about canadian community health survey (CCHS) data - 2015/2016

Contact Peel Public Health to submit:

comments/feedback about this website, or
Questions about health data.

Need help understanding the data contained on this site?

For each data source, information about data collection and analytical methods, limitations, the citation and additional resources can be found on the Data Sources and Methods page.

The Canadian Community Health Survey (CCHS) is a federal cross-sectional survey aimed at providing health information at the regional and provincial levels. This survey collects information related to health status, health care utilization, and health determinants for the Canadian population. The CCHS underwent a major redesign that started in 2012 and was implemented in 2015. Therefore, data from 2015 onwards should not be compared to or combined with data from previous years.

DATA SOURCE

Original Source: Statistics Canada
Cite as: Canadian Community Health Survey Share File, 2015/2016, Statistics Canada. Ontario Ministry of Health and Long-Term Care.

METHODS

CCHS Redesign in 2015

In 2012, the redesign began with extensive consultations across Canada with key experts and federal, provincial and health region stakeholders. Proposed changes were implemented starting in 2015.

Around 70% of the modules that existed before the redesign have seen some level of change. These changes range from minor edits to major changes to concepts, vocabulary, or response categories. New modules were also created to allow for emerging concepts or data gaps previously identified.
Changes also include the use of higher quality survey frames and the adoption of more efficient collection and sample allocation strategies. These changes help produce higher quality data while making the survey more efficient.
However, these changes make it very difficult to determine whether any changes or consistencies between estimates pre and post redesign reflect the true population characteristic, or the effect of the significant methodological and operation changes made to the survey.
Combining cycles of CCHS data from before and after the redesign is therefore not recommended. Caution should be taken when comparing estimates across those years. Even content that has remained unchanged may not necessarily be comparable with past cycles as other major changes (e.g., new survey frames and collection methods) may still impact these estimates.

Sample Design

The target population of the CCHS is all Canadian residents aged 12 years and older. Excluded are individuals living on Indian Reserves and on Crown Lands, institutional residents, youth aged 12 to 17 living in foster homes, full-time members of the Canadian Forces, and residents of certain remote regions. Together, these exclusions represent less than 3% of the target population.
The CCHS is a sample survey with a cross-sectional design. The sample is selected using different frames based on age group. For the adult population (18 years and older), the sample of household is selected from an area frame used by the Canadian Labour Force Survey (LFS). The sampling for LFS is a two-stage stratified cluster design in which the dwelling or household is the final sampling unit. For the youth population (12 to 17 years old), a list frame created from the Canadian Child Tax Benefits (CCTB) file is used.
Starting in 2007, major changes were made to the survey design in order to improve its effectiveness and flexibility through data collection on an ongoing basis. As a result, data collection now occurs every year, but a ‘cycle’ is now considered to be a 2-year period (e.g., 2013/2014, 2015/2016).

Data Collection Methods

The interview for the health region-level survey takes 40-45 minutes: 30 minutes of common content to be asked of all sample units, 10 minutes of optional content determined by each health region from a predefined list of questionnaire modules, and 5 minutes of socio-economic and demographic content.
Data collection for the CCHS is done by either computer assisted personal or telephone interviewing.
The CCHS share file consists of all the respondents who agreed to share their data with the provincial ministries and health regions. The Health Planning Branch of the Ministry of Health and Long-Term Care (MOHLTC) distributes the Ontario portion of the share file to public health units (PHUs) that agree to the privacy conditions for access.
Statistics Canada provides health regions with the CCHS public use file. The CCHS master files can be accessed at Statistics Canada’s regional offices or regional data centres.
Additional details about the CCHS including instrument design, sampling and other measurement concepts can be found on the Statistics Canada website.

Weighting and Release Guidelines

All data have been weighted using the appropriate weighting variable.
To assess whether data are releasable, all CCHS data presented on this website have been analyzed using the survey package in Stata.
Coefficients of Variation (CV) are generated through this process and are applied to the Statistics Canada release guidelines as follows:
- CV less than 15.0: Releasable
- CV between 15.1-35.0: Use with caution. In this scenario, an asterisk (*) is presented with the data table, with a footnote stating ‘Use with caution’
- CV greater than 35.0: Not releasable. In this scenario, the acronym ‘NR’ is presented in the data table, with a footnote stating ‘not releasable due to small numbers’
Additionally, estimates are not released if there are less than 10 observations with the characteristic of interest (numerator) or less than 20 observations in the domain (denominator).

Analytical Methods

95% confidence intervals are calculated and presented within the data tables.
Generally, ‘Don’t Know’ and/or ‘Refused’ category responses are not included in the denominator calculation or presented in the data tables. When there are a sizable number of respondents who did not answer the question (i.e., 5% or greater of total respondents), a note below the table indicates the percentage of ‘don’t know’ and ‘refused’ responses. This may be presented as a range to cover multiple years of data.
‘Don’t Know’ responses to questions are included in tables where ‘I don’t know’ is a valid response option.

Variables

VARIABLE	CATEGORIES FOR ANALYSIS
Age Group¹	Standard Age Grouping (years)	Age Grouping (years) for indicators related to driving (a) or passengers (b)		Age Grouping (years for selected drinking-related indicators)
Age Group¹	12-18 19-29 30-44 45-64 65+	*Option a* 16-18 19-29 30-44 45-64 65+ *Option b* 12-15 16-24 25-44 45-64 65+		19-29 30-44 45-64 65+
Education Level of Respondent²	Less than high school (less than high school graduation)	High school graduate (no post-secondary education)		Post-secondary graduate (received post-secondary degree/diploma
Income Level³	The income levels provided in the tables is a distribution of residents of each province/health region in five categories based on the adjusted ratio of their total household income to the low-income cut-off corresponding to their household and community size. It provides a relative measure of their household income to the household incomes of all other respondents in the same province. Income variables in the 2015/2016 are populated from one of three sources: tax records, respondent provided data, and imputed data. Where respondents did not object to a link to their tax data and where a link to the appropriate tax records could be found, the income variables were determined from tax records. Where linkage to tax data was not feasible, respondent data was used. If neither, linked tax data nor respondent reported data, was available, an imputation of the total personal and total household income variables was done. NOTE: Beginning with the 2011 reference year, the household income variable is imputed. Missing values due to either respondent refusal or respondent’s lack of knowledge of household income will be completed using statistical techniques.
Immigrant Status	Recent Immigrant (person who immigrated to Canada within the last 10 years of the CCHS interview)		Long-term immigrant (person who immigrated to Canada 11 or more years prior to the CCHS interview)	Non-immigrant (born in Canada)
Ethnicity	White Latin American (including Mexico, Caribbean islands, South America) East/ Southeast Indian (including Chinese, Filipino, Southeast Asian (e.g., Cambodian, Indonesian, Laotian, Vietnamese), Japanese, Korean) Black Aboriginal (includes people of North America – North American Indian, Metis, Inuit/Eskimo) West Asian / Arab (including Arab and West Asian (e.g., Afghan, Iranian) South Asian (e.g., East Indian, Pakistani, Sri Lankan) Other (multiple responses across categories defined here)

¹Age group question:

What is your age?

²Refers to the highest level education obtained by the respondent. This question is only asked of respondents aged 14 years and older. A series of questions asked to ascertain the highest level of education.

³Income

What is your best estimate of your total household income received by all household members, from all sources, before taxes and deductions, during the year ending December 31, [current year - 1]?
Income can come from various sources such as from work, investments, pensions or government. Examples include Employment Insurance, Social Assistance, Child Tax Benefit and other income such as child support, spousal support (alimony) and rental income.

Immigrant status

In what country were you born?
In what year did you first become a landed immigrant in Canada?

Ethnicity

You may belong to one or more racial or cultural groups on the following list. Are you...?
White?
Chinese?
South Asian (e.g., East Indian, Pakistani, Sri Lankan)?
Black?
Filipino?
Latin American?
Southeast Asian (e.g., Cambodian, Indonesian, Laotian, Vietnamese)?
Arab?
West Asian (e.g., Afghan, Iranian)?
Japanese?
Korean?
Other - Specify
Don’t know, Refused
Are you an Aboriginal person, that is, First Nations, Métis or Inuk (Inuit)? First Nations includes Status and Non-Status Indians.

LIMITATIONS

Depending upon the question, self-reported data may be subject to a number of survey biases, including social desirability bias (when asked questions of a sensitive nature, respondents may give an answer that they believe to be socially acceptable), response bias (differences between those who respond to the survey and those who don’t) or recall bias (being unable to recall the information to accurately answer the question).
Errors may occur from proxy reporting (when another member of the household completes the survey for the randomly selected household member).
Some analyses are limited by sample size.
Modules change from one cycle to another. Question response categories may also change. Both of these can make comparisons of data by year difficult.

REFERENCES AND RESOURCES

Beland Y. Canadian Community Health Survey – Methodological Overview. Health Reports 2002;13(3):9-14.
Canadian Community Health Survey - Annual Component (CCHS) Detailed Information for 2014 [Internet].Ottawa (ON): Statistics Canada; [updated 2015 Apr 20; cited 2016 Oct 27]
http://www23.statcan.gc.ca/imdb/p2SV.pl?Function=getSurvey&Id=164081

Last updated: July 11, 2019

Home | About Us | Contact Us