Health Promotion Survey (HPS)

Detailed information for 1990




Every 5 years

Record number:


The objectives of the HPS were to update and expand the national and provincial baseline data on the knowledge, attitudes, beliefs, intentions and behaviours of adult Canadians on a wide range of health promotion issues.

Data release - March 31, 1995


Health and Welfare Canada (now Health Canada) was interested in collecting information to assist them in planning programs to encourage Canadians to adopt and maintain healthy lifestyles. The Health Promotion Survey, conducted in 1985, provided the baseline information on current attitudes and behaviours. The survey was conducted again in 1990 to evaluate programs initiated by Health and Welfare to promote health.

Although this survey has been discontinued, it remains a source of historical data on the health of Canadians, and some products and services are still available.


  • Health
  • Lifestyle and social conditions

Data sources and methodology

Target population

The target population for the HPS was all persons 15 years of age or older living in Canada with the following two exceptions:

1. residents of the Yukon and the Northwest Territories;
2. full-time residents of institutions.

Because the HPS was conducted using telephone sampling techniques, households (and thus persons living in households) that do not have telephones were obviously excluded from the surveyed population. This accounts for less than 3% of the total population. However, the survey estimates have been weighted to include persons without telephones.

Instrument design

The two main components of the survey were the Control Form and the 1990 HPS Data questionnaire.

The Control Form was used to select a respondent within the household. The choice of questions for the Control Form had to respect certain constraints associated with Random Digit Dialling surveys.

Although the 1990 questionnaire closely resembled the one used in 1985 several modifications were made:

1) The wording of several questions from the 1985 survey was improved to correct for observed deficiencies. Question I1 -(about the number of breakfasts in the past week) is an example of this kind of question.
2) Some questions asked in 1985 were dropped from the 1990 questionnaire. This was done to avoid duplication with other health surveys and to reflect the new mission statement of the Health Promotion Directorate.
3) New sections were added, such as the section on the prevention of sexually transmitted diseases and dental health section.

In March 1990, prior to the national survey, a pre-test of the two 1990 questionnaires was carried out in two Statistics Canada regional offices, Halifax and Montréal. Approximately 300 respondents were interviewed in each regional Office. The purpose of the pretest was to verify the quality of the collection instrument in both official languages (i.e. interview length, respondent reaction, etc.). Selected respondents from two strata (rural and urban) within each of the two provinces (Nova Scotia and Québec) were interviewed. Based on the pre-test results and interviewer de-briefings some final wording changes were made to the questionnaire used in the full survey.


This is a sample survey with a cross-sectional design.

The Health Promotion Survey employed Random Digit Dialling sampling techniques. For the ten provinces, the Waksberg Method was used.

Data sources

Data collection for this reference period: June 1, 1990 to June 30, 1990

Responding to this survey is voluntary.

Data are collected directly from survey respondents.

Interviews were conducted from Statistics Canada's eight Regional Offices, from June 1 - 30, 1990.

All interviews were conducted between 8:30 a.m. to 9:30 p.m. local time during week days. Interviews were also conducted during daytime on Saturdays.

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

Error detection

Following data capture, all survey records were subjected to an exhaustive computer edit. Partial non-response, flow pattern errors and abnormally high or low responses were identified. Records with missing or incorrect data were assigned non-response codes or in some cases, imputed from other areas from the same questionnaire. The one exception to this was the selected person's age and sex. In some cases these variables were imputed from another record (i.e. a donor record). Sampling rates, as well as non-response rates, varied significantly from province to province. Non-respondents were more likely to be males and more likely to be younger (15-24). Thus unbiased estimates are only obtained with the application of the weights.


Initial processing resulted in the formation of 13,960 records. To accommodate most statistical packages, all blank fields were converted to a numeric value.

A customized edit program was designed using the "bottom up" approach to correct for erroneous data flow as a result of either interviewer or data capture error. The "bottom up" method of editing looks at responses within blocks of questions to determine the correct flow. Then, questions which were determined to be "NOT APPLICABLE" for a particular response pattern were given a standard value (i.e. "8", "98", etc,).

Checks were also carried out to compare certain fields. For example, age and year of birth were examined for consistency.

Industry and Occupation were coded using a computerized system developed for the Labour Force Survey.

After all processing the micro data file contains 13,792 records. (Note: 268 records were dropped from the file for several reasons - refer to section 9.2 and 9.3 of the user guide.)


When a probability sample is used, as was the case for the HPS, the principle behind estimation is that each person selected in the sample
represents (besides himself/herself) several other persons not in the sample. For example, in a simple random sample of 1% of the population, each person in the sample represents 100 persons in the population.

For the HPS microdata file an overall statistical weight (called "WEIGHT") was placed on each record to represent the number of sampled persons that the record represents. This weighting factor refers to the number of times a particular record should contribute to a population estimate. For example, to estimate the number of persons who describe their lives as being "Very Stressful" the value of WEIGHT is summed over all records with question A2 having a code of 1. The HPS weighting process is described in Section 12.2 of the User Guide.

Quality evaluation

Considerable time and effort has been made to reduce non-sampling errors in the HPS. Quality assurance measures have been implemented at each step of the data collection and processing cycle to monitor the quality of the data. These measures include the use of highly skilled interviewers, extensive training of interviewers with respect to the HPS procedures and questionnaires, observation of interviewers to detect problems of questionnaire design or misunderstanding of instructions, procedures to ensure that data capture errors are minimized and coding and edit quality checks to verify the processing logic. Despite these efforts non-sampling error is bound to have some impact on HPS estimates.

Disclosure control

Statistics Canada is prohibited by law from releasing any information it collects that 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.

In order to prevent any data disclosure, confidentiality analysis is done using the Statistics Canada Generalized Disclosure Control System (G-Confid). G-Confid is used for primary suppression (direct disclosure) as well as for secondary suppression (residual disclosure). Direct disclosure occurs when the value in a tabulation cell is composed of or dominated by few enterprises while residual disclosure occurs when confidential information can be derived indirectly by piecing together information from different sources or data series.

Revisions and seasonal adjustment

This methodology does not apply to this survey.

Data accuracy

For the HPS 35,077 phone numbers were called and 17,674 of these were determined to belong to households. Of these households, 2,288 (12.9%) were non-responding households because, either they refused to respond or could not respond to the survey. Included here, as well, are households that could not be reached during the entire survey collection period.

For the 15,386 responding households where an interview was attempted, 511 selected persons refused to complete the survey (one person was randomly selected per responding household). In addition, there were 168 records which were dropped during Head Office Processing either because of partial non-response or because the respondent was less than 15 years old.

If it is assumed that all the non-responding and dropped households were all "in scope" (i.e., had at least one member 15 years old or older), then the overall survey response rate was 78.0%.


Date modified: