There's no such thing as bad weather, just the wrong clothing: climate, weather and active school transportation in Toronto, Canada.

Mitra, Raktim ; Faulkner, Guy

Children who walk or cycle for school transportation tend to be more physically active overall than those who use other travel modes. (1) Policy and program initiatives in North America have focused on active school transportation (AST), i.e., walking and cycling, as a means to increase physical activity levels among children and youth, and in the longer term, to reverse the current trend of increasing obesity rates. This policy concern is matched by an emerging literature that has explored the barriers and correlates of active school transportation. (2) Much of the recent literature considers the potential influence of travel distance and the neighbourhood environment on AST uptake. (3-6)

For many North American cities that have marked seasonal variation in climate, weather conditions are popularly identified as enablers or barriers to participation in outdoor physical activity, including AST. For example, a study that analyzed data from a consumer styles survey in the US revealed that 18.6% of parents identified bad weather as a barrier to their children (5-18 years) walking to or from school at least once per week. (7) In Canada, parents who continued to drive their children to school after a School Travel Planning intervention most often cited weather (21.0%) as the reason for doing so. (8)

However, it is not clear from such North American evidence whether the seasonal climate (e.g., summer, fall and winter) and short-term weather conditions related to climatic variations (e.g., temperature, rain, snow) do influence decision-making behaviour about school travel or whether perhaps these natural conditions are used to externalize the reason for driving. The actual effects of seasonal climate and objectively measured weather conditions associated with these seasonal climates remain largely overlooked in the school transportation literature. Existing evidence on the association between climatic conditions and active travel is limited and inconclusive. For example, Sirard et al. (9) studied rates of active travel among students going to eight elementary schools in Columbia, South Carolina, US, and found no association between weather conditions, temperature and the number of students actively travelling (walking and cycling) to school. Robertson-Wilson et al. (10) studied students from 76 high schools in Ontario; season of the year (summer, fall and winter), average weekly temperature and weekly precipitation were not associated with AST. In Norway, where there are extreme differences in weather conditions between the summer and winter months, the number of children walking to and from school actually increases in winter (24% in the fall to 65% in the winter) as a result of a decline in cycling during that season. (11)

[FIGURE 1 OMITTED]

Seasonal climate and weather conditions may have received less attention in the current literature because these natural conditions are non-modifiable. However, there are two important reasons why their effects on school travel outcome should be explored. First, if climate and weather conditions have an important influence on school travel behaviour, then expensive public investments leading to improvements in the built environment can only produce limited benefits, perhaps only by improving walking rates in months when weather conditions are generally good. This should be an important consideration before making such investments. Second, if climate and weather conditions do not have an important influence, then there is a need for more focused interventions that target households situated within a walkable distance from school throughout the school year and that are tailored appropriately for each season.

Within this context, this study explored the effects of seasonal climate and objectively measured weather conditions on children's AST uptake in the City of Toronto. The potential role of snow-clearing policy was also taken into account. To our knowledge, this is the first study to rigorously examine climate-related effects on children's school travel mode in a large North American city with marked seasonal variation in climatic conditions.

Study design

The school transportation behaviour of children 11-12 years old in the City of Toronto was examined. The primary hypothesis of the paper was that once the variations in household socio-economic characteristics and the travel distance are taken into account, the effect of seasonal climate and related weather conditions on active school travel, particularly walking, would be minimal.

Study area

Toronto is the largest city in Canada, with a population of over 2.5 million.12 The city is situated in a continental climate zone (Koppen climate classification: Dfa). (13) In 2006, the mean February tempera ture in Toronto was -2.4[degrees]C (minimum temperature recorded in 2006 was -13.1[degrees]C). In contrast, the mean temperatures in July and October were 23.4 [degrees] C and 9.7 [degrees] C respectively. (14) Total precipitation in 2006 was 957.1 mm, which occurred mostly in the summer and winter months. The city also has different snow management policies for its inner-city and inner-suburban neighbourhoods, thanks to the legacy of a political and geographic amalgamation in 1998 (Figure 1). The 2000 Snow Plan requires owners of inner-city properties to clear sidewalks of snow and ice within 12 hours after a snowfall. In contrast, inner-suburban residents of Toronto continue to enjoy publicly funded, mechanical sidewalk clearing services, as they did before the amalgamation. (15)

Travel data

This study uses school travel data from the 2006 Transportation Tomorrow Survey (TTS). The TTS is a repeated cross-sectional survey of travel behaviour in southern Ontario and covers a 5% sample of all households in the study area. (16) The 2006 TTS data were collected for a randomly selected weekday in fall or winter; an adult household member proxy reported travel data (e.g., origin/destination of trips, trip start time, purpose, primary travel mode) for all trips by household members aged 11 years and older, associated with the day before the interview. For this study, all home-to-school trips between the 6h00-9h30 time interval (n=2,520) were extracted. Only the students who travelled to public and Catholic schools were included; these students are expected to attend schools that are closest to their residential locations. The school trips were made between September 2006 and January 2007. School travel mode was determined on the basis of the proxy reported data on primary mode of travel.

Socio-economic and travel distance data

Household socio-demographic information and the distance between home and school locations were used as control variables (Table 1). The socio-demographic data were taken from the 2006 TTS. However, the TTS did not provide information on household income. As a result, the median household income data from the population census of Canada were aggregated to identify the low-income neighbourhoods. Shortest path network distance (i.e., minimum travel distance) between home and school locations of a child was computed using Toronto's street network file (DMTI Can-Map [C] RouteLogistics file, version 2007.3).

Climate and weather data

School trip data were collected between September 2006 and January 2007. These data were categorized into fall (78.2% of total trips; data collected between September 10 and December 17, 2006) and winter (21.8% of total trips; data collected in January 2007) trips, in order to capture potentially climatically moderated differences in travel behaviour. In addition, seven objectively measured weather-related variables were computed for three weather stations located inside and near the City of Toronto (Toronto City, Toronto Lester B. Pearson Airport and Toronto Buttonville Airport), using data from Environment Canada customized climate search (Figure 1).14 Weekly average for each weather variable was used, computed from an average of all school days in the week of data collection (Table 1). The 2006 TTS did not provide information on the date of travel. For each household, the nearest weather station (straight line distance) was identified to determine the weekly weather condition for that household. In order to account for Toronto's snow management policy, households located inside and outside of the sidewalk snow-plough zone were identified.

Statistical analysis

Binomial logistic regressions were estimated to explore the correlates of active (i.e., walking) versus non-active (i.e., private auto mobile, public transit or school bus) mode choice for school trips. The effect of weather on walking and cycling are potentially different; these two modes also have different costs of access (i.e., equipment, safety) and infrastructure requirements. In our sample, only 16 children cycled to school and, because of this, cycling trips were excluded from further statistical analysis. In addition, we assumed that beyond a distance of 3.2 km (2 miles) the transportation choices become primarily limited to motorized modes. (18) As a result, this study only explored the travel behaviour of children living within 3.2 km from their schools. Adjusting for missing data and outliers, the final dataset included 1,992 home-to-school trips. The results are presented in terms of odds ratios (OR = exp(/3i)), which demonstrates the relation between a variable i and the odds of active travel. Statistical analyses were performed with R[C] version 2.9.0.

The bivariate association between active travel and each of the climate and weather-related variables was first examined; effect plots were generated for the variables that demonstrated statistically significant associations. The degree of multi-collinearity across the climate and weather variables was also explored before the multivariate analysis. Not surprisingly, weather conditions (e.g., temperature, precipitation) were highly correlated with seasonal climate (i.e., fall and winter). To overcome this collinearity problem, separate models were estimated to explore the effects of seasonal climate and weekly weather conditions. Some of the weather variables were also highly correlated (r>0.9). Those correlated variables (e.g., Temperature 6-9:30 am, Max temperature, Min temperature, Mean temperature; and Precipitation days, Average precipitation) were entered into the multivariate (i.e., adjusted) model one at a time, and only the ones with strongest association (e.g., Temperature 6-9:30 am; Precipitation days) were included in the final model specification.

[FIGURE 2 OMITTED]

RESULTS

Logistic regression models of mode choice were estimated using travel data for 1,992 students aged 11-12 years. The majority (62.7%) walked to school; the other 37.3% travelled by private automobile, school bus or transit (Table 2). Most students (79.8%) lived within 1.6 km (1 mile) of their schools. Of these students, 72.7% walked to school, 17.6% were driven, and 9.7% used school bus or transit as their travel mode.

Table 2 also demonstrates that school transportation mode shares (percentage of total school trips) were not different between fall and winter seasons, suggesting that seasonal climate does not have an influence on mode choice. The rates of walking and car (i.e., private automobile) trips at different travel distances were also compared (Figure 2). Figure 2 indicates that in both fall and winter, more children (with or without caregivers) walked than were driven to school when the household locations were within 1.4 km of school. Not surprisingly, walking rates declined with increased distance, but no systematic variation across seasons was evident. This result suggests that the perception of a "walkable distance" was not different between fall and winter seasons. The model results further confirmed these observations (Table 3). Children in general were less likely to walk within the sidewalk snow-plough zone (i.e., in the inner-suburban neighbourhoods) compared with the areas outside of the zone (i.e., in the inner-city neighbourhoods); seasonal climate (i.e., fall versus winter conditions) was not associated with the likelihood of walking within any of these urban locations.

With regard to weekly weather conditions, the probability of walking was inversely correlated (bivariate) with the number of weekdays with precipitation and the average weekly precipitation (mm) (Figure 3). There was also an association between walking and snow days across the two snow-plough zones. However, most of these correlations disappeared in the multivariate (i.e., adjusted) model. Table 3 suggests that objective measures of weather were not associated with mode choice when household socio-economic characteristics and school travel distance were taken into account.

The only statistically significant variable was "Snow Days". However, the observed effect relates entirely to the geographic location of the households, similar to our earlier observation related to seasonal climate. The amount of snowfall was not associated with the likelihood of walking.

In addition to children living outside of the sidewalk snowplough zone (i.e., in the inner-city neighbourhoods), older students and males were more likely to walk to school than the younger students and females (Table 3). The propensity of walking decreased with an increased distance between home and school locations, and with an increased number of vehicles in the households per licensed driver.

DISCUSSION

Our findings indicate that seasonal climate and weekly weather conditions do not appear to be major influencing factors on choice of school travel mode in Toronto. Distance between home and school remained the strongest correlate of travel mode, supporting what has been reported elsewhere. (19,20) Students living in inner-suburban neighbourhoods walked to school less. Even with the removal of a potential barrier to walking in the winter in the inner-suburban neighbourhoods (i.e., sidewalk snow removal by the City of Toronto), students were still less likely to walk, suggesting consistency in travel mode regardless of season. While the city-run, sidewalk snow plough service remains a political legacy in Toronto's inner-suburban neighbourhoods, this policy does not facilitate children's AST uptake.

[FIGURE 3 OMITTED]

In this study, weather variables were based on weekly averages rather than the weather on the day of the school trip. In other words, the variables explored in this study capture the prevalent weekly weather conditions and their potential contribution to the formation of individual travel patterns. We could not examine responses to extreme weather conditions on any given day. Extreme weather may produce short-term changes in mode choice anywhere on the planet for that matter, and for any activity. However, given the utilitarian necessity of the school trip, it may be that choice of transportation modes for travelling to elementary schools is largely habitual in nature and less influenced by external factors such as the climate and weather unless in those extreme conditions where walking becomes dangerous or extremely difficult. Developed from a qualitative study of parent/child interviews focused on AST in Toronto, a two-stage AST decision-making process was described by Faulkner et al., (21) one decision being whether or not the child needs escorting to/from school and a second decision about mode choice, which is largely influenced by perceptions as to the easiest and most convenient way to travel. Importantly, these initial decisions had developed into routinized behaviour that no longer required a conscious decision-making process. For example, for the parents of children who walked to school, walking remained the most convenient option even in the winter months. (21) Additionally, others have reported that adults who enjoy exercise (22) or who walk for any reasons in and around their neighbourhoods (23) are less likely to mention weather as a barrier. Overall, this again points to the potential stability of choice of school travel mode based on preferences and perceptions of convenience rather than weather per se.

With more extensive sampling during winter and a more rigorous exploration of climate and weather conditions at different travel distances and across different built and policy environments, this study significantly extends existing research on the relation of climate and weather conditions with school travel. However, further research is required to confirm the absence of an association given some limitations of this study. First, there may be some variability between weather conditions at the weather stations and those conditions in close vicinity to the household, although the majority of households were within 10 km of a weather station (mean 8.96[+ or -]4.03 km). Second, our findings also require replication in other geographic locations in Canada where there is more extreme seasonal variation. Yet local policy should be based upon local evidence, and our results have important implications for promoting active school travel within the Greater Toronto Area, Canada's largest and most culturally diverse metropolitan region. In terms of policy, our results suggest that climate and weather conditions do not have any significant effect on AST in this study location. The results are encouraging for policies directed toward improvements in the built environment to increase rates of walking and physical activity among children. Given that seasonality and short-term weather conditions appear not to limit AST uptake in general, the potentially enormous capital cost of built environment interventions designed to facilitate AST could have benefits that spill over across the entire year rather than being limited to a particular season.

In terms of practice, there is growing interest in initiatives targeting drivers of children from households located within a walkable distance from school. (8,24) Our findings suggest that seasonal climate and weather should not be actual barriers to AST in Toronto and, moreover, that parents are likely driving their children to school even when the climate is most conducive to supporting AST (e.g., in the spring and fall). For example, in the fall of 2006 (between September and December), 17.6% of all students who lived within 1.6 km of their schools were driven to school, and in the winter of 2007, 17.5% were driven. Educational campaigns to promote winter walking with strategies for overcoming barriers and parental safety concerns, making the trip fun, and ensuring that clothing choices are appropriate, are also warranted in complementing built environment modifications that facilitate active school travel.

Acknowledgements: This research was funded by the Built Environment, Obesity and Health Strategic Initiative of the Heart and Stroke Foundation and the Canadian Institutes of Health Research. The first author wishes to acknowledge support from the Natural Sciences and Engineering Research Council, Canada.

Conflict of Interest: None to declare.

xxx REFERENCES

(1.) Faulkner GEJ, Buliung RN, Flora PK, Fusco C. Active school transport, physical activity levels and body weight of children and youth: A systematic review. Prev Med 2009;48(1):3-8.

(2.) Stewart O. Findings from research on active transportation to school and implications for Safe Routes to School programs. J Planning Literature 2011;26(2):127-50.

(3.) McDonald NC. Children's mode choice for the school trip: The role of distance and school location in walking to school. Transportation 2008;35(1):23 35.

(4.) McMillan TE. The relative influence of urban form on a child's travel mode to school. Transportation Research Part A 2007;41(1):69-79.

(5.) Mitra R, Buliung RN, Roorda MJ. Built environment and school travel mode choice in Toronto, Canada. Transportation Research Record 2010;2156:150-59.

(6.) Panter JR, Jones AP, van Sluijs EMF, Griffin SJ. Neighborhood, route, and school environments and children's active commuting. Am J Prev Med 2010;38(3):268-78.

(7.) Martin S, Carlson S. Barriers to children walking to or from school: United States, 2004. MMWR 2005;54(38):949-52.

(8.) Buliung R, Faulkner GEJ, Beesley T, Kennedy J. School travel planning: Mobilizing school and community resources to encourage active school transportation. J School Health 2011;81:704-12.

(9.) Sirard JR, Ainsworth BE, McIver KL, Pate RR. Prevalence of active commuting at urban and suburban elementary schools in Columbia, SC. Am J Public Health 2005;95(2):236-37.

(10.) Robertson-Wilson JE, Leatherdale ST, Wong SL. Social-ecological correlates of active commuting to school among high school students. J Adolesc Health 2008;42(5):486-95.

(11.) Borrestad LAB, Andersen LB, Bere E. Seasonal and socio-demographic determinants of school commuting. Prev Med 2011;52:133-35.

(12.) Statistics Canada. Population and Dwelling Counts, for Canada, Provinces and Territories, and Census Divisions, 2006 and 2001 Censuses - 100% Data, 2008. Available at: http://www12.statcan.ca/english/census06/data/popdwell/ Table.cfm?T=702&PR=35&S=0&O=A&RPP=25 (Accessed July 5, 2012).

(13.) McKnight TL, Hess D. Physical Geography: A Landscape Appreciation, 7th ed. Upper Saddle River, NJ: Prentice Hall, 2002;198-239.

(14.) Environment Canada. National Climate Data and Information Archive, 2011. Available at: http://climate.weatheroffice.gc.ca (Accessed November 25, 2011).

(15.) City of Toronto. Snow - City's First Snow Plan 2000. 2011. Available at: http://www.toronto.ca/transportation/snow/plan.htm (Accessed November 25, 2011).

(16.) Data Management Group. Transportation Tomorrow Survey, 2008. University of Toronto. Available at: http://www.dmg.utoronto.ca/transportationtomorrowsurvey/index.html (Accessed July 2, 2010).

(17.) Statistics Canada. Low income cut-offs for 2006 and low income measures for 2005. 2010. Available at: http://www.statcan.gc.ca/bsolc/olc- cel/olccel?lang=eng&catno=75F0002M2007004 (Accessed August 26, 2012).

(18.) Nelson NM, Foley E, O'Gorman DJ, Moyna NM, Woods CB. Active commuting to school: How far is too far? Int J Behav Nutr Phys Act 2008;5:1.

(19.) Mitra R, Buliung RN. Built environment correlates of active school transportation: Neighborhood and the modifiable areal unit problem. J Transport Geography 2012;20(Special Issue on Child and Youth Mobility):51-61.

(20.) Wong B, Faulkner GEJ, Buliung RN. GIS measured environmental correlates of active school transport: A systematic review of 14 studies. Int J Behav Nutr Phys Act 2011;8:39.

(21.) Faulkner GEJ, Richichi V, Buliung R, Fusco C, Moola F. What's "Quickest and Easiest?": Parental decision making about school trip mode. Int J Behav Nutr Phys Act 2010;7:62.

(22.) Salmon J, Owen N, Crawford D, Bauman A, Sallis JF. Physical activity and sedentary behaviour: A population-based study of barriers, enjoyment, and preference. Health Psychol 2003;22(2):178-88.

(23.) Humpel N, Owen N, Iverson D, Leslie E, Bauman A. Perceived environment attributes, residential location, and walking for particular purposes. Am J Prev Med 2004;26(2):119-25.

(24.) McDonald NC, Aalborg AE. Why parents drive children to school: Implications for safe routes to school programs. J Am Planning Assoc 2009;75(3):331 42.

Raktim Mitra, PhD, [1] Guy Faulkner, PhD [2]

Author Affiliations

[1.] Department of Geography and Program in Planning, University of Toronto, Toronto, ON

[2.] Faculty of Kinesiology and Physical Education, University of Toronto, Toronto, ON Correspondence: Raktim Mitra, School of Urban and Regional Planning, Ryerson University, 105 Bond St., Toronto, ON M5B 1Y3, E-mail: raktim.mitra@ryerson.ca. Table 1. Description of Variables and Summary Statistics % (n=1992) Mean (SD) Control Variables Age: The child was 12 years old 52.2 (reference: 11 years). Sex: The child was a male (reference: 52.8 female). Number of Children: Number of school-age 1.92 (0.84) children below driving age (4-15 years) in the household. Single-adult Household: There was only one adult household member (>17 yrs) in the 12.4 household (reference: >1 adults in a household). Vehicles per Licensed Driver: Number of 0.72 (0.42) vehicles in the household per licensed driver. Distance: Minimum travel distance (i.e., 1.05 (0.69) shortest path using a street network) between home and school (km). Low-income Neighbourhood: * The child's residential neighbourhood was a low-income neighbourhood, i.e., median household income was <CAD $39,400. Median household income was estimated by taking a median of the 16.3 census dissemination area median household incomes (reference: not a low-income neighbourhood). Climate and Weather Variables Seasonal Climate: ([dagger]) (reference: Fall AND outside of the sidewalk snow-plough zone). Winter AND outside of the sidewalk 8.9 snow-plough zone. Fall AND inside of the sidewalk 54.8 snow-plough zone. Winter AND inside of the sidewalk 12.9 snow-plough zone. Temperature (6-9:30 am): ([double dagger]) 5.08 (5.64) Weekly average of hourly temperatures ([degrees]C) between the 06h00-09h30 time interval. Max Temperature: Weekly average of daily 9.70 (5.91) maximum temperatures ([degrees]C). ([double dagger]) Min Temperature: Weekly average of daily 2.52 (5.66) minimum temperatures ([degrees]C). ([double dagger]) Mean Temperature: Weekly average of daily 6.13 (5.73) mean temperatures ([degrees]C). ([double dagger]) Precipitation Days: ([double dagger]) 2.16 (1.20) Number of days in a week with precipitation. Average Precipitation: ([double dagger]) 2.30 (3.11) Average precipitation in a week (mm). ([double dagger]) Snow Days: ([double dagger]) (reference: residence located outside of the sidewalk snow-plough zone AND no snow during the week). Residence located outside of the sidewalk 9.1 snow-plough zone AND [greater than or equal to]1 days of snow during the week. Residence located within the sidewalk 58.7 snow-plough zone AND no snow during the week. Residence located within the sidewalk 8.9 snow-plough zone AND [greater than or equal to]1 days of snow during the week. Note: Variables in italics were excluded from the multivariate logistic regression specifications. * Individual household income data were not available. Median household income was calculated using 2006 population census data from Statistics Canada. Average household size for the sample was 4.3 (SD=1.28). In a large metropolitan area such as Toronto (i.e., population >500,000), the low income cut-off, defined by Statistics Canada, was CAD $39,399 for a four-member household. (17) ([dagger]) Fall: Travel data were collected between September 10 and December 17, 2006; Winter: Travel data were collected in January 2007. ([double dagger]) Weather data were averaged/aggregated for weekdays only; holidays and weekends were excluded. (14) Table 2. School Travel Mode Share (Percentage of Total School Trips) All Seasons Fall Winter (n=1992) (n=1558) (n=434) Chi-square * Walk 62.7 62.6 62.9 0.06 Private automobile 20.5 20.7 19.8 (p=0.807) School bus 9.6 9.5 9.9 Transit 7.2 7.2 7.4 * Difference in mode choice distribution between fall and winter seasons; calculated on the basis of the total number of trips. Table 3. Correlates of Walking to School Base Model OR (95% CI) p Age 11 years 1.00 12 years 1.60 (1.28-1.99) * 0.000 * Sex Female 1.00 Male 1.34 (1.08-1.67) * 0.008 * Number of children 1.08 (0.95-1.24) 0.241 Single-adult household 1.07 (0.77-1.50) 0.681 Vehicles per licensed driver 0.62 (0.48-0.81) * 0.000 * Distance 0.13 (0.11-0.16) * 0.000 * Low-income neighbourhood No 1.00 Yes 1.24 (0.91-1.68) 0.166 Seasonal climate Fall AND outside of the sidewalk snow-plough zone Winter AND outside of the sidewalk snow-plough zone Fall AND inside of the sidewalk snow-plough zone Winter AND inside of the sidewalk snow-plough zone Precipitation days Temperature (6-9:30 am) Precipitation days x Temperature (6-9:30 am) Snow days Outside of the sidewalk snow-plough zone AND no snow during the week Outside of the sidewalk snow-plough zone AND [greater than or equal to]1 days of snow during the week Within the sidewalk snow-plough zone AND no snow during the week Within the sidewalk snow-plough zone AND [greater than or equal to]1 days of snow during the week Intercept 12.18 (7.93-18.72) * 0.000 -2 [L(0) - L(B)] 646.6 McFadden's [[rho].sup.2] (adjusted) 0.24 (0.24) AIC ([dagger]) 2002.0 Seasonal Climate Model OR (95% CI) p Age 11 years 1.00 12 years 1.58 (1.26-1.97) * 0.000 * Sex Female 1.00 Male 1.38 (1.11-1.72) * 0.004 * Number of children 1.09 (0.95-1.25) 0.208 Single-adult household 1.03 (0.74-1.44) 0.865 Vehicles per licensed driver 0.64 (0.49-0.83) * 0.000 * Distance 0.13 (0.10-0.15) * 0.000 * Low-income neighbourhood No 1.00 Yes 1.23 (0.91-1.67) 0.159 Seasonal climate Fall AND outside of the sidewalk 1.00 snow-plough zone Winter AND outside of the sidewalk 0.73 (0.46-1.16) 0.183 snow-plough zone Fall AND inside of the sidewalk 0.57 (0.43-0.75) * 0.000 * snow-plough zone Winter AND inside of the sidewalk 0.56 (0.38-0.82) * 0.003 * snow-plough zone Precipitation days Temperature (6-9:30 am) Precipitation days x Temperature (6-9:30 am) Snow days Outside of the sidewalk snow-plough zone AND no snow during the week Outside of the sidewalk snow-plough zone AND [greater than or equal to]1 days of snow during the week Within the sidewalk snow-plough zone AND no snow during the week Within the sidewalk snow-plough zone AND [greater than or equal to]1 days of snow during the week Intercept 17.82 (10.99-28.88) * 0.000 * -2 [L(0) - L(B)] 964.0 McFadden's [[rho].sup.2] (adjusted) 0.25 (0.25) AIC ([dagger]) 1990.6 Weather Conditions Model OR (95% CI) p Age 11 years 1.00 12 years 1.58 (1.26-1.97) 0.000 Sex Female 1.00 Male 1.37 (1.10-1.70) 0.005 Number of children 1.09 (0.95-1.25) 0.209 Single-adult household 1.03 (0.73-1.43) 0.879 Vehicles per licensed driver 0.65 (0.50-0.85) 0.001 Distance 0.13 (0.11-0.16) 0.000 Low-income neighbourhood No 1.00 Yes 1.21 (0.89-1.65) 0.213 Seasonal climate Fall AND outside of the sidewalk snow-plough zone Winter AND outside of the sidewalk snow-plough zone Fall AND inside of the sidewalk snow-plough zone Winter AND inside of the sidewalk snow-plough zone Precipitation days 0.94 (0.84-1.07) 0.362 Temperature (6-9:30 am) 1.03 (0.97-1.09) 0.342 Precipitation days x Temperature 0.99 (0.97-.01) 0.441 (6-9:30 am) Snow days Outside of the sidewalk snow-plough zone AND no snow during the week 1.00 Outside of the sidewalk snow-plough zone AND [greater than or equal 1.06 (0.62-1.82) 0.828 to]1 days of snow during the week Within the sidewalk snow-plough zone AND no snow during the week 0.64 (0.48-0.86) * 0.003 * Within the sidewalk snow-plough zone AND [greater than or equal to]1 0.71 (0.42-1.20) 0.203 days of snow during the week Intercept 16.94 (9.64-29.75) * 0.000 * -2 [L(0) - L(B)] 665.9 McFadden's [[rho].sup.2] (adjusted) 0.25 (0.25) AIC ([dagger]) 1994.7 Note: Variables in * = bold are significant at [alpha]=0.01. OR= odds ratios, CI=confidence interval. ([dagger]) Akaike information criterion.