Canadian Financial Capability Survey (CFCS)

Canadian Financial Capability Survey (CFCS)
Summary of changes
Other reference periods
Related products

Detailed information for 2008

Status:

Inactive

Frequency:

Occasional

Record number:

5159

The intention of the survey is to collect information that will illuminate the degree of knowledge that Canadians have concerning financial decision-making.

Data release - December 22, 2009 (2008 data, collected in 2009)

Description

The Canadian Financial Capability Survey (CFCS) will shed light on Canadians' knowledge, abilities and behaviour concerning financial decision-making. In other words, how Canadians understand their financial situation, the financial services available to them and their plans for the future. The survey is designed to collect information surrounding respondents' approaches to day-to-day money management and budgeting, longer term money management and general financial planning.

Subjects

  • Household assets, debts and wealth
  • Household spending and savings
  • Income, pensions, spending and wealth

Data sources and methodology

Target population

The target population for the CFCS is all persons 18 years of age and over living in Canada. Full-time residents of institutions and residents of the Yukon, Northwest Territories and Nunavut are not included in this survey. Telephone numbers that might correspond to these areas have been excluded from the sample.

Instrument design

In the case of the Canadian Financial Capability Survey, it was proposed from conception that it be collected by telephone interview; an approach that reflected previous successes in other countries with similar subject matter. A first round of cognitive testing, including one-on-one interviews and focus group discussions, across Canada in spring 2007 confirmed that this was indeed the best way to proceed.

With the addition of Finance Canada and the Bank of Canada as active partners, the content was modified to reflect each of the partners data needs. This led to a second round of cognitive testing in only a few selected cities in the spring of 2008. The computer-assisted telephone interviewing (CATI) application was developed and tested during the summer and fall months in 2008.

Sampling

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

Because the survey is conducted using a sample of telephone numbers, households (and thus persons living in households) that do not have telephone land lines were excluded from the sample population. This means that people without telephones and people with cell phones only, were excluded. People without land lines account for about 8% of the target population. However, the survey estimates have been weighted to include persons without land lines.

The sample design is a two-phase stratified random sample of telephone numbers. In the first phase, households are selected using Random Digit Dialling (RDD). In the second phase, one individual from the contacted household is selected.

The sample for the CFCS was generated using a refinement of RDD sampling called the Elimination of Non-Working Banks (ENWB). Within each province-stratum combination, a list of working banks (area code + next five digits) was compiled from telephone company administrative files.

Next, a systematic sample of banks (with replacement) was selected within each stratum. For each selected bank, a two-digit number (00 to 99) was generated at random. This random number was added to the bank to form a complete telephone number. This method allowed listed and unlisted residential numbers as well as business and non-working numbers (i.e. not currently or never in service), to have a chance of being in the sample. A screening activity aimed at removing not in service and known business numbers was performed prior to sending the sample to the computer-assisted telephone interviewing (CATI) unit.

Each telephone number in the CATI sample was dialled to determine whether or not it reached a household. If the telephone number is found to reach a household, the person answering the telephone was asked to provide information on the individual household members. The ages of the household members were used to determine who, in the household, would be selected for the interview.

In order to ensure that people from all parts of Canada were represented in the sample, each of the 10 provinces were divided into strata or geographic areas. Census Metropolitan Areas (CMA) are areas defined by the Census of Population and correspond roughly to the cities with populations of 100,000 or more. Many CMAs were each considered as a separate stratum. This was the case for St. John's, Halifax, Saint John, Montreal, Quebec City, Toronto, Ottawa, Hamilton, Winnipeg, Regina, Saskatoon, Calgary, Edmonton, and Vancouver. The remaining CMAs in Ontario, Quebec, and British Columbia were combined into two separate strata. Generally, within each province, a non-CMA stratum was created though in Prince Edward Island there was only one stratum for the entire province. This resulted in a design with 27 strata in all.

The survey collected data from 15,519 respondents.

Data sources

Data collection for this reference period: 2009-02-11 to 2009-05-09

Responding to this survey is voluntary.

Data are collected directly from survey respondents.

Proxy interviews are not permitted.

Data are collected using computer-assisted telephone interviewing (CATI). A front-end module contains a set of standard response codes for dealing with all possible call outcomes, as well as the associated scripts to be read by the interviewers. A standard approach set up for introducing the agency, the name and purpose of the survey, the survey sponsors, how the survey results will be used, and the duration of the interview is used.

The CATI application ensure that only valid question responses are entered and that all the correct flows are followed. Edits are built into the application to check the consistency of responses, identify and correct outliers, and to control who gets asked specific questions. This means that the data are already quite "clean" at the end of the collection process.

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

Error detection

Error detection is done through edits programmed into the CATI system. The data capture program allows a valid range of codes for each question and built-in edits, and automatically directs the flow of the questionnaire.

All survey records are subjected to computer edits throughout the course of the interview. The CATI system principally edits the flow of the questionnaire and identifies out-of-range values. As a result, such problems can be immediately resolved with the respondent. If the interviewer is unable to correctly resolve the detected errors, it is possible for the interviewer to bypass the edit and forward the data to head office for resolution. Interviewer notes and comments are reviewed and taken into account in head office editing.

Head office edits perform the same checks as the CATI system as well as more detailed edits. Errors in the questionnaire flow, where questions which did not apply to the respondent were found to contain answers, were edited automatically to resolve inconsistencies with answers to previous, and in some cases, subsequent questions. Errors involving a lack of information for questions which should have been answered were treated by coding the item as a non-response, or "not-stated."

Imputation

Imputation is the process that supplies valid values for those variables that have been identified for a change either because of invalid information or because of missing information. The new values are supplied in such a way as to preserve the underlying structure of the data and to ensure that the resulting records will pass all required edits. In the case of the CFCS, donor imputation was used to fill in missing data for item and partial non-response for personal and household income.

All imputations involved donors that were selected using a score function. For each item non-response or partial non-response records (also called recipient records), certain characteristics were compared to characteristics from all the donors. When the characteristics were the same between a donor and the recipient, a value was added to the score of that donor. The donor with the highest score was deemed the "closest" donor and was chosen to fill in missing pieces of information of the non-respondents. If there was more than one donor with the highest score, a random selection occurred. The pool of donors was made up in such a way that the imputed value assigned to the recipient, in conjunction with other non-imputed items from the recipient would still pass the edits.

Imputation of personal and household incomes was performed (together whenever necessary, and then always from the same donor).

In total, almost 10,000 respondents (63%) were eligible donors having reported both household and personal incomes. Respondents who did not provide a dollar estimate of their incomes were asked questions in order to derive an income range. Almost 2,000 respondents (13%) did not provide any information on their incomes. The reported income ranges and the missing income information were imputed by the donor values in a series of steps, depending on the information available for other variables involved in forming the imputation groups. In a final step, the income values, whether reported or imputed, were converted into quartiles, quintiles, and deciles to assist in the analysis of survey results.

Estimation

For the microdata file, statistical weights were placed on each record to represent the number of sampled persons that the record represents. One weight was calculated for each responding person.

The weighting for the Canadian Financial Capability Survey (CFCS) consisted of several steps:
- calculation of a basic weight,
- adjustments for non-response,
- dropping out-of-scope records,
- an adjustment for selecting one individual in the household, and finally,
- an adjustment to make the populations estimates consistent with known province-age sex totals from the Census projected population counts for persons 18 years and over.

The last step of weighting consists of an adjustment to the person weights in order to make population estimates consistent with external population counts for persons 18 years and older. This is known as post-stratification. The following external control totals, as projected for February 2009, were used:

1) Population totals by province, sex and the following age groups: 18 to 24, 25 to 29, 30 to 34, 35 to 39, 40 to 44, 45 to 49, 50 to 54, 55 to 59, 60 to 64, 65 to 69 and 70 and over.

2) Population totals of persons aged 18 years and older in Census Metropolitan Areas.

The method called generalized regression (GREG) estimation was used to modify the weights to ensure that the survey estimates agreed with the external totals simultaneously along the two dimensions.

In order to supply coefficients of variation (CV) which would be applicable to a wide variety of categorical estimates produced from this microdata file and which could be readily accessed by the user, a set of Approximate Sampling Variability Tables has been produced. These CV tables allow the user to obtain an approximate coefficient of variation based on the size of the estimate calculated from the survey data.

The coefficients of variation are derived using the variance formula for simple random sampling and incorporating a factor which reflects the multi-stage, clustered nature of the sample design. This factor, known as the design effect, was determined by first calculating design effects for a wide range of characteristics and then choosing from among these a conservative value to be used in the CV tables which would then apply to the entire set of characteristics. The variance estimation used the Mean Bootstrap method.

Quality evaluation

Considerable time and effort were expended to reduce non-sampling errors in the survey. Quality assurance measures were implemented at each step of the data collection and processing cycle to monitor the quality of the data. These measures include extensive training of interviewers with respect to the survey procedures and computer-assisted telephone interviewing (CATI) application, observation of interviewers to detect problems of questionnaire design or misunderstanding of instructions and testing of the CATI application to ensure that range checks, edits and question flow were all programmed correctly.

A comparison of selected data from the CFCS was made with other Statistics Canada surveys, such as the 2006 Census of Population (record number 3901), the Survey of Labour and Income Dynamics (record number 3889) and the Survey of Financial Security (record number 2620) to ensure consistency.

Disclosure control

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.

It should be noted that the "Public Use" Microdata Files (PUMF) may differ from the survey "master" files held by Statistics Canada. These differences usually are the result of actions taken to protect the anonymity of individual survey respondents. The most common actions are the suppression of file variables, grouping values into wider categories, and coding specific values into the "Not stated" category.

Revisions and seasonal adjustment

This methodology does not apply to this survey.

Data accuracy

While considerable effort is made to ensure high standards throughout all stages of collection and processing, the resulting estimates are inevitably subject to a certain degree of error. These errors can be broken down into two major types: non-sampling and sampling error.

Considerable time and effort were expended to reduce non-sampling errors in the survey. Quality assurance measures were implemented at each step of the data collection and processing cycle to monitor the quality of the data. These measures included cognitive testing to ensure concepts were clear, extensive training of interviewers with respect to the survey procedures and computer-assisted telephone interviewing (CATI) application, observation of interviewers to detect problems of questionnaire design or misunderstanding of instructions and testing of the CATI application to ensure that range checks, edits and question flow were all programmed correctly.

Non-response is an important source of non-sampling error. The overall response rate for the CFCS, conducted from February to May 2009 was 56.3%. The provincial response rates ranged from 54.7% to 61.5%.

The basis for measuring the potential size of sampling errors is the standard error of the estimates derived from survey results. Because of the large variety of estimates that can be produced from a survey, the standard error of an estimate is usually expressed relative to the estimate to which it pertains. This resulting measure, known as the coefficient of variation (CV) of an estimate, is obtained by dividing the standard error of the estimate by the estimate itself and is expressed as a percentage of the estimate.

Please refer to the User Guide for detailed information.

Documentation

Date modified: