COVID-19 Vaccination Coverage Survey (CVCS)
Detailed information for May 2021 (cycle 2)
The objective of this survey is to collect information on COVID-19 vaccination rates.
Data release - July 9, 2021
This survey aims to
- measure COVID-19 vaccination rates across Canada
- find out about knowledge and perceptions regarding COVID-19 vaccines and about the sources of information that people rely on.
Results from the CVCS will help the Canadian government plan a response to the pandemic that addresses the health and safety needs of the Canadian population.
- Prevention and detection of disease
- Society and community
Data sources and methodology
The target population for the survey is people aged 18 years and older, living in the 10 provinces.
The target population excludes persons living in the territories, persons living on reserves and in other Indigenous settlements, persons living in institutions and persons living in collective dwellings.
The questionnaire content was developed by the Centre for Social Data Integration and Development (CSDID) at StatCan, in consultation with epidemiologists from the Public Health Agency of Canada (PHAC).
StatCan's Questionnaire Design Resource Centre (QDRC) was consulted during development of the initial questionnaire. QDRC was responsible for conducting 20 one-on-one, in-depth cognitive interviews: 10 in French, 10 in English, all of them conducted on-line. During the QDRC cognitive interviews, respondents were presented with mock-ups of electronic questionnaire (EQ) screens in PDF format.
Objectives of the testing were as follows
- To obtain feedback from respondents on their overall impressions of and reactions to the EQ.
- To test the cognitive processes of respondents in answering the questions.
- To assess respondents' understanding of specific concepts, terminology, questions and response categories.
- To assess the availability of the information requested.
- To test respondents' ability and willingness to respond to the EQ.
- To determine the appropriateness and completeness of response categories.
- To test the questionnaire's format, layout and the flow of questions.
- To test the respondent-friendliness of the EQ (i.e., that it is easily understood and can be accurately completed).
On the basis of these interviews, QDRC wrote a detailed report of recommended improvements to the questionnaire. Recommendations were considered by CSDID, in consultation with their clients in PHAC, and were implemented wherever possible. Following this initial phase of development, questionnaire content was further developed as an on-line application. The questionnaire underwent further testing for accessibility in this on-line format, as well as rigorous internal validation, to ensure optimal functionality prior to its being finalized. The final version of the questionnaire was then subject to a final approval from QDRC.
This is a sample survey with a cross-sectional design.
The frame is the Dwelling Universe File. Institutions, collective dwellings and dwellings on Indigenous reserves are excluded.
The CVCS sample has a two-stage design: the sampling unit for the first stage is the dwelling, and the sampling unit for the second stage is the person. During collection, all members of the dwelling are listed and a person aged 18 years or over is automatically selected using various selection probabilities based on age and household composition.
The CVCS frame was stratified by province, and a simple random sample of dwellings was independently selected within each province.
Sampling and sub-sampling
Sufficient sample was allocated to each of the provinces so that the survey could produce provincial-level estimates. For this CVCS cycle, a sample of 20,000 dwellings was selected in the provinces and sent to collection.
Data collection for this reference period: 2021-04-12 to 2021-05-12
Responding to this survey is voluntary.
Data are collected directly from survey respondents.
Invitation letters were sent out by mail. Respondents were invited to complete the survey in either official language. While self-response EQ was the primary method of collection for the CVCS, computer Assisted Telephone Interview (CATI) was used to follow up in cases of non-response. Proxy reporting was not permitted, rather, it was required that the survey be completed by the household member selected in the introductory letter or in the interviewer entry pages. The average estimated time to complete the survey was 15 minutes.
View the Questionnaire(s) and reporting guide(s) .
The purpose of processing survey data is to convert the collected data into a form that is appropriate for analysis and tabulation.
For CVCS, collection was performed using an electronic questionnaire (EQ) which was completed by the respondent or with the help of an interviewer. This mode of collection allowed for certain edits to be built into the application. For example, validity edits were built into the collection application, to ensure that responses fall within an accepted range. Other validity edits would prompt a respondent to correct a character value if entered into a numeric field, or a numeric value entered into character fields.
After collection, the raw data file was put through a series of standard processing steps designed to clean the data and help ensure its consistency, thereby increasing its usefulness. These verifications were carried out at both at the micro and macro level.
Next, flow edits replicated the flow patterns used in the application and set the non-applicable questions to a value of 'Valid Skip'. Non-responses to questions that were applicable to the respondent but were not answered, were set to a value of 'Not Stated'.
In addition, various types of editing were done to detect missing or inconsistent information. For example, edits were performed to check the logical relationship between responses. Also, as cycle 2 of the survey was conducted at a time when it was known that only vaccines with a two-dose schedule had been administered, responses that indicated receipt of a single-dose shot were corrected to say two-dose.
New variables were derived using collected data. A derived variable may be created based on a single variable (by re-grouping or collapsing categories) or based on several variables (by combining them together to define a new concept).
Participants who reported a gender of "Other" were randomly assigned a sex of either "Male" or "Female" for analytical purposes.
Valid values of the postal code (or its first three digits or first digit in the absence of a complete postal code) were used to derive a province of residence.
No imputation was performed on questions left unanswered by participants.
The COVID-19 Vaccination Coverage Survey (CVCS) is a probability survey. As is the case with any probability survey, the sample was selected so as to be able to produce estimates for a reference population. Therefore, each unit in the sample represents a certain number of units in the population in addition to themselves. This number is referred to as the survey weight.
1) Each selected dwelling is given an initial weight equal to the inverse of its selection probability from the sampling frame. Dwellings identified as out-of-scope during collection are dropped from the sample.
2) The weights for responding households are adjusted to represent the households that did not respond. Adjustment factors are calculated separately by province, dwelling type and household income.
3) The household weights are calibrated so that the sum of the weights match provincial-level household size demographic counts.
4) Person weights are computed by multiplying the household-level weights by the inverse of the probability of selecting the person within the household.
5) The person weights are calibrated so that the sum of the weights matches demographic population counts at the provincial level by census metropolitan area and at the provincial level by age group by gender level.
To estimate variances directly, one set of 1,000 bootstrap weights was also created and made available in a separate file.
The Generalized Estimation System was used to generate the survey weights and bootstrap weights.
While rigorous quality assurance mechanisms are applied across all steps of the statistical process, validation and scrutiny of the data by statisticians are the ultimate quality checks prior to dissemination. Many validation measures were implemented. They included (among others):
a) Analysis of changes over time (where possible)
b) Verification of estimates through cross-tabulations
c) Consultation with stakeholders internal to Statistics Canada
d) Consultation with the Public Health Agency of Canada
e) Review of production processes
f) Coherence analysis based on quality indicators
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.
Survey errors come from a variety of different sources. One dimension of survey error is sampling error. Sampling error is defined as the error that arises because an estimate is based on a sample rather than the entire population. Sampling error can be expressed through a confidence interval or coefficient of variation.
The response rate for cycle 2 of the COVID-19 Vaccination Coverage Survey was 59.15%.
Measurement errors (sometimes referred to as response errors) occur when the response provided differs from the real value; such errors may be attributable to the respondent, the questionnaire, the collection method or the respondent's record-keeping system. Such errors may be random or they may result in a systematic bias if they are not random.
Processing errors are the errors associated with activities conducted once survey responses have been received. They include all data handling activities after collection and prior to estimation. Like all other errors, they can be random in nature, and inflate the variance of the survey's estimates, or they can be systematic, and introduce bias. It is difficult to obtain direct measures of processing errors and their impact on data quality especially since they are mixed in with other types of errors (nonresponse, measurement and coverage).
The survey estimates are adjusted to account for non-response through the survey weights. To the extent that the non-responding households and persons differ from the rest of the sample, the results may be biased.
Coverage errors arise when there are differences between the target population and the observed population. For example, the observed population is persons living in dwellings with mailable addresses on the frame. Approximately 95.4% of the dwellings on the frame had a mailable address. To the extent that the excluded population differs from the rest of the target population, the results may be biased.