What you should know about this study

The people selected for inclusion in this study were all those who travelled between home and work the day before the telephone interview for the 2005 General Social Survey (or two days before in some cases). For more details on the survey methodology, please see The Time it Takes to Get to Work and Back, Statistics Canada Catalogue no. 89-622-XWE.

Analytic techniques and statistical models

The figures shown in the tables are predicted probabilities based on an ordered logit model. They represent the estimated probability that a “commuting worker” with a particular characteristic (e.g., driving his/her car to work) will like or dislike commuting, after all the other factors in the regression model have been taken into account, i.e., kept constant. The predicted probabilities were calculated by keeping all variables, except the variable of interest (e.g., driving), constant at their average value for the sample in question. To take into account the General Social Survey’s complex sampling methods, bootstrap weights were used to estimate the standard errors of the regression models’ beta coefficients.