Canadian Community Health Survey - Annual Component (CCHS)

Summary of changes

Activity on this program started: September 2000

Reference period of change - 2016

Prior to 2015, there was overlap between the area and telephone frames. After weights were produced for each frame, they had to be combined through a complicated integration step which negatively affected the design effect.

Based on the LFS redesign, cluster selection has become systematic. This has reduced the complication in initial weight adjustments.

Non-response adjustments are now based on separate models for telephone and personal interviews. New data sources have also been used for designing these adjustments.

Non-contacted units are no longer automatically deemed in-scope nonrespondents. Their scope is determined according to the found scope rate in the contacted sample.

Finally, household weights have only been created for the area frame cases (respondents aged 18 or older). These weights are representative of the whole target population (of households).

Reference period of change - 2015

In 2012, CCHS began work on a major redesign project that was completed and implemented for the 2015 cycle. The objectives of the redesign were to review the sampling methodology, adopt a new sample frame, modernize the content and review the target population. Consultations were held with federal, provincial and territorial share partners, health region authorities and academics.

As a result of the redesign, the 2015 CCHS has a new collection strategy, is drawing the sample from two different frames and has undergone major content revisions. With all these factors taken together, caution should be taken when comparing data from previous cycles to data released for the 2015 cycle onwards.

Sampling - Starting in 2015, a new multi-stage sample allocation strategy is used to give relatively fair sample distribution to the HRs and the provinces. For each age group (18 and over, 12 to 17), the sample is first allocated among the provinces using a power allocation of 0.75 according to the size of their respective population. Each province's sample is then allocated among its HRs using a power allocation of 0.35 according to the size of the population in each HR.

Prior to 2015, three sampling frames were used to select households: an area frame, a list frame of telephone numbers, and a Random Digit Dialling (RDD) sampling frame. After a selected household was contacted and rostered, a person aged 12 or older was selected according to various age-based selection probabilities.

Estimation - Prior to 2015, there was overlap between the area and telephone frames. After weights were produced for each frame, they had to be combined through a complicated integration step which negatively affected the design effect.

Based on the LFS redesign, cluster selection has become systematic. This has reduced the complication in initial weight adjustments.

Non-response adjustments are now based on separate models for telephone and personal interviews. New data sources have also been used for designing these adjustments.

Non-contacted units are no longer automatically deemed in-scope nonrespondents. Their scope is determined according to the found scope rate in the contacted sample.

Finally, household weights have only been created for the area frame cases (respondents aged 18 or older). These weights are representative of the whole target population (of households).

Reference period of change - 2013

Target population - In Nunavut, starting in 2013, the coverage was expanded to represent 92% of the targeted population. Before 2013, the coverage was 71% since the survey covered only the 10 largest communities.

Data sources - Up until 2012, sample units selected from the area frame were interviewed using the Computer-Assisted Personal Interviewing (CAPI) method while units selected from the Random Digit Dialling (RDD) and telephone list frames are interviewed using the Computer-Assisted Telephone Interviewing (CATI) method. Starting in 2013, a specific number of cases selected from the area frame were also interviewed using CATI (CATI dwelling).

Reference period of change - 2011

Imputation - Beginning with the 2011 reference year, the household income variable is imputed.

Reference period of change - 2009

Instrument design - As of the 2009 reference period, the theme content was removed from the questionnaire.

Reference period of change - 2007 (Cycle 4.1)

Until 2005, the CCHS data were collected every two years over a one year period and released every two years, about six months after the end of the collection period. In 2007, the CCHS was redesigned to address two main points: the needs of partners to increase the survey's content and the frequency of data releases, and to ensure better use of operational resources. For these reasons, the proposed changes to the CCHS design focused on improving the survey's efficiency and flexibility through ongoing data collection.

Reference period of change - 2005 (Cycle 3.1)

The data release of December 21, 2005 covers data collected over the first 6 months (January to June 2005) of the CCHS Cycle 3.1. At that time, the survey had collected information from about 69,000 individuals, aged 12 and older.

Only part of the data collected with the CCHS Cycle 3.1 questionnaire has been processed and finalized for this release. Data covering the entire 12 months collection period (January to December 2005) were released on June 13, 2006.

Reference period of change - 2003 (Cycle 2.1)

Since 2003, this survey includes the Health Services Access Survey (number 5002), which contains data at the provincial level for 2001. Please refer to its description under the Documentation section.

Reference period of change - 2000-2001 (Cycle 1.1)

Since 2000/01, this survey includes the National Population Health Survey - Household Component (number 3236), which contains data at the provincial level for 1994/95 to 1998/99.

Since 2000/01, this survey includes the National Population Health Survey - North Component (number 5004), which contains data at the territorial level for 1994/95 to 1998/99.

Report a problem on this page

Is something not working? Is there information outdated? Can't find what you're looking for?

Please contact us and let us know how we can help you.

Privacy notice

Date modified: