Survey of Financial Security (SFS)

Detailed information for 2019

Status:

Active

Frequency:

Occasional

Record number:

2620

The purpose of the survey is to collect information from a sample of Canadian households on their assets, debts, employment, income and education. The SFS provides a comprehensive picture of the financial health of Canadians. Information is collected on the value of all major financial and non-financial assets and on the money owing on mortgages, vehicles, credit cards, student loans and other debts.

Data release - December 22, 2020

Description

The SFS provides a comprehensive picture of the net worth of Canadians. Information is collected on the value of all major financial and non-financial assets and on the money owing on mortgages, vehicles, credit cards, student loans and other debts. A family's net worth can be thought of as the amount of money they would be left with if they sold all of their assets and paid off all of their debts.

The survey data are used by government departments to help formulate policy, the private sector and by individuals and families to compare their wealth with those of similar types of families.

Collection period: Starting in 2012, the collection period lasts 3 months, from beginning of September to beginning of December.

Subjects

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

Data sources and methodology

Target population

The target population for the SFS is families across the ten provinces of Canada.
Excluded from the survey are:
- the territories,
- those living on reserves and other Indigenous settlements,
- official representatives of foreign countries living in Canada and their families,
- members of religious and other communal colonies,
- members of the Canadian Forces living in military bases,
- people living in residences for senior citizens, and
- people living full time in institutions, for example, inmates of penal institutions and chronic care patients living in hospitals and nursing homes.
These exclusions represent approximately 2% of the population.

Instrument design

Qualitative testing was carried out by Statistics Canada's Questionnaire Design Resource Centre (QDRC) for selected modules of the survey questionnaire, while questions for the remaining modules came from other Statistics Canada surveys. Questions adhere as closely as possible to content established by the Harmonized Content Committee at Statistics Canada.

The questionnaire follows standard practices and wording used in a computer-assisted interviewing environment, such as the automatic control of flows that depend upon answers to earlier questions and the use of edits to check for logical inconsistencies and capture errors. The computer application for data collection was tested extensively.

Sampling

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

Each province is stratified into rural and urban areas and a different design is used in each. In rural areas, a multi-stage sample was selected using the Labour Force Survey area frame. In urban areas, a stratified sample was selected from the Dwelling Universe File (DUF). Information from the T1 Family File (T1FF) is used for stratification which improves the efficiency of the urban part of the sample.

All families residing in the selected dwellings were included in the sample.

Sampling unit:
In urban areas, where a stratified single-stage design is used, the sampling unit is the dwelling.

In rural areas, where the LFS area frame is used in a multi-stage design, geographic areas referred to as LFS clusters are the sampling unit at the first stage and dwellings selected within these clusters are the sampling unit at the second stage.

Stratification method:
The first level of stratification is by province and each province is further stratified into rural and urban areas. Two independent samples are drawn within each province, one from each of these strata.

In rural areas, a multi-stage sample was selected using the Labour Force Survey area frame. The LFS stratification into large geographic strata is used during first stage selection of clusters.

In urban areas, information from the T1 Family File (T1FF), such as age and income, is used to stratify the Dwelling Universe File (DUF), into groups of dwellings predicted to have similar net worth.

Sampling and sub-sampling:
The SFS sample consists of 20,010 dwellings, 13,435 dwellings selected from the urban strata and 6,575 dwellings within 704 clusters from the rural strata.

The allocation takes into account the different sample designs in urban and rural areas. In addition, to improve the quality of the estimates, higher net worth strata are oversampled compared to lower net worth strata in the urban areas.

Data sources

Data collection for this reference period: 2019-09-09 to 2019-12-14

Responding to this survey is voluntary.

Data are collected directly from survey respondents, extracted from administrative files and derived from other Statistics Canada surveys and/or other sources.

Collection method:
CAPI (computer-assisted personal interviewing)

Capture method:
Blaise

Initial contact:
Introductory letter sent to the respondents

Follow up:
Interviewer visits/calls respondents

Proxy reporting:
Yes

Languages offered:
English and French

Average time of interview:
45 minutes

Administrative data source:
Income tax Records file (T1 Family File (T1FF))
Administrative Personal Income Masterfile (APIM)

Other source: Pension Plans in Canada (PPIC)

To reduce response burden, information from personal tax data and the Pension Plans in Canada survey are used.

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

Error detection

The computerized questionnaire contains many features designed to maximize the quality of the data collected.

Many edits are built into the questionnaire to compare the reported data with unusual values and detect logical inconsistencies.
When an edit fails, the interviewer is prompted to correct the information (with the respondent's help, if necessary).

Once the data are transmitted to Head Office, a comprehensive series of processing steps are undertaken for the purpose of detailed verification of each questionnaire.
Invalid responses are corrected or flagged for imputation.

Edits were applied at a micro level.

Deterministic edits and consistency edits were also performed at the micro level. Data was checked for outliers and extreme values, and were corrected at a micro level when required.

Imputation

For income data, all respondents are matched to the tax data file unless they refuse to have their information linked. Income tax information comes from the Administrative Personal Income Masterfile (APIM), which is created from tax slips such as the T1 and T4. Partial imputation is performed for APIM records that have some information from tax slips but that did not file their taxes and hence do not have a T1. Complete imputation of income variables is required when the respondent could not be linked to the administrative data. Imputation is performed using donor imputation with the nearest neighbour method. The imputation is performed using Statistics Canada's Census Edit and Imputation System (CANCEIS).

Imputation is also performed for other key variables when information is missing. The imputation of the non-income variables was also done primarily using the nearest neighbour imputation method. In some cases deductive imputation was also used. The imputation is performed in several steps. Variables in the same sections of the questionnaire or in related sections of the questionnaire are often imputed together. An appropriate set of matching variables and imputation classes are determined for each group of variables processed together. Statistic Canada's CANCEIS, as well as custom SAS programs were used to perform the imputation of the non-income variables.

Imputation is used to handle item nonresponse for many, but not all, variables. Variables not subject to imputation retain missing values in the form of "Don't Know", "Refusal" and "Not Stated" reserved codes. Imputation rates for questions which applied to the majority of respondents tended to be low, but items that applied only to a small percentage of respondents sometimes had fairly high imputation rates indicating that the respondents were having much more difficulty answering or were less willing to provide answers to these questions.

More information about the imputation rate for questions on the SFS can be obtained by requesting the SFS Quality report. To obtain this documentation, contact Client Services (613-951-7355, STATCAN.income-revenu.STATCAN@canada.ca).

Estimation

An integrated weight, meaning that all household members are given the same weight, is produced for SFS. The weighting process begins by calculating design weights separately for the urban and rural parts of the sample. The weights are then adjusted for non-response separately within each sample. After non-response adjustment, the weights are combined into a single file. Next, the weights undergo an initial calibration to known population totals. The totals comprise the following: demographic projections produced by Statistics Canada's Demography division based on the 2016 Census, the number of wage and salary earners by several wage and total income classes by province based on APIM 2018 Prelim administrative file, and the number of people with registered pension plans by province based on totals from PPIC 2019. Influential observations are then identified, and weights are reduced for a small number of extreme observations. To complete the process, calibration is then repeated a second time with the condition that the influential observations do not have their weights adjusted any further. The resulting weighted units represent the entire SFS target population.

Variance is estimated using the Rao-Wu-Yue method with 1,000 bootstrap replicate weights. To determine the bootstrap weights, 1,000 initial replicates are created, and each replicate undergoes the same adjustment process as the survey weights.

Quality evaluation

Data are compared to the results of other data sources: Census, administrative data and other Statistics Canada surveys.

Direct comparisons with outside sources, such as the Financial and Wealth Accounts of the System of National Accounts, are difficult to make due to definitional, coverage and treatment differences. However, based on rough comparisons the following general conclusions can be drawn:

(a) SFS appears to underestimate some net worth components, particularly financial assets and consumer debt.

(b) The quality of estimates of real assets (e.g., owner-occupied homes, vehicles) is much better than that of financial assets.

The SFS is designed to describe the financial situation of the majority of Canadian families, using a methodology that has remained stable over time, allowing for the description of levels and trends. It is designed to create reliable estimates of the top 5% of the net-worth distribution. The sample size of the SFS is insufficient to have representative sample of economic families with very high wealth.

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.

Suppression rules are applied to the various tables of SFS estimates to ensure respondent confidentiality and data quality. For example, estimates are rounded (to the nearest hundred for medians) and estimates based on less than 30 estimates are suppressed.

Revisions and seasonal adjustment

This methodology does not apply to this survey.

Data accuracy

The quality of estimates produced with SFS data is measured using 95% confidence intervals. When comparing estimates, it is important to use confidence intervals to determine if differences between values are statistically significant. Confidence intervals describe sampling variability and give an indication of the precision of a given estimate.

The width of the confidence interval depends on the domain of interest and on the prevalence and variability of the characteristic.

In SFS 2019, the 95% confidence interval for the average net worth of Canadian families had a width of $47,000.

More information about the quality of estimates produced using the SFS can be obtained by requesting the SFS Quality report. To obtain this documentation, contact Client Services (613-951-7355, STATCAN.income-revenu.STATCAN@canada.ca).

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: