The two primary objectives of the General Social Survey (GSS) are: to gather data on social trends in order to monitor changes in the living conditions and well being of Canadians over time; and to provide information on specific social policy issues of current or emerging interest.
The purpose of this survey is to provide a snapshot of the lives of caregivers and care receivers in today's Canada.
Data release – September 10, 2013.
This survey collects data on the situation of Canadians who receive help or care because of a long-term health condition, a disability or problems related to aging, and of those who provide help or care to family members or friends with those conditions. Data from this survey will help us to better understand the needs and challenges faced by these Canadians, and allow policy makers to design programs that meet their needs.
Questions in the survey cover the types and amount of care family caregivers provide, the kinds and amounts of care Canadians receive, and the unmet needs of those who need care but are not receiving it. An expanded set of questions covers the impact of caregiving on various aspects of the lives of caregivers. All respondents will be asked questions about their overall health, employment, housing and other socio-demographic characteristics such as birth place, religion and language.
Results from this survey will be used by analysts and researchers to study current situations and trends, and by many government departments to develop policies and programs that can have an impact on individuals who receive care, their families, those who provide care, and those who may need or provide care in the future.
The target population for the GSS is all non-institutionalized persons 15 years of age or older, living in the ten provinces of Canada.
In the GSS, all respondents are contacted and interviewed by telephone. Thus persons in households without telephones cannot be interviewed. However, persons living in such households represent less than 2% of the target population.
The questionnaire was designed based on research and extensive consultations with data users. Qualitative testing, conducted by Statistics Canada's Questionnaire Design Resource Center (QDRC), was carried out, where one-on-one in-depth interviews with respondents from across Canada highlighted questions that worked well and others that needed clarification or redesign. QDRC staff compiled a detailed report of the results along with their recommendations. All comments and feedback from qualitative testing were carefully considered and incorporated into the survey when possible.
The pilot test (which resulted in 2,000 interviews conducted) of the data collection methodology and questionnaire was conducted in September 2011. This test allowed for the questionnaire to be fully tested over a two-week period with respondents in British Columbia, Alberta and Quebec. Data collection observations of the pilot test were conducted by survey team members. All observation comments and suggestions were fully documented and, along with comments from interviewers, analyzed and implemented into the survey when possible.
This is a sample survey with a cross-sectional design.
In order to carry out sampling, the ten provinces of the target population are divided into strata, i.e. geographic areas.
Many of the Census Metropolitan Areas (CMAs) are each considered separate strata. This is the case for St. John's, Halifax, Saint John, Montreal, Quebec City, Toronto, Ottawa, Hamilton, Winnipeg, Regina, Saskatoon, Calgary, Edmonton and Vancouver. CMAs not on this list are located in Quebec, Ontario and British Columbia. Three more strata are formed by grouping together the remaining CMAs in each of these three provinces. Finally, the non-CMA areas of each of the ten provinces form ten more strata. This results in 27 strata in all.
Phone numbers, used to contact households for the survey, are randomly selected through a technique called "Random Digit Dialling" (RDD). All sampled telephone numbers are numbers that are listed as 'in service for residential use' based on Statistics Canada's administrative sources. A survey respondent is randomly selected once contact is made with the household.
For Cycle 26, a technique called "rejective sampling" is used to reach more caregivers and care receivers. This technique has been used in other surveys in order to include more respondents from hard-to-reach or small populations. After a respondent is classified as a caregiver, care receiver, both or neither, sub-sampling will be carried out for selected respondents who are neither caregivers nor care receivers. All respondents who are caregivers or care receivers will do a long interview. Those who are NOT caregivers or care receivers will be randomly divided into two groups. One group will do a long interview, while the other group will do a short interview.
There will be 25,000 respondents who will complete a long interview for the main survey from all the phone numbers selected. There will also be an additional 11,500 respondents who will complete a short interview.
Data collection for this reference period: 2012-03-01 – 2012-12-31
Responding to this survey is voluntary.
Data are collected directly from survey respondents.
Data collection for the survey is conducted by Computer Assisted Telephone Interviewing (CATI) methods through the Halifax, Winnipeg, Edmonton and Sherbrooke regional offices. Each regional office will be assigned phone numbers from which to collect the survey information. Initial contact is made through an introductory mail out letter. Proxy interviews are permitted in cases where the selected respondent does not speak either of the official languages or where the respondent is not able to take part in the survey because of health reasons.
Error detection was done through edits programmed into the CATI system.
The CATI data capture program allowed a valid range of codes for each question and built-in edits, and automatically followed the flow of the questionnaire.
All survey records were subjected to computer edits throughout the course of the interview. The CATI system principally edited the flow of the questionnaire and identified out of range values. As a result, such problems could be immediately resolved with the respondent. If the interviewer was unable to correctly resolve the detected errors, it was possible for the interviewer to bypass the edit and forward the data to head office for resolution. All interviewer comments were reviewed and taken into account in head office editing.
Head office edits performed the same checks as the CATI system as well as more detailed edits.
The flow editing carried out by head office followed a 'top down' strategy, in that whether or not a given question was considered "on path" was based on the response codes to the previous questions. If the response codes to the previous questions indicated that the current question was "on path", the responses, if any, to the current question were retained, though "don't know" was recoded as 9 (99 or 999, etc.) and refusals were recoded as "Not Stated", i.e. 8 (98 or 998, etc.). If the response codes to the previous questions indicated that the current question was "off path" because the respondent was clearly identified as belonging to a sub-population for which the current question was inappropriate or not of interest, the current question was coded as "Not Asked", i.e. 7 (97 or 997, etc.).
Due to the nature of the survey, imputation was not appropriate for most items so missing data were coded as 'Not stated'.
However, non-response was not permitted for those items required for weighting. Values were imputed in the rare cases where either of the following was missing: sex or number of residential telephones.
When a probability sample is used, as was the case for the GSS, the principle behind estimation is that each person selected in the sample represents (in addition to himself/herself) several other persons not in the sample. For example, in a simple random sample of 2% of the population, each person in the sample represents 50 persons in the population (himself/herself and 49 others). The number of persons represented by a given respondent is usually known as the weight or weighting factor.
GSS Cycle 26 was a survey of individuals and the analytic files contain questionnaire responses and associated information from 23,093 respondents.
Two weighting factors were placed on the Main File. They are listed and explained below:
WGHT_PER: This is the basic weighting factor for analysis at the person level, i.e. to calculate estimates of the number of persons (non-institutionalized and aged 15 or over) having one or several given characteristics.
WGHT_HSD: This is the usual GSS household weight, to be used only for estimates of household characteristics. For example, to estimate the number of households that live in low-rise apartments, WGHT_HSD should be summed over all records with this characteristic.
In addition to the estimation weights, bootstrap weights have been created for the purpose of design-based variance estimation.
Quality assurance measures were implemented at every collection and processing step. Measures included recruitment of qualified interviewers, training provided to interviewers for specific survey concepts and procedures, observations of interviews to correct questionnaire design problems and instruction misinterpretations, procedures to ensure that data capture errors were minimized and edit quality checks to verify the processing logic. Data are verified to ensure internal consistency and they are also compared to other published sources.
Statistics Canada is prohibited by law from releasing any information it collects which could identify any person, business, or organization, unless consent has been given by the respondent or as permitted by the Statistics Act. Various confidentiality rules are applied to all data that are released or published to prevent the publication or disclosure of any information deemed confidential. If necessary, data are suppressed to prevent direct or residual disclosure of identifiable data.
For micro data: content is reduced and modified. For tabular data: sensitive cells correction methods such as cell collapsing and suppression are applied.
The methodology of this survey has been designed to limit the number of errors and to reduce their potential effects. However, the results of the survey remain subject to both sampling and non-sampling error.
As the data are based on a sample of persons they are subject to sampling error. That is, estimates based on a sample will vary from sample to sample, and typically they will be different from the results that would have been obtained from a complete census. The potential range of this difference has been estimated for key data and used to produce tables that can be used to estimate the sampling variability of many estimates. More precise estimates of the sampling variability of estimates can be produced with the bootstrap method using bootstrap weights that have been created for this survey. The bootstrap method was used to estimate the sampling variability for all of the estimates produced based on the data from GSS Cycle 26. Estimates with high sampling variability are indicated in this publication and all of the highlighted differences between subgroups of the population are significant at the 95% level.
Even a census of the population of interest produces estimates subject to error. While these are called non-sampling errors, estimates from samples still contain errors of this type. Common sources of these errors are imperfect coverage and non-response.
Coverage errors (or imperfect coverage) 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 the excluded population differs from the rest of the target population, the results may be biased. In general, since these exclusions are small, one would expect the biases introduced to be small.
The overall response rate for GSS cycle 26 was 65.7%. 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. Some non-response occurred at the household level, and some at the individual level. Survey estimates have been adjusted (i.e. weighted) to account for non-response cases. To the extent that the non-responding households and persons differ from the rest of the sample, the results may be biased.
Other types of non-sampling errors can include response errors and processing errors.