la Culture); Vincenzo Verardi
gratefully acknowledges financial support from FNRS. We also thank
Maurice Gergaud for helping to gather and code the data and Ralf
Powierski for creating the map in Figure 1.
Gergaud: Department of Finance and Economics, KEDGE Business
School, Talence 33405, France; CRED, University of Paris 2, France.
Phone + 33 (0) 326 08 22 35, E-mail olivier.gergaud@kedgebs.com
Storchmann: Economics Department, New York University, New York, NY
10012; Department of Finance and Economics, KEDGE Business School,
Talence 33405, France. Phone 212-992-8083, Fax 212-995-4186, E-mail
karl.storchmann@nyu.edu
Verardi: Department of Economics, CRED, University de Namur and
FNRS, Namur, 5000 Belgium. Phone +32 (0)81 7241
ll.E-mailvverardi@ulb.ac.be
TABLE 1
Descriptive Statistics Food, Service, Decor Quality, and Price:
Treatment and Nontreatment Group 2003 and 2006
Number of Mean Std. Dev.
observations (CV in %)
Food
All 2003 1497 20.46 2.82(13.8)
All 2006 1516 20.97 2.58(12.3)
Control 2003 1128 19.75 2.55(12.9)
Control 2006 1094 20.34 2.55(12.5)
Treatment 2003 369 22.66 2.42(10.7)
Treatment 2006 422 22.59 2.42(10.7)
Service
All 2003 1497 18.20 3.17(17.4)
All 2006 1518 18.47 3.08(16.7)
Control 2003 1128 17.55 2.95 (16.8)
Control 2006 1096 17.77 2.85(16.0)
Treatment 2003 369 20.19 3.00(14.9)
Treatment 2006 422 20.27 2.93(14.5)
Decor
All 2003 1494 16.63 4.58(27.5)
All 2006 1517 16.79 4.50 (26.9)
Control 2003 1125 15.84 4.41 (27.8)
Control 2006 1096 15.90 4.38 (27.6)
Treatment 2003 369 19.04 4.24 (22.3)
Treatment 2006 421 19.10 3.95 (20.7)
Price
All 2003 1497 38.14 14.94 (39.1)
All 2006 1515 40.69 20.64 (50.7)
Control 2003 1128 34.81 12.74 (36.6)
Control 2006 1094 35.81 13.84 (38.7)
Treatment 2003 369 48.34 16.50 (34.1)
Treatment 2006 421 53.36 28.54 (53.5)
Minimum Maximum
Food
All 2003 9 28
All 2006 10 29
Control 2003 9 28
Control 2006 9 28
Treatment 2003 15 28
Treatment 2006 16 28
Service
All 2003 8 30
All 2006 8 29
Control 2003 8 30
Control 2006 8 29
Treatment 2003 10 27
Treatment 2006 10 29
Decor
All 2003 1 28
All 2006 3 29
Control 2003 1 28
Control 2006 3 29
Treatment 2003 5 28
Treatment 2006 5 28
Price
All 2003 5 185
All 2006 5 446
Control 2003 5 93
Control 2006 5 142
Treatment 2003 16 185
Treatment 2006 16 446
Mean comparison t-tests control treatment: Food 2003: 19.27; 2006:
15.62; Service 2003: 14.86, 2006: 15.19; Decor 2003: 10.77, 2006:
13.08; Price 2003: 16.39, 2006: 16.89 (all significant at 1% level).
Source: Zagat Restaurant Guide New York City (2003, 2006), Michelin
Travel Publications (2005).
TABLE 2
Percentage Change in Quality and Price from
2003 to 2006: Treatment and Control Group
Food Control 2.99
Treatment -0.31
Service Control 1.25
Treatment 0.40
Decor Control 0.38
Treatment 0.21
Price Control 2.87
Treatment 10.38
Source: Zagat Restaurant Guide New York City (2003,
2006), Michelin Travel Publication (2005).
TABLE 3
OLS Difference-in-Differences Equations of Perceived Quality
(2003-2006), Full Sample, Treatment: Michelin 2005
Dummy Treatment
Food Decor Service
Michelin 0.00 ** 0.00 0.00
(2.15) (0.51) (0.57)
Michelin x After 0.10 *** 0.18 *** 0.12 ***
(16.20) (12.76) (13.64)
After (2006) 2.88 *** 2.44 *** 2.58 ***
(147.46) (60.66) (82.16)
Lagged Dependent(2003) 0.96 *** 0.90 *** 0.90 ***
(152.54) (66.46) (84.01)
Open after 11 p.m. -0.02 *** -0.00 -0.03 ***
(-5.40) (-0.10) (-5.41)
No credit cards accepted 0.02 *** -0.16 *** -0.06 ***
(4.45) (-7.89) (-6.87)
Closed on Sunday -0.03 *** -0.03 *** -0.04 ***
(-6.11) (-2.73) (-6.25)
Limited no. reviews (2003) -0.00 ** -0.00 -0.00
(-2.51) (-0.35) (-0.46)
Constant 0.17 *** 0.28 *** 0.34 ***
(7.03) (6.10) (9.44)
Food ethnicity fixed effects Yes Yes Yes
Observations 3,012 3,010 3,014
R-squared 0.65 0.61 0.57
Ordered Treatment
Food Decor Service
Michelin 0.00 ** 0.00 0.00
(2.37) (0.55) (0.58)
Michelin x After 0.09 *** 0.16 *** 0.11 ***
(19.52) (14.83) (16.64)
After (2006) 2.88 *** 2.45 *** 2.58 ***
(151.28) (61.15) (84.11)
Lagged Dependent(2003) 0.96 *** 0.90 *** 0.90 ***
(156.20) (66.98) (86.02)
Open after 11 p.m. -0.02 *** -0.00 -0.03 ***
(-5.45) (-0.10) (-5.41)
No credit cards accepted 0.02 *** -0.16 *** -0.06 ***
(4.49) (-7.91) (-6.87)
Closed on Sunday -0.02 *** -0.03 ** -0.04 ***
(-5.63) (-2.43) (-5.85)
Limited no. reviews (2003) -0.00 ** -0.00 -0.00
(-2.40) (-0.32) (-0.48)
Constant 0.17 *** 0.28 *** 0.33 ***
(7.06) (6.02) (9.34)
Food ethnicity fixed effects Yes Yes Yes
Observations 2,475 2,473 2,498
R-squared 0.64 0.60 0.56
Note: Dependent variable: In of perceived quality; Dummy Treatment: 0
= not in Michelin, 1 = in Michelin-, Ordered Treatment: 0 = not in
Michelin, 1 =in Michelin but no stars, 2 = one star, 3 = two stars, 4
= three stars; robust z-statistics in parentheses; z-statistics are
based on restaurant-clustered standard errors.
*** p < 0.01 ; ** p < 0.05; * < 0.1.
Source: Zagat Restaurant Guide New York City (2003, 2006), Michelin
Travel Publications (2005).
TABLE 4
2SLS Difference-in-Differences Equations of Perceived Quality
(2003-2006), Full Sample, Treatment: Michelin 2005
Dummy Treatment
Food Decor Service
Michelin 0.01 0.00 -0.00
(1.24) (0.17) (-0.37)
Michelin x After 0.05 0.39 *** 0.03
(0.89) (2.75) (0.44)
After (2006) 2.87 *** 2.47 *** 2.61 ***
(69.23) (51.81) (56.71)
Lagged dependent 0.95 *** 0.92 *** 0.90 ***
(67.99) (50.65) (47.47)
Open after 11 p.m. -0.02 *** 0.02 -0.03 ***
(-5.08) (1.61) (-4.82)
No credit cards accepted 0.02 ** -0.15 *** -0.08 ***
(2.42) (-5.38) (-6.04)
Closed on Sunday -0.02 *** -0.01 -0.04 ***
(-4.52) (-0.59) (-5.44)
Constant 0.21 *** 0.20 *** 0.35 ***
(4.45) (3.08) (5.65)
Food ethnicity fixed effects Yes Yes Yes
Observations 2,476 2,474 2,499
R-squared 0.644 0.557 0.597
Kleibergen-Paap rk (LM) 30.747 27.313 29.898
p value 0.000 0.000 0.000
Kleibergen-Paap stat. 7.618 9.114 9.712
IV relative bias 10%-20% 5%-10% 5%-10%
Hansen's overid. test 4.764 0.168 1.924
p value 0.190 0.920 0.382
Ordered Treatment
Food Decor Service
Michelin 0.01 0.00 -0.00
(1.23) (0.21) (-0.37)
Michelin x After 0.03 0.29 *** 0.03
(0.80) (2.82) (0.46)
After (2006) 2.87 *** 2.48 *** 2.61 ***
(70.19) (53.18) (56.27)
Lagged dependent 0.95 *** 0.92 *** 0.90 ***
(68.06) (51.39) (48.04)
Open after 11 p.m. -0.02 *** 0.01 -0.03 ***
(-5.51) (1.46) (-5.11)
No credit cards accepted 0.02 ** -0.15 *** -0.08 ***
(2.45) (-6.03) (-6.42)
Closed on Sunday -0.02 *** -0.00 -0.04 ***
(-4.34) (-0.34) (-5.26)
Constant 0.21 *** 0.20 *** 0.35 ***
(4.48) (3.39) (5.77)
Food ethnicity fixed effects Yes Yes Yes
Observations 2,476 2,474 2,499
R-squared 0.648 0.588 0.599
Kleibergen-Paap rk (LM) 38.839 35.311 35.813
p value 0.000 0.000 0.000
Kleibergen-Paap stat. 9.410 11.158 11.412
IV relative bias 5%-10% 0%-5% 0%-5%
Hansen's overid. test 4.863 0.186 1.911
p value 0.182 0.911 0.385
Note: Dependent variable: In of perceived quality; for dummy vs.
ordered treatment see text or Table 3; robust z-statistics are based
on restaurant-clustered standard errors.
*** p < 0.01; ** p < 0.05; * p < 0.1.
Source: Zagat Restaurant Guide New York City (2003, 2006), Michelin
Travel Publications (2005).
TABLE 5
OLS Difference-in-Differences Equations of Perceived Quality
(2003-2006), Restricted Paired Sample, Treatment: Michelin 2005
Dummy Treatment
(1) (2) (3)
Food Decor Service
Michelin 0.00 ** -0.00 0.00
(2.33) (-0.37) (0.06)
Michelin x After 0.11 *** 0.20 *** 0.13 ***
(15.92) (12.57) (14.14)
After (2006) 2.84 *** 2.38 *** 2.51 ***
(107.84) (45.54) (58.82)
Lagged dependent (2003) 0.95 *** 0.89 *** 0.88 ***
(111.54) (50.64) (60.74)
Open after 11 p.m. -0.02 *** -0.01 -0.03 ***
(-4.44) (-0.87) (-4.91)
No credit cards accepted 0.03 *** -0.17 *** -0.07 ***
(4.28) (-6.98) (-6.77)
Closed on Sunday -0.03 *** -0.03 ** -0.04 ***
(-5.69) (-2.07) (-5.79)
Limited no. reviews (2003) -0.00 0.00 0.00
(-1.48) (0.44) (1.07)
Constant 0.20 *** 0.30 *** 0.39 ***
(6.44) (5.24) (8.19)
Food ethnicity fixed effects Yes Yes Yes
Observations 2,062 2,062 2,062
R-squared 0.628 0.641 0.649
Ordered Treatment
(4) (5) (6)
Service Decor Service
Michelin 0.00 ** -0.00 0.00
(2.56) (-0.32) (0.08)
Michelin x After 0.10 *** 0.18 *** 0.12 ***
(17.96) (13.65) (16.49)
After (2006) 2.85 *** 2.39 *** 2.52 ***
(110.79) (45.79) (60.22)
Lagged dependent (2003) 0.95 *** 0.89 *** 0.89 ***
(114.35) (50.80) (62.21)
Open after 11 p.m. -0.02 *** -0.01 -0.03 ***
(-4.48) (-0.84) (-4.91)
No credit cards accepted 0.03 *** -0.17 *** -0.07 ***
(4.29) (-7.03) (-6.82)
Closed on Sunday -0.03 *** -0.02 * -0.04 ***
(-5.28) (-1.79) (-5.48)
Limited no. reviews (2003) -0.00 0.00 0.00
(-1.43) (0.46) (1.06)
Constant 0.19 *** 0.29 *** 0.37 ***
(6.37) (5.12) (8.03)
Food ethnicity fixed effects Yes Yes Yes
Observations 2,058 2,058 2,058
R-squared 0.645 0.644 0.661
Note: Dependent variable: In of perceived quality; for dummy vs.
ordered treatment see text or Table 3; robust z-statistics are based
on restaurant-clustered standard errors.
*** p < 0.01; ** p < 0.05; * p < 0.1.
Source: Zagat Restaurant Guide New York City (2003, 2006), Michelin
Travel Publications (2005).
TABLE 6
2SLS Difference-in-Differences Equations of Perceived Quality
(2003-2006), Restricted Paired Sample, Treatment: Michelin 2005
Dummy Treatment
Food Decor Service
Michelin -0.00 0.01 -0.02
(-0.08) (0.26) (-1.06)
Michelin x After 0.20 *** 0.22 0.08
(2.66) (1.12) (0.88)
After (2006) 2.85 *** 2.42 *** 2.60 ***
(30.55) (33.26) (36.04)
Lagged dependent 0.96 *** 0.90 *** 0.90 ***
(28.93) (30.21) (30.39)
Open after 11 p.m. -0.02 *** 0.00 -0.03 ***
(-2.69) (0.32) (-3.78)
No credit cards accepted 0.04 *** -0.16 *** -0.038 ***
(3.68) (-4.59) (-5.33)
Closed on Sundays -0.02 ** -0.01 -0.05 ***
(-2.55) (-0.56) (-4.60)
Constant 0.16 0.26 ** 0.35 ***
(1.54) (2.49) (3.67)
Food ethnicity fixed effects Yes Yes Yes
Observations 1,638 1,638 1,638
R-squared 0.580 0.644 0.626
Kleibergen-Paap rk (LM) 19.384 20.892 19.462
p value 0.001 0.000 0.000
Kleibergen-Paap stat. 5.238 5.546 6.112
IV relative bias 20%-30% 10%-20% IO%-20%
Hansen's overid. test 3.554 3.474 0.731
p value 0.314 0.176 0.694
Ordered Treatment
Food Decor Service
Michelin -0.00 0.01 -0.02
(-0.20) (0.26) (-1.06)
Michelin x After 0.16 *** 0.18 0.07
(2.75) (1.11) (0.93)
After (2006) 2.88 *** 2.43 *** 2.60 ***
(32.30) (34.05) (35.80)
Lagged dependent 0.96 *** 0.90 *** 0.90 ***
(30.16) (30.13) (30.40)
Open after 11 p.m. -0.02 *** 0.00 -0.03 ***
(-3.33) (0.22) (-4.04)
No credit cards accepted 0.03 *** -0.17 *** -0.08 ***
(3.73) (-4.92) (-5.64)
Closed on Sundays -0.02 ** -0.01 -0.05 ***
(-1.97) (-0.28) (-4.11)
Constant 0.14 0.26 ** 0.35 ***
(1.44) (2.46) (3.64)
Food ethnicity fixed effects Yes Yes Yes
Observations 1,640 1,640 1,640
R-squared 0.623 0.650 0.632
Kleibergen-Paap rk (LM) 23.523 20.488 19.779
p value 0.000 0.000 0.000
Kleibergen-Paap stat. 5.629 5.640 6.224
IV relative bias 20%-30% 10%-20% 10%-20%
Hansen's overid. test 4.548 3.470 0.763
p value 0.208 0.176 0.683
Note: Dependent variable: In of perceived quality; for dummy vs.
