15. Methodology

View the most recent version.

15.1 The General Social Survey

In 2005, Statistics Canada, through a sport supplement to the General Social Survey (GSS), surveyed 19,597 Canadians (aged 15 years and older) about the extent and nature of their participation in sport during the 12 months prior to the survey.

Similar questions were also asked in 1992 and 1998. These three data bases are the primary data source for this study.

The sport questions were developed by Statistics Canada based on the information needs of federal and provincial/territorial partners having an interest in sport information. The questions were sponsored by a consortium of federal and provincial data users with the objective of obtaining a more comprehensive look at the extent of sport participation in Canada.

Involvement in sport was determined by asking the question:

"Did you regularly participate in any sports during the past 12 months?"

'Regularly' meant that the respondent participated in a sport at least once a week during the season or for a certain period of the year.

The types of sports within scope for this survey were determined by Sport Canada (see Appendix 1). "Sport" was defined by Sport Canada as an activity having the following characteristics:

• involves two or more participants who engage for the purpose of competitively evaluating their personal performance;
• involves formal rules and procedures;
• requires tactics and strategies;
• requires specialized neuromuscular skills which can be taught and learned;
• requires a significant involvement of large muscle groups;
• involves a high degree of difficulty, risk or effort in reproduction of movement or form;
• its competitive mode implies the development of trained coaching personnel;
• its primary activity involves physical interaction of the participant with the environment; and
• does not involve activities in which the performance of a motorized vehicle is the primary determinant of the competitive outcome. Where mechanized vehicles or conveyance are used, the activity must entail significant physical effort in propelling the vehicle or conveyance.

Based on these general guidelines defining sport, several physical and leisure activities were excluded such as non-competitive aerobics, aquafit, bicycling for recreation or transportation only, body building or body sculpting, car racing, dancing, fishing, fitness classes, hiking, jogging, lifting weights (non-competitive), motorcycling, snowmobiling, and non-competitive walking.

Participation during the 12 months previous to the survey was the reference period for the three survey cycles in this study (1992, 1998 and 2005). It is recognized that a reference period of one year may incur the problem of recall. As well, the risk of over-statement may be at play as respondents may be reluctant to admit, particularly in these health-conscious days, that they had not been physically active during the past year. It is not possible from this questionnaire to measure the presence or extent of either the under coverage or over reporting of sports participation.

The GSS, originating in 1985, conducts a telephone survey across the 10 provinces. The GSS is recognized for its continual collection of data that allows for trend analysis. The history of GSS data collection topics is outlined below.

General Social Survey cycle topics,
sample size and response rate

Each survey contains a core topic as well as a standard set of sociodemographic questions. The target population for the GSS is all persons 15 years of age and over residing in Canada. Residents of the territories and fulltime residents of institutions are excluded from the sample. Data for Cycle 19 of the GSS were collected in each month from January to December 2005. The sample was distributed over the 12 months to represent any seasonal variation in the data. Over this period, a total of 19,597 people were successfully interviewed, yielding a response rate of 59%.

Computer Assisted Telephone Interviewing (CATI) is used to collect data for the GSS. Households without telephones were excluded. However, persons living in households without telephones represent less than 2% of the target population. Survey estimates have been adjusted (i.e., weighted) to account for this population. Collecting data via telephone is attractive because of lower collection costs, as well as considerable flexibility with respect to sample design. Nevertheless, telephone interviewing does have some drawbacks: non-coverage of households, while low, is concentrated in population groups with low educational attainment or low income; response rates tend to be lower than for face-to-face interviews and there are limitations on the amount and type of data which can be collected over the telephone.

Instrument design

The GSS questionnaire was designed based on qualitative testing (focus groups), a pilot test and interviewer debriefing. In order to include more content in this questionnaire while maintaining the respondent burden at its minimum, the survey was split into two sub-samples. Half of the respondents were asked questions about Culture, Sports and Physical Activity Participation and the remaining half were asked questions on Social Network and Trust and Transportation. The respondents were randomly assigned to one of the sub-samples.

Weighting

When a probability sample is used, as was the case for the GSS, the principle behind estimation is that each person selected 'represents' (in addition to himself/herself) several other persons not in the sample.

Sampling rates as well as non-response rates vary significantly from province to province and by various demographic characteristics. For example, it is known that non-respondents are more likely to be males and more likely to be younger. Therefore, unweighted sample counts cannot be considered to be representative of the survey target population.

The survey weights are used when producing estimates or performing analyses in order to account as much as possible for the geographic over- and underrepresentation of age-sex groups, months of the year, or days of the week in the unweighted file.

Data limitations

The figures which appear in this report are estimates based on data collected from a small fraction of the population (roughly one in 1,300) and are subject to error. The error can be divided into two components: sampling error and non-sampling error.

Sampling error is the difference between an estimate derived from the sample and the one that would have been obtained from a census that used the same procedures to collect data from every person in the population. The size of the sampling error can be estimated from the survey results and an indication of the magnitude of this error is given for the estimates in this report. If the estimated sampling error is greater than 33% of the estimate, it is considered too unreliable to publish and the symbol 'F' is printed in table cells where this occurs. Although not considered too unreliable to publish, estimates with an estimated error between 16.6% and 33.3% of the related estimate should be "qualified" and used with caution. These are identified with an ^'E'.

All other types of errors, such as coverage, response, processing, and nonresponse, are non-sampling errors. Many of these errors are difficult to identify and quantify.

Coverage errors arise when there are differences between the target population and the surveyed population. Households without telephones represent a part of the target population that was excluded from the surveyed population. To the extent that this excluded population differs from the rest of the target population, the estimates will be biased. Since these exclusions are small, one would expect the biases introduced to be small. However, since there are correlations between a number of questions asked on this survey and the groups excluded, the biases may be more significant than the small size of the groups would suggest.

Individuals residing in institutions were excluded from the surveyed population. The effect of this exclusion is greatest for people aged 65 and over, for whom the proportion excluded is around 7%.

To the extent that the non-responding households and persons differ from the rest of the sample, the estimates will be biased. Non-response could occur at several stages in this survey. There were two stages of information collection: at the household level and at the individual level. As such, some non-response occurred at the household level, some at the individual level. Non-response also occurred at the level of individual questions.

For most questions, the response rate was high, with non-response indicated in the data files. While refusal to answer specific questions was very low, accuracy of recall and ability to answer some questions completely can be expected to affect some of the results presented. Criteria for accepting a time use diary were stringent, requiring the reporting of information for at least 20 of the 24 hours. Time use episodes for which activity details were refused or not stated are shown as "Residual" time.