Canadian Health Survey on Children and Youth (CHSCY)

Detailed information for 2023

The Canadian Health Survey on Children and Youth explores issues that have an impact on the physical and mental health of children and youth, such as physical activity, the use of electronic devices, time spent in school and extracurricular activities, mental health, childhood experiences, suicidal thoughts, substance use and impact of the COVID-19 pandemic.

Additionally, the 2023 iteration of the Canadian Health Survey on Children and Youth follows respondents from the previous cycle (2019), assessing changes over time in health and well-being outcomes of Canadian children and youth.

Information from the survey will be used to develop appropriate programs and policies to better serve Canadian children and youth, as well as promote physical activity and good physical and mental health.

Data release - Fall 2024

• Questionnaire(s) and reporting guide(s)
• Description
• Data sources and methodology
• Data accuracy

Description

The main objectives of the Canadian Health Survey on Children and Youth are to:

- provide current, detailed, and ongoing health-related information on Canadian children and youth;
- better understand the impact of the COVID-19 pandemic on their health and functioning;
- assess changes over time in their health and well-being;
- examine their levels of health following the first years of the COVID-19 pandemic;
- explore issues that have an impact on the physical and mental health of Canadian children and youth.

The data collected will be used by Statistics Canada, Health Canada and the Public Health Agency of Canada, provincial and territorial ministries of Health, as well as by other federal and provincial departments.

The survey was developed by Statistics Canada, the Public Health Agency of Canada, and a national research team led by McMaster's Offord Centre for Child Studies. McMaster's Offord Centre for Child Studies received funding from the Canadian Institutes of Health Research (CIHR) to directly support the longitudinal data collection and lead the initial longitudinal analyses.

The information collected from respondents will be used to monitor, plan, implement and evaluate programs to improve the health of Canadian children and youth. Researchers from various fields are also interested in the survey data and will use the information to conduct research into the various factors that affect the health and well-being of children and youth in Canada.

Subjects

• Children and youth
• Health
• Health and well-being (youth)
• Health care services
• Risk behaviours

Data sources and methodology

Target population

For producing annual estimates, the 2023 Canadian Health Survey on Children and Youth (CHSCY) covers the population aged 1 to 22 as of January 31, 2023, living in the ten provinces. Excluded from the survey's coverage are children and youth living on First Nation reserves and other Aboriginal settlements in the provinces, children and youth living in foster homes and the institutionalized population.

Follow-up with respondents to the 2019 CHSCY will also be done in order to produce longitudinal estimates measuring change in outcomes over time for the target population of that survey (children and youth aged 1-17 as of January 31, 2019).

Based on a study comparing the Canadian Child Benefit (CCB) file with the 2018 population estimates, the CCB covers 98% of the Canadian population aged 1 to 17 in all provinces.

Instrument design

The survey content was developed based on consultation across Canada with key experts and federal and provincial stakeholders. The goal of the consultation was to provide advice to Statistics Canada on what survey content would be relevant for programs and policies and to fill data gaps related to children and youth. The questionnaire was developed by Statistics Canada, in collaboration with McMaster's Offord Centre for Child Studies, the Public Health Agency of Canada and Health Canada.

Qualitative testing by Statistics Canada's Questionnaire Design Resource Centre, using face-to-face interviews and focus groups, was conducted in November 2021 and February 2022.

Sampling

This is a sample survey with a cross-sectional design and a longitudinal follow-up.

FRAME
The sampling frame for the Canadian Health Survey on Children and Youth is the Canada Child Benefit file.

SAMPLING UNIT
The sample for the 2023 CHSCY consists of two parts: a longitudinal sample and a cross-sectional sample.
The longitudinal sampling units are children and youth for whom responses to the 2019 CHSCY were collected. These children and youth are therefore aged 5 to 22 as of January 31, 2023. Data collected from longitudinal sampling units will support longitudinal estimation while only data collected from the subset of longitudinal sampling units who are 5 to 17 years of age as of January 31, 2023 will support cross-sectional estimates.
The cross-sectional sampling units are children and youth aged 1 to 17 years of age as of January 31, 2023.

STRATIFICATION METHOD
In terms of geography, the sample is primarily stratified by province. The one exception is in Ontario, where the geographic strata consist of the province's 34 health regions. The sample is further stratified into four age groups: children aged 1 to 4 years old (cross-sectional sample only), children aged 5 to 11 years old (all sampling units), youth aged 12 to 17 years old (all sampling units) and young adults aged 18 or older (longitudinal sample only).

SAMPLING
The longitudinal sample consists of all respondents to the 2019 survey, aside from all respondents originally stratified in the Territories in 2019, as well as a subset of respondents stratified in Ontario, and a small number of other exclusions.
The cross-sectional sample consists of a random sample of units selected from each geography and age group stratum. The number of longitudinal units in the strata for 5- to 17-year-olds is considered when determining the required cross-sectional stratum sample size.
The sample size for the survey is 175,000 raw units (41,932 longitudinal units and 133,068 cross-sectional units sent to collection).

Data sources

Data collection for this reference period: 2023-03-13 to 2024-03-31

Responding to this survey is voluntary.

Data are collected directly from survey respondents.

Data collection for this reference period takes place in two waves. Data collection for all longitudinal units and a random sample of cross-sectional records in each stratum takes place from March to June 2023. The remainder of the data collection for the cross-sectional sample takes place from September 2023 to March 2024.

Respondents are given an opportunity to complete the questionnaire online using an e-questionnaire. If an e-questionnaire is not completed in the first month of collection (March 2023 for wave 1 and September 2023 for wave 2), a Statistics Canada interviewer will call and ask the respondent to complete the questionnaire over the telephone.

View the Questionnaire(s) and reporting guide(s).

Error detection

Some editing of the data is performed at the time of the interview within the electronic questionnaire. The questionnaire has built-in checks for some out-of-range or extreme values that prompt respondents and interviewers to verify the recorded answer. Flow errors are controlled in the application through programmed skip patterns. For example, questions that do not apply to the respondent are not asked.

Imputation

Non-response was not permitted for those items required for weighting. Values were imputed in the rare cases where the sex of the respondent was missing. The imputation was based on a detailed examination of the data and the consideration of any useful data such as the age and sex of other household members, and the interviewer's comments.

Information from other questions in the survey was used to impute missing or incorrect information on sleeping, eating, as well as travel and commuting. Several of these questions were added to the 2022 survey based on analysis of data from the 2015 survey, to enhance data quality when issues related to underreporting were present.

Missing information was at times imputed manually based on other responses in the diary. For example, simultaneous activities were used to update primary activities, if appropriate, when the latter was missing.

Estimation

For estimates produced from survey data to be applicable to the covered population, and not just the sample itself, users must incorporate the survey weights in their calculations. A survey weight is given to each respondent included in the final sample. This weight corresponds to the number of persons in the entire population that are represented by the respondent.

As described in the sampling section, the Canadian Health Survey on Children and Youth (CHSCY) uses the Canada Child Benefit as a frame for its sample selection. For cross-sectional sample units selected from this frame, initial weights are calculated for each sampled child. For the longitudinal sample units, their final survey weights from 2019 serve as their initial weights for the 2023 survey. In order to produce final cross-sectional survey weights, these initial weights undergo several adjustments, including a reweighting to account for the fact that longitudinal and cross-sectional sample units were selected from overlapping frames, an adjustment for non-response and a calibration to align with known population totals. A subset of these adjustments is applied to the initial weights of longitudinal units alone to produce final weights suitable for longitudinal analysis.

The steps for weighting are described in the CHSCY User Guide.

Bootstrap weights are created through resampling the original sample and applying similar adjustments to the bootstrap weights as to the sample weights.

The sample design used for this survey was not self-weighting. That is to say, the sampling weights are not identical for all individuals in the sample. When producing simple estimates, including the production of ordinary statistical tables, users must apply the proper sampling weight.

Estimates of the number of people with a certain characteristic are obtained from the data file by summing the final weights of all records possessing the characteristic of interest.

Proportions and ratios are obtained by summing the final weights of records having the characteristic of the numerator and the denominator, and then dividing the first estimate by the second.

Disclosure control

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.

Revisions and seasonal adjustment

This methodology type does not apply to this statistical program.

Data accuracy

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. 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 the estimates produced based on the data from the 2022 Time Use Survey.

RESPONSE RATES:
The overall response rate is 30.7%.

NON-SAMPLING ERROR:
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. Dwellings without telephones and mailable addresses were not collected as we had no way to contact them. 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.

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 were adjusted (i.e. weighted) to account for non-response cases.

Other types of non-sampling errors can include response errors and processing errors.

NON-RESPONSE BIAS:
The main method used to reduce nonresponse bias involved a series of adjustments to the survey weights to account for nonresponse as much as possible. Information was extracted from administrative sources and used to model and adjust nonresponse.

COVERAGE ERROR:
The frame for the regular sample was Dwelling Universe File (DUF), a file produced at Statistics Canada. All respondents in the ten provinces were interviewed by telephone or self-completed an electronic questionnaire. Dwellings that were identified as vacant at the time the sampling frame was created were excluded. Dwellings that had neither a mailing address nor an associated telephone number were not collected, as they could not be contacted by any of the survey collection modes. However, the survey estimates were weighted to include persons living in these dwellings.

OTHER NON-SAMPLING ERRORS:
For the 2022 TUS, significant effort was made to minimize bias by using a well-tested questionnaire, a proven methodology, specialized interviewers and strict quality control, and by following up with households that did not initially respond to the survey.

MODE EFFECT:
The 2022 TUS offered an Internet option to almost all survey respondents. This approach to data collection was in recognition of the need to adapt to the changing use of technology and the ever-present demands on Canadians' time. However, there are reasons to believe that the use of an electronic questionnaire might have an impact on the estimations. The impact of the collection mode on the estimates has been analyzed by selecting certain groups of key questions.

Users should refer to the survey user guide and codebook for details on which variables have been identified as being impacted by a strong or mild mode effect.