ordered treatment see text or Table 3; robust z-statistics in
parentheses; z-statistics are based on restaurant-clustered standard
errors.
*** p < 0.01; ** p < 0.05; * p < 0.1.
Source: Zagat Restaurant Guide New York City (2003, 2006), Michelin
Travel Publications (2005).
TABLE 7
Restaurant Closures in 2007, Probit Equations
(1) (2) (3)
Zagat-Food rating -0.13 *** -0.14 ***
(-5.18) (-5.44)
Zagat-Decor rating 0.03 **
(1.96)
Zagat-Service rating 0.05 *
(1.77)
Michelin-Dummy -0.31 **
(-2.41)
Limited no. reviews 1.15 *** 1.12 *** 1.02 ***
(6.38) (6.55) (5.73)
Open after 11 p.m. -0.34 *** -0.25 ** -0.25 **
(-2.65) (-2.07) (-2.11)
No credit cards accepted 0.31 0.34 * 0.06
(1.53) (1.69) (0.31)
Closed on Sunday -0.36 ** -0.31 * -0.26
(-2.06) (-1.74) (-1.55)
Middle Eastern 1.34 *** 1.04 ** 1.21 **
(2.60) (2.37) (2.33)
North American 0.42 0.33 0.63 **
(1.23) (1.25) (1.98)
South American -0.47 -0.46 -0.36
(-0.82) (-0.83) (-0.64)
Central American 0.64 0.55 0.65
(1.53) (1.54) (1.59)
Asian 0.52 0.40 0.44
(1.44) (1.34) (1.26)
West European 0.28 0.23 0.34
(0.83) (0.88) (1.07)
African 0.27 0.21 0.46
(0.41) (0.33) (0.69)
Constant 0.72 0.72 -1.45 ***
(1.05) (1.05) (-3.90)
Observations 1,055 1.145 1.055
Pseudo [R.sup.2] 0.135 0.106 0.108
Note: Dependent variable: closed=l, not closed = 0;
robust s-statistics in parentheses.
*** p < 0.01; * p < 0.05; * p < 0.1.
Source: Zagat Restaurant Guide New York City (2007).
TABLE 8
2SLS Difference-in-Differences Equations for Perceived Quality
(2004-2006), Restricted Paired Sample, Treatment: Michelin 2005
Dummy Treatment
Food Decor Service
Michelin 0.02 0.01 0.01
(1.22) (0.15) (0.61)
Michelin x After 0.15 ** 0.35 ** 0.03
(2.43) (2.08) (0.37)
After (2006) 2.84 *** 2.40 *** 2.66 ***
(33.10) (33.43) (34.17)
Lagged dependent 0.95 *** 0.90 *** 0.91 ***
(32.63) (31.13) (30.42)
Open after 11 p.m. -0.02 *** 0.01 -0.03 ***
(-3.63) (1.14) (-4.40)
No credit cards accepted 0.03 *** -0.16 *** -0.09 ***
(3.31) (-4.37) (-5.25)
Closed on Sundays -0.02 *** -0.01 -0.05 ***
(-3.15) (-0.53) (-5.78)
Constant 0.18 ** 0.22 ** 0.31 ***
(2.06) (2.44) (3.42)
Food ethn. fixed effects Yes Yes Yes
Observations 1,774 1,774 1,774
R-squared 0.600 0.596 0.609
Kleibergen-Paap rk (LM) 26.757 27.665 20.478
p value 0.000 0.000 0.000
Kleibergen-Paap stat. 5.095 6.055 6.189
IV relative bias 20%-30% 5%-10% 10%-20%
Hansen's overid. test 4.756 2.245 6.485
p value 0.191 0.325 0.039
Ordered Treatment
Food Decor Service
Michelin 0.02 -0.00 0.01
(1.11) (-0.03) (0.60)
Michelin x After 0.12 ** 0.30 ** 0.03
(2.27) (2.14) (0.41)
After (2006) 2.86 *** 2.41 *** 2.67 ***
(35.37) (34.44) (34.37)
Lagged dependent 0.95 *** 0.91 *** 0.91 ***
(34.49) (30.90) (30.31)
Open after 11 p.m. -0.02 *** 0.01 -0.03 ***
(-4.07) (1.10) (-4.51)
No credit cards accepted 0.03 *** -0.17 *** -0.09 ***
(3.22) (-4.79) (-5.57)
Closed on Sundays -0.02 *** -0.00 -0.05 ***
(-2.56) (-0.09) (-5.13)
Constant 0.18 ** 0.22 ** 0.30 ***
(2.08) (2.45) (3.39)
Food ethn. fixed effects Yes Yes Yes
Observations 1.782 1.778 1,778
R-squared 0.638 0.603 0.619
Kleibergen-Paap rk (LM) 29.714 28.680 23.342
p value 0.000 0.000 0.000
Kleibergen-Paap stat. 4.911 6.098 6.172
IV relative bias 20%-30% 5%-10% 10%-20%
Hansen's overid. test 6.050 1.697 6.684
p value 0.109 0.428 0.035
Note: Dependent variable: ln of perceived quality; for dummy vs.
ordered treatment see text or Table 3; robust z-statistics in
parentheses; z-statistics are based on restaurant-clustered standard
errors.
*** p < 0.01; ** p < 0.05; * p < 0.1.
Source: Zagat Restaurant Guide New York City (2004, 2006), Michelin
Travel Publications (2005).
TABLE 9
2SLS Difference/in/Differences Equations for Prices (2003/4-2006),
Restricted Paired Sample
Dummy Treatment
Base year 2003 Base year 2004
Michelin 0.08 0.12 *
(1.12) (1.71)
Michelin x After 0.38 ** 0.41 **
(2.04) (2.31)
After (2006) 2.85 *** 3.08 ***
(19.28) (19.89)
Lagged dependent 0.81 *** 0.86 ***
(17.14) (19.18)
Open after 11 p.m. 0.01 0.01
(0.87) (0.42)
No credit cards accepted -0.21 *** -0.20 ***
(-6.19) (-6.07)
Closed on Sunday -0.10 *** -0.10 ***
(-4.12) (-4.31)
Constant 0.73 *** 0.46 ***
(4.18) (2.93)
Food ethnicity fixed effects Yes Yes
Observations 1,638 1,774
R-squared 0.637 0.626
Kleibergen-Paap rk (LM statistic) 14.690 14.470
p value 0.002 0.002
Kleibergen-Paap stat. 5.784 5.480
IV relative bias 10%-20% 10%-20%
Hansen's overidentification test 1.004 1.786
p value 0.605 0.409
Ordered Treatment
Base year 2003 Base year 2004
Michelin 0.08 0.10
(1.15) (1.54)
Michelin x After 0.31 * 0.33 **
(1.94) (2.19)
After (2006) 2.86 *** 3.10 ***
(19.71) (20.97)
Lagged dependent 0.81 *** 0.86 ***
(17.29) (19.41)
Open after 11 p.m. 0.01 0.01
(0.75) (0.39)
No credit cards accepted -0.22 *** -0.21 ***
(-6.73) (-6.76)
Closed on Sunday -0.09 *** -0.09 ***
(-3.56) (-3.71)
Constant 0.73 *** 0.46 ***
(4.18) (2.91)
Food ethnicity fixed effects Yes Yes
Observations 1,638 1,774
R-squared 0.660 0.667
Kleibergen-Paap rk (LM statistic) 15.010 15.529
p value 0.002 0.001
Kleibergen-Paap stat. 5.817 5.338
IV relative bias 10%-20% 20%-25%
Hansen's overidentification test 1.059 1.633
p value 0.589 0.442
Note: Dependent variable: ln of prices; for dummy vs. ordered
treatment see text or Table 3; treatment: Michelin 2005; robust
z-statistics in parentheses; z-statistics are based on
restaurant-clustered standard errors.
*** p < 0.01; ** p < 0.05; * p < 0.1.
Source: Zagat Restaurant Guide New York City (2003, 2004, 2006),
Michelin Travel Publications (2005).
TABLE 10
Determinants of Price Changes, Dependent Variable: Nominal Price
Change from 2003 to 2006
Not Michelin Reviewed
Independent Variable All Restricted
sample (a)
Change in food quality (t) 0.008 (0.10) -0.028 (-0.23)
(obs. mean price 2003) (702; $33.60) (388, $34.81)
Change in decor quality (t) 0.093(1.39) -0.028 (-0.22)
(obs. mean price 2003) (702; $33.60) (373; $34.92)
Change in service quality (t) 0.063 (0.81) 0.065 (0.48)
(obs, mean price 2003) (702; $33.60) (385; $35.00)
Michelin Reviewed
Independent Variable All Restricted
sample (a)
Change in food quality (t) 0.452 * (1.98) 0.564 * (2.11)
(obs. mean price 2003) (331; $49.54) (189; $48.12)
Change in decor quality (t) 0.379 *** (2.67) 0.248 (0.88)
(obs. mean price 2003) (331; $49.54) (180; $48.07)
Change in service quality (t) 0.544 *** (2.81) 0.723 *** (2.61)
(obs, mean price 2003) (331; $49.54) (203; $48.92)
Note: All equations contain a constant term, a complete set of food
fixed effects and controls for "no credit cards accepted," "open after
11 pm" and "low response" (not reported here); robust f-statistics,
number of observations and mean 2003 price in parentheses.
(a) The sample is restricted to observations with no change for all
other Zagat quality variables. For instance, the impact of food
quality changes is measured for restaurants that have not changed
their service and decor quality from 2003 to 2006.
Significance + (8%), * (5%), ** (2%), *** (1%).
Source: Zagat Restaurant Guide New York City (2003, 2006), Michelin
Travel Publications (2005).
TABLE 11
Prices and Restaurant Closures in 2007 Probit Equations
Food Quality Quartiles
(Zagat Food Points)
Q1 superior Q2 above average
(Zagat > 22) (Zagat 21-22)
Price-squared (x 1000) 0.0638 *** 0.1705
(2.83) (1.46)
Michelin dummy -0.755 *** -0.199
(-2.65) (-0.73)
Observations 254 297
Pseudo-[R.sup.2] 0.175 0.183
Food Quality Quartiles
(Zagat Food Points)
Q3 below average Q4 inferior
(Zagat 19-20) (Zagat < 19)
Price-squared (x 1000) 0.0408 -0.0249
(0.31) (-0.15)
Michelin dummy -0.131 n.a.
(-0.52)
Observations 287 152
Pseudo-[R.sup.2] 0.089 0.062
Notes: Closed = 1, not closed = 0; robust z-statistics in parentheses.
All equations contain a constant term and a full set of food ethnicity
fixed effects, as well as a dummy for open after 11 p.m., no credit
card acceptance, closed on Sundays, and limited reviews (not reported
here).
*** p < 0.01.
Source: Zagat Restaurant Guide New York City (2007).
TABLE 12
2SLS Difference-in-Differences Equations for
Investments (2003-2006), Dependent Variable:
Wine Spectator Award; Two-Step Estimation;
Second Step Is an ML-Ordered Probit
Dummy treatment Ordered treatment
Michelin 0.49 0.63
(0.45) (0.66)
Michelin x After 3.32 ** 2.69 **
(0.51) (2.23)
After (2006) 0.00 0.62
(0.51) (0.38)
Lagged dependent (2003) 2.82 ** 2.79
(2.18) (1.56)
Open after 11 p.m. 0.17 0.17 *
(1.41) (1.70)
No credit cards accepted -0.17 -0.19
(-0.17) (-0.17)
Closed on Sunday 0.13 0.21
(0.83) (1.41)
Threshold 1 3.39 *** 3.42 **
(3.09) (2.11)
Threshold 2 4.46 *** 4.49 ***
(4.05) (2.74)
Threshold 3 7.02 ** 7.06
(2.27) (1.56)
Food ethnicity fixed effects Yes Yes
Observations 2473 2473
Kleibergen-Paap rk (LM) 51.306 44.652
p value (0.000) (0.000)
Kleibergen-Paap stat. 7.223 7.383
IV relative bias 10%-20% 10%-20%
Hansen's overid. test 5.336 5.183
p value (0.1488) (0.1588)
Pseudo R-squared 0.388 0.389
Notes: Treatment: Michelin 2005; for dummy vs. ordered
treatment see text or Table 3; robust z-statistics in parentheses;
z-statistics are based on restaurant-clustered standard errors.
Standard errors are bootstrapped.
*** p < 0.01; ** p < 0.05; * p < 0.1.
Source: Zagat Restaurant Guide New York City (2003,
2006), Michelin Travel Publications (2005).
TABLE 13
Probit Equations for Inclusion in 2006 Michelin
Guide (a)--Restricted Paired Sample
Base year 2003 Base year 2004
Food ratings 0.235 *** 0.256 ***
(11.21) (11.76)
Decor ratings 0.071 *** 0.075 ***
(5.94) (6.35)
Cuisine styles
North America 0.158 0.117
(1.05) (0.80)
Asia -0.204 -0.183
(-1.43) (-1.35)
Western Europe -0.189 * -0.140
(-1.68) (-1.29)
Exogenous controls
Low responses -0.673 *** -0.639 ***
(-2.84) (-3.00)
Closed on Sunday 0.037 0.025
(0.27) (0.18)
No credit card accepted -0.596 *** -0.604 ***
(-2.91) (-3.12)
Closed after 11 p.m. 0.047 0.102
(0.47) (1.06)
Constant -6.578 *** -7.121 ***
(-13.19) (-13.91)
Observations 1,039 1,125
Pseudo [R.sup.2] 0.230 0.252
Note: Robust z-statistics in parentheses.
(a) Note, the 2006 Michelin Guide was published in 2005.
*** p < 0.01; ** p < 0.05; * p < 0.1.
Source: Michelin Travel Publications (2005).
TABLE 14
Propensity Score Matching Impact of Michelin on Ratings, Awards, and
Prices Effect of 2005 Michelin Treatment on 2006 Outcomes Restricted
Paired Sample
(1) (2) (3)
Food Service Decor
Matching on
Base year 2003, cuisine 0.483 *** 0.012 0.128
styles & exog. Controls -3.019 -0.055 -0.511
Observations 899 899 899
Base year 2004, cuisine 0.255 * -0.126 0.041
styles & exog. Controls (1.805) (-0.630) (0.083)
Observations 914 914 914
(4) (5)
WS Award Price
Matching on
Base year 2003, cuisine 0.196 *** 4.037 ***
styles & exog. Controls -3.477 -2.852
Observations 899 897
Base year 2004, cuisine 0.229 *** 3.118
styles & exog. Controls (4.444) (0.763)
Observations 914 912
Note: Robust z-statistics in parentheses.
*** p < 0.01; ** p < 0.05; * < 0.1.