Technical guide for use for Financial Consumer Agency of Canada's datasets

Please follow these guidelines to ensure your results are robust and reliable.

a) When possible, conduct analysis using weighted rather than unweighted data. FCAC generally provides data that has been weighted to closely approximate a nationally representative sample. When conducting analysis, researchers should use the population weights provided unless the statistical approach warrants otherwise or there is a justification for using unweighted data.

b) Determine the quality of any estimate(s) before releasing results. If fewer than 30 respondents contribute to the calculation of an indicator, FCAC recommends not releasing these results. If reported, it should be flagged as unreliable and include the following warning: "Please be warned that these estimates do not meet FCAC’s quality standards. Conclusions based on these data will be unreliable and may be inaccurate."

c) Ensure respondent confidentiality. Tabulated data must not show demographic or respondent characteristic categories with a column or row total of fewer than 10 respondents. Particular care must be taken when respondent verbatim statements are included in data files.

For further information on best practices for the management and analysis of public opinion research data, please see Standards for the Conduct of Government of Canada Public Opinion Research.

If you have any questions about how to analyze the data or are unsure of how to interpret certain variables, you are encouraged to contact FCAC directly at: fcac.research-recherche.acfc@fcac-acfc.gc.ca.