What does volume reveal: a study of the Indian single stock futures market.
Martins, Renato Alas ; Singh, Harminder ; Bhattacharya, Sukanto 等
Abstract
A single stock future is a relatively new type of exchange-traded
derivative that has become popular in some of the emerging financial
markets. In order to uncover any information effect of trading volume, a
cogent question to ask is whether a relationship exists between the
volume of trade on the underlying stock and the number of its single
stock futures contracts traded. In this paper we have explored the
bivariate relationship between trading volume of some of the most liquid
individual stocks as well as the single stock futures traded on those
stocks in the fast emerging Indian market. Our findings indicate that a
significant relationship exists between the trading volumes of the
straight stocks and the single stock futures on them.
JEL classification: G11; G12
Keywords: Single stock futures; information effect of volume;
Indian financial market
INTRODUCTION
The contemporaneous relation between stock prices and trading
volume is reasonably well documented in finance literature. Volume is a
useful tool in determining the extent of price disagreement that exists
post-arrival of new information. Saatcioglu and Starks (1998) suggested
that when volume is relatively heavy in bullish markets and relatively
light in bearish markets, it can make the stock prices move. More
recently, Gunduz and Hatemi-J (2005) empirically tested the relationship
between volume and absolute price change and between volume and price
change per se and found mixed results. In particular, chartists and
technical analysts have been well-known for their interest in volume,
which presumably conveys valuable information about future price
movements. Intensive trading volume can help to identify the periods in
which either allocational or informational shocks occur and thus can
provide valuable information to market observers about future price
movements of the stock (Llorente et al, 2002). Of the several factors
affecting trading volume, the one which correlates the most to the
fundamental valuation of the security is the arrival of new information.
Volume is useful in determining if a price change was due to any
information effects, and also whether investor interpretations of
information are consistent (Sun, 2003).
However the study of price-volume relationship has so far been
largely limited to straight stocks--the use of spot trading volume as a
predictor of single stock futures trading volume has not been studied
much. Futures markets not only provide an important vehicle for price
discovery but they also offer an alternative way to take equity
positions. Therefore the existence or otherwise of an inter-relationship
between the trading volumes in both markets (spot and futures) yields a
research question that's worthy of a rigorous empirical
exploration.
It is well known that price variability affects trading volume in
futures contracts. This interaction determines whether speculation is a
stabilizing or destabilizing factor on futures prices. The time to
delivery of a futures contract affects the volume of trading, and
possibly also the price (Sun, 2003). Though in case of our study this
doesn't seem plausible as the Indian single stock futures are not
deliverable contracts, rather they are cash settled either at before the
expiry. The efficient market hypothesis predicts that trading volume
should not have any predictive power for asset returns beyond an
appropriate measure of risk. However an important question is whether
the spot trading volume on straight stocks has any predictive power in
explaining changes in the trading volume of the single stock futures on
those stocks.
In this paper we look at the price-volume relation for single stock
futures in the fast emerging Indian financial market. Although previous
studies have some important implications for causal relations between
trading volume and stock returns, there are not many rigorous empirical
studies of causal relations between volume and returns of spot market as
well as of single stock futures market to confirm or reject these
implications. The information flow in an emerging market like India is
not equivalent to the information flow in the more developed markets due
to significant cross-market institutional differences (Agarwal et al.,
1993; Barry and Lockwood, 1995).
The main contribution of our paper is to understand and explore the
existence or otherwise of a relation between trading volumes (and
returns) in spot and single stock futures market in India. Our results
indicate that while there is no strong evidence of spot trading volume
affecting returns in the Indian market, there is nevertheless a strong
support for the view that it does affect the number of single stock
futures traded thus contributing to futures market activity. Our paper
is organized as follows: the first section presents an overview of
literature, the second provides an overview of Indian stock futures
market, the third provides data and methodology, the fourth discusses
the major results and then the last one concludes.
OVERVIEW OF LITERATURE
Schwert (1990) argued that volume induces price changes because of
a common belief in price persistence which results in many investors
wishing to trade in the same direction when there is a price movement.
This "herd" mentality becomes a self-fulfilling prophecy as
the increased trading exacerbates the change in price which in turn
influences more investors to trade in the same direction. Informed
traders will transact when new information, both public and private,
becomes available (however, since trading based on private information
is difficult to identify, volume has generally been examined in the
context of public information). Using daily, weekly, and monthly series
of different indices in the Tokyo Stock Exchange, Tse (1991) reported
mixed results for the relations between volume and returns. Harris and
Raviv (1993) and Shalen (1993) showed that large trading volume is
related to large subsequent absolute price changes i.e. high volatility.
Wang (1994) analyzed the dynamic relationship between volume and returns
in presence of information asymmetry. He showed that volume may provide
information about expected future returns. Campbell et al. (1993)
concluded that price changes accompanied by relatively high volume will
tend to be reversed but this will be less true for price changes
occurring on days when the volume of trading is relatively low.
Blume et al. (1994) presented a model where traders
'learned' valuable information about a security by observing
both past price and past volume information. While examining the stock
price-volume relation in a set of Latin American markets, Saatcioglu and
Starks, (1998) observed a clear positive relation for the first time
between volume and both the magnitude of price change and the price
change itself. However, using VAR analysis and testing for Granger
causality, they failed to find evidence of such a price-volume
relationship.
Chordia and Swaminathan (2000) concluded that the returns of stocks
with high trading volume lead returns of stocks with low trading volume
primarily because the high volume stocks adjust faster to market wide
information. This is consistent with the idea that trading volume plays
a significant role in the dissemination of market-wide information. Lee
and Rui (2000) found that trading volume did not Granger-cause stock
returns on any of the four Chinese stock markets. Gervais et al. (2001)
found that stocks experiencing unusually high (low) trading volume over
a day or a week tend to appreciate (depreciate) over the course of the
following month. They further argue that this high-volume return premium
is consistent with the idea that shocks in the trading activity of a
stock affect its visibility, and in turn the subsequent demand and price
for that stock. In a multi-country study Chen et al. (2001) found a
positive correlation between trading volume and the absolute value of
the stock price change--their results indicate that trading volume
contributes some information to the returns process. Repeating their
earlier study, Lee and Rui (2002) found that trading volume did not
Granger-cause stock returns on the New York, Tokyo and London markets.
However, all the above-reported studies looked at the information
effect of volume in the stock market--none of them explored the
volume-volume relationship between an underlying stock and its
derivative. Back (1993) argued that volume of trade in derivatives
versus volume of trade in their underlying assets may convey different
information. Blume et al. (1994) showed that option trading volume
provides evidence regarding the quality of information that cannot be
deduced from prices alone. Subsequently, Kraus and Smith (1996)
suggested that trading in derivatives can alter the equilibrium in
markets for underlying securities either by reducing the information
asymmetry or by allowing investors to conjecture additional uncertainty
about the future prices of underlying securities. Further, from an
options point of view, Easley, O'hara, and Srinivas (1998)
documented that trading volume on options has predictive power on future
returns. However, only positive option volume (buy call, sell put) were
observed to predict rises in stock prices, and only negative option
volume (sell call, buy put) predicted falls in stock prices. Pan and
Poteshman (2006) also similarly showed that signed option volume
provides information about stock returns.
Specifically on single stock futures, McKenzie and Brooks (2003)
analyzed the single stock futures market of Hong Kong. Their empirical
analysis of information flows proxied by spot market volume and stock
futures volume provides evidence that suggests that it is not the
arrival of news to the market which motivates derivatives trading. Our
paper is largely motivated by the one by McKenzie and Brooks (2003) and
also uses a comparable approach.
A BRIEF BACKGROUND OF THE INDIAN STOCK AND STOCK FUTURES MARKET
India has the oldest stock market amongst the developing market-
Bombay Stock Exchange (BSE), which was established in 1875. There are
two major stock exchanges in India-BSE and NSE (National Stock Exchange
of India), the latter was recognised as a stock exchange in April, 1993.
Especially, BSE is the world's largest in terms of the number of
listed companies (BSE, 20091). India is one of the strongest emerging
economies in terms of a market for exchange-traded derivatives with
wholesome characteristics like nationwide access, anonymous electronic
trading, and a developed retail market. India's tryst with equity
derivatives began in the year 2000 on the National Stock Exchange (NSE)
and the Bombay Stock Exchange (BSE). Trading first commenced in Index
futures contracts, followed by index options in June 2001, options in
individual stocks in July 2001 and futures on single stocks in November
2001. Since then, derivatives in India have come a long way--NSE
derivatives turnover increasing from Rs. 23,654 million (US$ 207
million) in 2000-01 to Rs. 110,104,821 million (US$2,161 billion) (2) in
2008-09.
In particular, India is among the few countries where trading in
single stock futures has shown a tremendous upward trend. Single stock
futures on NSE are traded in monthly series; the expiration date for
each series being the last Thursday of the month. At any point in time,
three monthly series (current month expiry, two month and three month
expiry) are traded side by side. These contracts are spot settled and
can be exercised either at or before expiration. The stock selection
criteria for derivatives trading in India ensure that the stock is of a
large firm in terms of market capitalization and turnover; and has
sufficient liquidity in the underlying market with no adverse issues
related to market manipulation. Like elsewhere in the world, the major
factors that have been driving the growth of financial derivatives in
India are increased volatility in asset returns in the financial
markets; increased integration of national financial markets with
international markets; and the development of more sophisticated risk
management tools that provide economic agents with a much wider choice
of risk management strategies that can be tailored to fit their
'risk control budgets'. The single stock futures provides a
unique set up that may help in understanding the role of information in
both spot as well as futures contracts in the context of the Indian
market. As entering into a short position in single stock futures is as
convenient as acquiring a long position, the introduction of single
stock futures reduces, if not eliminates, the short-selling constraints
that are faced by traders wanting to short the underlying stock. Another
advantage is that it affords investors greater leverage as futures
contracts require less up-front capital.
In terms of number of single stock futures contracts traded in 2007
and 2008, NSE held the second position worldwide during both these
years. These rankings are shown in Fig. 1 below [Source: World
Federation of Exchanges (WFE) Annual Report and Statistics 2008]:
[FIGURE 1 OMITTED]
DATA AND METHODOLOGY
We use a sample of sixteen most liquid stocks trading on the NSE
since November 2001. The main sample for this study is the daily returns
of these sixteen stock futures and the returns of their underlying
stocks in the spot market. The stock futures series analyzed here uses
data on the near month contracts as they carry the highest trading
volume. January 2003 to December 2007 constitutes our overall sample
window, which gives us slightly less than 1500 data points. Our
intension was to specifically capture the goings-on prior to the global
financial crisis (GFC) as we wanted to draw parallels with the results
of the precedent study on the Hong Kong market that was done by McKenzie
and Brooks (2003) with pre-GFC data. To take care of any potential
expiration effects in the sample, the stock futures contracts are rolled
over to the next month contract on two days prior to their respective
expiry date which effectively transform them into 'perpetual
securities' like straight stocks. We also looked for trends and
seasonality components in our data series (not reported here for
brevity), but did not find any evidence of trend or seasonality in the
data in our specified time window.
Four separate Ordinary Least Squares (OLS) regression models (model
specifics furnished below) were considered in order to test the
significance of relationships between spot volume and returns and also
between spot volume and number of single stock futures contracts traded
after appropriately adjusting the data for stock splits and bonus
issues, if any, in the sample time window. The first two models concern
the spot trading volumes and returns while the last two models concern
spot and futures volumes. These are stated below:
Model I: Percentage daily returns regressed on lagged trading
volume
[R.sub.t] = [a.sub.l] + [b.sub.l] [V.sub.t-1] + [epsilon] (i)
Model II: Change in percentage daily returns regressed on change in
lagged trading volume
[DELTA][R.sub.t] = [[alpha].sub.II] + [[beta].sub.II]
[DELTA][V.sub.t-1] (ii)
Model III: Number of futures contracts traded regressed on lagged
volume in the spot market
[DELTA][[eta].sub.t] = [[alpha].sub.III] + [[beta].sub.III]
[V.sub.t-1] + [epsilon] (iii)
Model IV: Change in number of futures contracts traded regressed on
change in lagged spot volume
[DELTA][[eta].sub.t] = [[alpha].sub.IV] + [[beta].sub.IV]
[DELTA][V.sub.t-1] + [epsilon] (iv)
The first-difference models (ii) and (iv) were only intended to
counter presence of any positive serial correlation indicated by the
Durbin-Watson (DW) statistic shown in each case.
RESULTS AND DISCUSSION
After running the first OLS model, only two of the sixteen
companies in the sample showed up an evidence of a relationship between
spot returns and volume that was statistically significant at the 5%
level (one of these was actually significant at the 1% level). None of
these two companies had reported a stock split or bonus issue inside the
sample time window. This indicates that volume information is pretty
well-incorporated in the stock prices i.e. the Indian stock market
appears to be generally efficient with respect to past volume
information.
As none of the DW statistics was significantly less than 2; no
positive serial correlation was evident and hence the second model was
not run as it was deemed superfluous in this case.
When the third OLS model was run, fifteen of the sixteen companies
in the sample showed up a strong relationship (statistically significant
at the 1% level) between the spot market volume and the number of single
futures contract traded (in both pre-split as well as post-split phases
for those that had stock splits). For the remaining one company this
relationship was statistically significant at the 5% level pre-split and
at 10% level post-split.
As the DW statistic was significantly less than two for most of the
results, the fourth model with first differences was run. When the
fourth OLS model was run, all the eight companies that did not have a
stock split or bonus issue in the sample time window showed up a strong
evidence of a relationship between change in spot market volume and
change in the number of single stock futures traded (all statistically
significant at 1% level). Seven of the remaining eight companies showed
up a strong evidence of a relationship between change in spot market
volume and change in the number of single stock futures traded (all
statistically significant at 1% level) in the pre-split phase but this
significance disappeared in the post-split phase in three of them. In
the remaining four, the significance was reduced to 5% level in the
post-split phase. For the remaining one company this relationship was
seen to be statistically significant at the 5% level pre-split and
became insignificant post-split. None of the DW statistics was observed
to be significantly less than 2; indicating that any issues with
positive serial correlation had been successfully accounted for via the
use of first differences.
An interesting observation is that although they are mostly
significant in either case, the sign of the slope term changes from
positive (using original data) to negative (using first differences),
which is attributable to the mechanics of de-trending that occurs due to
the use of first differences. Our results show that past volume is at
best a questionable predictor of stock returns in the Indian market,
indicating that the market is at least weakly price-efficient for
straight stocks. However these results also indicate the presence of a
strong relation between the trading volume of the straight stocks and
that of the relevant single stock futures.
Although the slope terms in our OLS results are mostly very
significant, we stop short of saying that a high volume of trade on the
underlying stock drives the volume of trade in the corresponding single
stock future as we have not tested for causality in this paper and
therefore cannot draw any inferences as to the causal direction in what
looks to be a strong bivariate relation. But all in all, if information
on the volume of trade in the spot market is a proxy for the arrival of
news in the stock futures market, then it is evident from our results
that such information affects the stock futures trading volume in India;
unlike the lack of evidence to that effect in the Hong Kong market
reported by McKenzie and Brooks (2003).
CONCLUSION
It has been an open question for some time whether a significant
relationship exists between volume of trade and observed market price
movements of a financial asset. Taking volume of trade to be a proxy for
arrival of new information, we have empirically explored whether it
significantly affects the returns (or change in returns) in the spot
market for a stock as well as the number of single stock futures traded
on such stock (or change in that number). Our results indicate that
while there is no strong evidence of spot trading volume affecting stock
returns in the Indian market indicating weak price-efficiency, there is
nevertheless evidence that it affects the volume of stock futures traded
and so contributes to futures market activity.
References
Back, K. (1993), "Asymmetric Information and Options"
Review of Financial Studies Vol. 6, 435-472.
Blume L., Easley, D. and O'Hara, M. (1994), "Market
Statistics and Technical Analysis: The Role of Volume" Journal of
Finance Vol. 49, No. 1, 153-182.
Campbell, J. Y., Grossman, S. J., and Wang, J. (1993),
'Trading Volume and Serial Correlation in Stock Returns"
Quarterly Journal of Economics, Vol. 108, 905-939.
Chordia, T. and Swaminathan, B. (2000), "Trading Volume and
Cross-autocorrelations in Stock Returns" Journal of Finance Vol.
55, 913-935.
Chen, G., Firth, M. and Rui, O. M. (2001), "The Dynamic
Relation Between Stock Returns, Trading Volume, and Volatility"
Financial Review Vol. 38, No. 3, 153-174.
Easley, D., O'Hara, M. and Srinivas, P. S. (1998),
"Option Volume and Stock Prices: Evidence on where Informed Traders
Trade" Journal of Finance Vol. 53, 431-465.
Gervais, S., Kaniel, R. and Mingelgrin, D. H. (2001), "The
High-Volume Return Premium" Journal of Finance, Vol. LVI, No. 3,
877-919.
Gunduz, L., and Hatemi-J, A. (2005), "Stock Price and Volume
Relation in Emerging Markets" Emerging Markets Finance and Trade,
Vol. 41, 29-44.
Harris, M. and Raviv, A. (1993), "Differences of Opinion Make
a Horse Race" Review of Financial Studies Vol. 6, 473-506.
Kraus, A., and Smith, M. (1996), "Heterogeneous Beliefs and
the Effect of Replicable Options on Asset Prices" Review of
Financial Studies, Vol. 9, 723-756.
Lee, C. F., and Rui, O. M. (2000), "Does Trading Volume
Contain Information to Predict Stock Returns? Evidence from China's
Stock Markets" Review of Quantitative Finance and Accounting, Vol.
14, 341-360.
Lee, B. S., and Rui, O. M. (2002), "The Dynamic Relationship
between Stock Returns and Trading Volume: Domestic and Cross-country
Evidence" Journal of Banking and Finance, Vol. 26, 51-78.
Llorente, G., Michaely, R., Saar, G., and Wang, J. (2002),
"Dynamic Volume-Return Relation of Individual Stocks" The
Review of Financial Studies, Vol. 15, No. 4, 1005-10047.
Mckenzie, M. D., and Brooks, R. D. (2003), "The Role of
Information in Hong Kong Individual Stock Futures Trading" Applied
Financial Economics, Vol. 13, 123-131.
Pan, J., and Poteshman, A. M. (2006), "The Information in
Option Volume for Stock Prices" Review of Financial Studies, Vol.
19, 871-908.
Saatcioglu, K. and Starks, L. (1998), "The Stock Price-Volume
Relationship in Emerging Stock Markets: The Case of Latin America"
International Journal of Forecasting, Vol. 14, 215-225.
Schwert, G. W. (1990), "Stock Market Volatility"
Financial Analysts Journal, Vol. 46, 23-34.
Shalen, C. T. (1993), "Volume, Volatility, and the Dispersion
of Beliefs" Review of Financial Studies Vol. 6, 405-434.
Sun, W., (2003), "Relationship between Trading Volume and
Security Prices and Return" Technical Report, P-2638;
http://ssg.mit.edu/~waltsun/docs/AreaExamTR2638.pdf, last retrieved on
1st December 2011.
Tse, Y. K. (1991), "Stock Returns Volatility in the Tokyo
Stock Exchange" Japan and the World Economy, Vol. 3, 285-298.
Wang, J. (1994), "A Model of Competitive Stock Trading
Volume" Journal of Political Economy Vol. 102, 127-168.
Notes
(1.) http://www.bseindia.com/about/introbse.asp, retrieved October
18, 2009.
(2.) http://www.nse-india.com/content/us/ismr2009ch7.pdf.
RENATO ALAS MARTINS, School of Business, Bond University, QLD 4229,
Australia
HARMINDER SINGH, School of Accounting, Economics and Finance,
Deakin University, VIC 3125, Australia
SUKANTO BHATTACHARYA, Deakin Graduate School of Business, Deakin
University, VIC 3125, Australia, E-mail: sukanto@deakin.edu.au
Table I
OLS Outputs for Lagged Volume vs. Percentage Daily Returns
No. of
observations [R.sup.2] Slope t-stat p-value
ACC 1461 0.001 -0.00002 -0.034 0.973
Bajaj 1483 0.010 -0.01307 -4.045 0.000 **
BPCL 1483 0.003 -0.00161 -2.423 0.016 **
Grasim 1482 0.001 0.00434 1.481 0.139
Hind Petro 1483 0.000 -0.00028 -0.664 0.506
MTNL 1482 0.000 0.00034 0.868 0.385
SBIN 1483 0.002 -0.00063 -1.985 0.047 **
Tata Power 1482 0.000 -0.00042 -0.643 0.520
Dr. Reddy's 1172 0.001 -0.00360 -1.045 0.296
310 0.000 0.00050 0.200 0.842
Guj. Ambuja 874 0.000 -0.00062 -0.544 0.587
520 0.002 -0.00031 -1.073 0.284
HDFC 237 0.004 0.01758 0.911 0.363
1245 0.000 0.00028 0.194 0.846
ITC 938 0.000 0.00113 0.469 0.639
543 0.001 -0.00020 -0.807 0.420
Mahindra 924 0.001 0.00068 0.742 0.458
556 0.000 -0.00003 -0.014 0.989
Satyam 1200 0.000 0.00002 0.142 0.887
279 0.001 -0.00035 -0.403 0.687
Cipla 593 0.000 0.01012 1.057 0.291
486 0.001 -0.00115 -0.822 0.411
400 0.001 -0.00048 -0.614 0.539
Infosys 628 0.000 0.00105 0.319 0.750
510 0.002 0.00154 1.020 0.308
340 0.001 0.00048 0.369 0.712
No. of DW Pre/Post split
observations statistic
ACC 1461 1.942 --
Bajaj 1483 1.945 --
BPCL 1483 1.937 --
Grasim 1482 1.980 --
Hind Petro 1483 1.869 --
MTNL 1482 1.865 --
SBIN 1483 1.908 --
Tata Power 1482 1.827 --
Dr. Reddy's 1172 1.983 Pre-split
310 2.013 Post (1st split)
Guj. Ambuja 874 1.946 Pre-split
520 2.001 Post (1st split)
HDFC 237 2.246 Pre-split
1245 2.018 Post (1st split)
ITC 938 2.030 Pre-split
543 2.012 Post (1st split)
Mahindra 924 1.832 Pre-split
556 1.880 Post (1st split)
Satyam 1200 2.005 Pre-split
279 2.085 Post (1st split)
Cipla 593 1.893 Pre-split
486 1.778 Post (1st split)
400 1.905 Post (2nd split)
Infosys 628 1.895 Pre-split
510 1.962 Post (1st split)
340 2.081 Post (2nd split)
Table II
OLS Outputs for Lagged Volume (Independent Variable) vs. Number of SF
Contracts Traded (Dependent Variable)
No. of
observations [R.sup.2] Slope t-stat p-value
ACC 1461 0.114 1.06057 13.700 0.000 ***
Bajaj 1483 0.146 5.67811 15.937 0.000 ***
BPCL 1483 0.231 0.49858 21.113 0.000 ***
Grasim 1482 0.044 1.62978 8.285 0.000 ***
Hind Petro 1483 0.253 0.54882 22.420 0.000 ***
MTNL 1482 0.311 1.10178 25.874 0.000 ***
SBIN 1483 0.022 0.70206 5.826 0.000 ***
Tata Power 1482 0.411 1.50841 32.108 0.000 ***
Dr. Reddy's 1172 0.088 1.70565 10.596 0.000 ***
310 0.095 1.44665 5.674 0.000 ***
Guj. Ambuja 874 0.433 1.83218 25.831 0.000 ***
520 0.169 0.36305 10.269 0.000 ***
HDFC 237 0.068 0.07211 4.137 0.000 ***
1245 0.102 0.65073 11.873 0.000 ***
ITC 938 0.066 1.40530 8.151 0.000 ***
543 0.038 0.13152 4.619 0.000 ***
Mahindra 924 0.308 1.20308 20.261 0.000 ***
556 0.022 0.61748 3.511 0.000 ***
Satyam 1200 0.004 0.04520 2.302 0.022 **
279 0.011 0.24474 1.722 0.086 *
Cipla 593 0.393 4.06349 19.563 0.000 ***
486 0.220 1.47501 11.688 0.000 ***
400 0.088 0.34521 6.200 0.000 ***
Infosys 628 0.134 3.09750 9.849 0.000 ***
510 0.020 1.53059 3.247 0.001 ***
340 0.064 2.62408 4.808 0.000 ***
No. of DW
observations statistic Pre/Post split
ACC 1461 0.734 --
Bajaj 1483 0.992 --
BPCL 1483 1.460 --
Grasim 1482 0.547 --
Hind Petro 1483 1.375 --
MTNL 1482 0.959 --
SBIN 1483 0.517 --
Tata Power 1482 1.038 --
Dr. Reddy's 1172 1.027 Pre-split
310 1.105 Post (1st split)
Guj. Ambuja 874 1.780 Pre-split
520 0.837 Post (1st split)
HDFC 237 1.079 Pre-split
1245 0.607 Post (1st split)
ITC 938 1.068 Pre-split
543 1.267 Post (1st split)
Mahindra 924 1.032 Pre-split
556 0.995 Post (1st split)
Satyam 1200 0.929 Pre-split
279 0.183 Post (1st split)
Cipla 593 0.044 Pre-split
486 1.126 Post (1st split)
400 0.981 Post (2nd split)
Infosys 628 1.209 Pre-split
510 1.071 Post (1st split)
340 0.979 Post (2nd split)
Table III
OLS Outputs for A Lagged Volume vs. D Number of SF Contracts Traded
No. of
observations [R.sup.2] Slope t-stat
ACC 1460 0.060 -789.19187 -9.659
Bajaj 1482 0.012 -0.02527 -4.221
BPCL 1482 0.040 -0.02337 -7.913
Grasim 1481 0.009 -0.01756 -3.732
Hind Petro 1482 0.028 -0.20354 -6.575
MTNL 1481 0.006 -127.99278 -3.046
SBIN 1482 0.026 -0.74904 -6.248
Tata Power 1481 0.048 -0.55314 -8.630
Dr. Reddy's 1171 0.025 -0.77192 -5.519
309 0.003 -0.21843 -0.889
Guj. Ambuja 873 0.110 -0.83722 -10.398
519 0.012 -0.07560 -2.535
HDFC 236 0.019 -29.04620 -2.106
1244 0.001 0.03812 1.315
ITC 937 0.068 -1.17213 -8.232
542 0.000 -0.01439 -0.455
Mahindra 923 0.062 -0.46487 -7.793
555 0.004 -0.22226 -1.403
Satyam 1199 0.022 -0.16206 -5.180
278 0.001 -0.04868 -0.387
Cipla 592 0.026 -0.75473 -3.944
485 0.017 -0.36260 -2.899
399 0.016 -0.11556 -2.526
Infosys 627 0.084 -2.47897 -7.569
509 0.012 -1.09545 -2.480
339 0.022 -1.31903 -2.770
No. of DW
observations p-value statistic Pre /Post split
ACC 1460 0.000 *** 2.461 --
Bajaj 1482 0.000 *** 1.924 --
BPCL 1482 0.000 *** 2.431 --
Grasim 1481 0.000 *** 2.714 --
Hind Petro 1482 0.000 *** 2.404 --
MTNL 1481 0.002 *** 2.601 --
SBIN 1482 0.000 *** 2.782 --
Tata Power 1481 0.000 *** 2.458 --
Dr. Reddy's 1171 0.000 *** 2.595 Pre-split
309 0.375 2.699 Post (1st split)
Guj. Ambuja 873 0.000 *** 2.369 Pre-split
519 0.012 ** 2.646 Post (1st split)
HDFC 236 0.036 ** 2.574 Pre-split
1244 0.189 2.760 Post (1st split)
ITC 937 0.000 ** 2.626 Pre-split
542 0.649 2.870 Post (1st split)
Mahindra 923 0.000 *** 2.457 Pre-split
555 0.161 2.599 Post (1st split)
Satyam 1199 0.000 *** 2.589 Pre-split
278 0.699 2.635 Post (1st split)
Cipla 592 0.000 *** 2.208 Pre-split
485 0.004 *** 2.677 Post (1st split)
399 0.012 ** 2.709 Post (2nd split)
Infosys 627 0.000 *** 2.357 Pre-split
509 0.013 ** 2.625 Post (1st split)
339 0.006 *** 2.737 Post (2nd split)
