To advance and promote the discipline and professional practice
of public health epidemiology in Ontario

Canadian Community Health Survey (CCHS)

The central objective of the Canadian Community Health Survey (CCHS) is to gather health-related data at the sub-provincial levels of geography (health region or combined health regions). 


Original Source:

Statistics Canada
Distributed By:

1. Ontario Ministry of Health and Long Term Care (MOHLTC)

2. Statistics Canada
Suggested Citation:

1. Canadian Community Health Survey [year], Statistics Canada, Share File, Ontario MOHLTC

2. Canadian Community Health Survey [year], Statistics Canada, Public Use Microdata File, Statistics Canada

See Data Citation Notes.

Report an IssueWebsite

Related OPHS Standards

Chronic Disease Prevention and Well-Being Healthy Growth and Development Immunization Infectious and Communicable Diseases Prevention and Control Substance Use and Injury Prevention
 

Data Notes

About the CCHS
  • The CCHS is a national survey designed to provide health information at the regional and provincial levels. The CCHS is the data source for many of the Health Indicators generated by Statistics Canada and the Canadian Institute for Health Information.
  • The target population of the CCHS includes household residents in all provinces and territories, with the principal exclusion of populations on Indian Reserves, Canadian Forces Bases, and some remote areas. There is one randomly selected respondent per household, with an oversampling of youths resulting in a second member of certain households being interviewed. For CCHS 2000/02, only those 12 years of age and over were eligible for selection. The CCHS 2002 on mental health included respondents aged 15 years and over.  The CCHS 2004 Nutrition survey included respondents aged 6 and over (Not all data are available for every age group).
  • The CCHS sample is primarily a selection of dwellings drawn from the Labour Force Survey area sampling frame. For the regional level survey, the sample is supplemented with a random digit dialing (RDD) sample in some health regions.
  • Data collection for the CCHS is done by either computer assisted personal or telephone interviewing for the area sample or telephone interviewing for the RDD sample. The interview for the health region-level survey takes approximately 45 minutes: 30 minutes of common content to be asked in all health 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.  In Ontario, the Ministry of Health and Long-Term Care (MOHLTC) co-ordinates a process to co-operatively select a single set of optional modules for all the health regions in the province.
  • Users of the CCHS Sharing File - Ontario sample, must adhere to the corresponding guidelines when publishing or otherwise releasing any data derived from the microdata files supplied by the MOHLTC. 


Methodological Changes over Time
  • Prior to 2005, the CCHS consisted of two separate cross-sectional surveys conducted over a two-year, repeating cycle:
    • In the first year of the two-year collection cycle, a general health survey was administered that provides data at the health region level
    • In the second year, a topic specific survey was administered that provides data at the provincial level.  The names of each of the cycles and the data contained in them are as follows:
      • Cycle 1.1 – Provides general health data collected in 2000/01 at the health region level
      • Cycle 1.2 – Provides provincial level data collected in 2002 that focuses on mental health.
      • Cycle 2.1 – Provides general health data collected in 2003 at the health region level
      • Cycle 2.2 – Provides provincial level data collected in 2004 that focuses on nutrition.
  • In 2005, data collection methodology changed. Only one survey was collected over one year, and was released about 6 months after collection. So data release occurred every other year.
      • Cycle 3.1 – Provides general health data collected in 2005 at the health region level.
      • Cycle 4.1 (now referred to as CCHS 2007, see below)  – Provides general health data collected in 2007 at the health region level.
  • In 2007, data collection methodology changed again.  Data collection that provides data at a health region level now occurs on an ongoing basis.  Statistics Canada releases a file that contains annual data covering a period from January to December. In addition, a file that combines two years of data is also released. To prevent confusion with previous cycles of the CCHS, surveys are no longer designated by x.1 and x.2. Regional data files are now simply named by the year of collection (e.g., "Canadian Community Health Survey, 2008”). Topic specific data files are named by the focus of the data file (e.g., "Canadian Community Health Survey on Healthy Aging”).
  • With the establishment of the CCHS, the National Population Health Survey (NPHS) stopped including a cross-sectional component but focused instead on providing longitudinal data. This data consists of approximately 17,000 people nationally followed since 1994/95 for up to 20 years.
  • Caution should be taken when comparing the results from Cycle 1.1 (2000/01) to subsequent years of the survey, due to a change in the mode of data collection.  The sample in Cycle 1.1 had a higher proportion of respondents interviewed in person, which affected the comparability of some ke health indicators.  Please refer to this link for a full text copy of the Statistics Canada article entitled "Mode effects in the Canadian Community Health Survey: a Comparison of CAPI and CATI".  


Calibration: Issues with Household-Level Analysis
  • As noted in the CCHS_Household_Weights.pdf, the last step in creating the CCHS household weight is calibration.  The calibration step is performed to ensure that, in each household size group, the sum of the final weights approximates the number of households at the provincial level. It controls the distribution of the survey weights at the provincial level so they reflect the proportion of the households in each of the different household size groups.
  • Because calibration is done only at the provincial level, when we use household variables at the health region level, there is a potential problem if the variable is related to household size. Health region estimates calculated using the household weights may result in over- or under-representation of households in the health regions. As a result, an estimate using a calibrated household weight may not accurately represent the underlying population of interest - even for proportions.
  • In most cases, the weighted distribution of households by size should be close to the actual distribution of households by size, but unfortunately without knowing the actual counts of the number of households of various sizes in each health region, it is not possible to know how close the estimates are to reality.  Where the variable of interest is related to household size, users should be aware of the implications for interpretation of the results.  See more detailed notes in the Food Insecurity Core Indicator. If the variable of interest does not relate to household size, it is appropriate to do analysis of proportions at the PHU level.  As for all CCHS variables, it is not recommended to report counts at the PHU level.

 

Analysis Checklist for All Associated Indicators 

Choice of Microdata File
  • There are three types of CCHS files: master files, sharing files, and Public Use Microdata Files (PUMF). 
      • CCHS master files can be accessed at Statistics Canada’s regional offices or regional data centres.
      • The CCHS sharing file is a subset of the CCHS master file.  The CCHS sharing file consists of all the respondents who agreed to share their health card number and data with the provincial ministries and health regions. The Health Analytics Branch, MOHLTC distributes the Ontario portion of the sharing file to public health units (PHUs) that agree to the privacy conditions for access
      • Statistics Canada makes available a portion of the CCHS public use microdata file (PUMF), which is designed to preserve statistical analytic capabilities while ensuring respondent confidentiality. Thus, the PUMF contains fewer variables and less detailed response categories than the master file. 
  • It is recommended that public health units use the Share File provided by the Ministry of Health and Long-Term Care rather than the public use file (PUMF) provided by Statistics Canada.  The Share File has a slightly smaller sample size because respondents must agree to share their information with the province to be included; however, the share file has more variables and fewer grouped categories within variables.  The Share File is a cleaner dataset for Ontario analyses because all variables that were not common content, theme content or optional content for Ontario have been removed.  
  • There may be slight differences between results from the share file and data published on the Statistics Canada website for the Health Indicators because rates calculated for Health Indicators use the master CCHS data file.  
  • Users of the CCHS Ontario Share File must adhere to Statistics Canada's release guidelines for the CCHS data when publishing or releasing data derived from the file in any form.

Release Guidelines for CCHS Data
  • Refer to the appropriate user guide for guidelines for tabulation, analysis and release of data from the CCHS.  
  • In general, when calculating the coefficient of variation (CV) from the SHARE FILE using the bootstrap weights, users should not use or release weighted estimates when the unweighted cell count is below 10.  For ratios or proportions, this rule should be applied to the numerator of the ratio.  Statistics Canada uses this approach for the tabular data on their website.  
  • Before releasing and/or publishing data, users should determine the CV of the rounded weighted estimate and follow the following guidelines:
      • Acceptable (CV of 0.0 - 16.5%)  Estimates can be considered for general unrestricted release.  Requires no special notation. 
      • Marginal (CV of 16.6 - 33.3%)  Estimates can be considered for general unrestricted release but should be accompanied by a warning cautioning subsequent users of the high sampling variability associated with the estimates.  Such estimates should be identified by the letter E (or in some other similar fashion).
      • Unacceptable (CV greater than 33.3%) Statistics Canada recommends not to release estimates of unacceptable quality.  However, if the user chooses to do so then estimates should be flagged with the letter F (or in some other fashion) and the following warning should accompany the estimates: "The user is advised that... (specify the data) ... do not meet Statistics Canada's quality standards for this statistical program.  Conclusions based on these data will be unreliable and most likely invalid."  These data and any consequent findings should not be published.  If the user chooses to publish these data or findings then this disclaimer must be published with the data.   
  • When using only the Approximate Sampling Variables (CV) lookup tables for the Share File, data may not be released when the unweighted cell count is below 30.  This rule should be applied to the numerator for ratios or proportions.  This provides a margin of safety in terms of data quality, give the CV being utilized is only approximate. 

Bootstrap Weighting
  • Refer to the appropriate user guide for guidelines for tabulation, analysis and release of data from the CCHS.  
  • Estimates must be appropriately weighted (generally the share weight for the CCHS) and rounded.  
  • Bootstrapping is more precise than using the approximate sampling variability (C.V.) tables because it estimates the variance by generating a random sample with replacement 500 times from within the CCHS sample and estimating the variance from these 500 estimates.
  • Statistics Canada provides bootstrap weights and SPSS or SAS programs to calculate the bootstrap variable for the CCHS sharing file but this is not provided in the Public Use Microdata File (PUMF).
  • Bootstrap weights can be used for quantitative variables and complex analyses, such as regression.

Inclusion/Exclusion of Standard CCHS Response Categories
  • Not applicable respondents should be excluded; however, it is important to understand who these respondents are from the questionnaire skip patterns to be able to describe the relevant population.  
  • Users need to consider whether or not to exclude the "Refused", "Don't Know" and "Not Stated" response categories in the denominator.  Rates published in most reports, including Statistics Canada's publication Health Reports generally exclude these response categories.  In removing not stated responses from the denominator, the assumption is that the missing values are random, and this is not always the case.  This is particularly important when the proportion is these response categories is high.  


 

Associated Indicators

Adolescent Body Mass Index Adolescent Drug Use Age of Sexual Debut Breastfeeding Exclusivity at Discharge from Hospital Breastfeeding Initiation and Duration Cell Phone Use and Text Messaging While Driving Chronic Health Problems Prevalences Condom Use the Last Time among those at Risk for STDs

  

Depression Prevalence Drinking and Driving Prevalence Drinking in Excess of the Low-Risk Alcohol Drinking Guidelines Education Level Family Structure Folic Acid Supplementation Food Insecurity Frequency of Condom Use among those at Risk for STDs Heavy Drinking Episodes Home Language

  

Illicit Drug Use Influenza Vaccination Leisure-Time Physical Activity Mother Tongue Need for Assistance with Activities of Daily Living Non-Smoker Second-Hand Smoke Exposure Number of Sexual Partners Screen Time Self-Perceived Life Stress Self-Perceived Work Stress

  

Self-Reported Injury Sense of Community Belonging Smoke-free Homes Smoking Cessation Smoking During Pregnancy Smoking Status Suicidal Thoughts and Attempts Underage Alcohol Drinking Vegetable and Fruit Consumption Youth Sexual Activity
 

References

General References

Acknowledgements

Lead Authors

Carma Lynn Wylie, Niagara Region Public Health

Elizabeth Rael, Ministry of Health Promotion and Sport

Contributing Authors

Jennifer Skinner 

Ahalya Mahendra

Elsa Ho

  

   

Revision History

 This Core Indicator Product webpage is maintained by the Healthy Eating Active Living Subgroup.  
Date Review Type Author Changes PDF
April 15, 2011 Formal Review Healthy Eating Active Living Subgroup
  • Data Notes updated
  • Release Guidelines updated
  • References and Resources updated
September 23, 2019
Website Update:
No Content Review
Caitlyn Paget,
on behalf of the CIWG
    Migrated to new website structure and format, including:
  • Reorganized content to provide high-level information at a glance, and move in-depth analytic information into dedicated sections for users to access when needed.  
  • Added short data source description in header.  
  • Moved Analysis Checklist items that are specific to the data source from the indicators pages to this data source page to reduce duplication.  
  • Crosslinked to relevant Core Indicators webpages including OPHS program standard(s) and associated indicator(s).
  • Added Revision History table, with PDF copy of previous version for reference.  
     
APHEO's Core Indicators Project has been developed through collaboration across the field of public health in Ontario, 
to provide standardized methodology for population health assessment, to measure complex concepts of individual and community health.
Please contact core.indicators@apheo.ca for further information.  
   
Documents Download 2011-2024 © APHEO- Association of Public Health Epidemiologists in Ontario
Design by: LifeLine