Data quality, concepts and methodology: Data source and methodology
Archived Content
Information identified as archived is provided for reference, research or recordkeeping purposes. It is not subject to the Government of Canada Web Standards and has not been altered or updated since it was archived. Please "contact us" to request a format other than those available.
The purpose of the Monthly Survey of Building Permits issued by Canadian municipalities is to collect data on construction intentions. The results of this survey are used by the Canada Mortgage and Housing Corporation (CMHC) as a reference base for conducting a monthly survey of housing starts and completions in accordance with its mandate. The statistics on building permits are also essential for the computation of capital expenditures. Furthermore, since the issuance of a building permit is one of the first steps in the construction process, these statistics are widely used as a leading indicator of building activity.
General methodology: The Building Permits Survey covers all Canadian municipalities that issue permits. The number of Canadian municipalities currently surveyed approximately 2,400, representing all the provinces and territories. They account for 95% of the Canadian population. Participation in the survey is mandatory; the survey does not use a predetermined sample of municipalities. The communities representing the other 5% of the population are very small, and their level of building activity have little impact on the total. In practice, all urban agglomerations are represented in the survey, as well as a fair percentage of rural municipalities. With certain exceptions, the minimum coverage corresponds to the municipalities already included in the CMHC Housing Starts and Completions Survey. Non-responding municipalities that issue permits are urged on a regular basis to respond to the Building Permit Survey. Therefore, the number of municipalities covered is increasing continually.
The survey is usually conducted by mail, although certain municipalities choose to respond by telephone. The municipal officer responsible for issuing permits is asked to fill out a form each month describing all major construction projects.
The municipalities forward a copy of their completed report to Statistics Canada's Head Office and another copy to the local office of the CMHC. To reduce their overhead, an increasing number of respondents are producing a computerized report. Only those municipalities that are late in reporting and that are included in the above-mentioned CMHC. survey are subject to follow-up by telephone.
The reports received at Statistics Canada's Head Office are verified, coded and processed.
Strict quality control procedures are applied to ensure that collection, coding and data processing are as accurate as possible. Checks are also performed on totals and the magnitude of data. Reports that fail to meet the quality standards are subject to verification and are corrected as required.
Imputations are required for each characteristic for which no report has been received. These are calculated automatically, subject to certain constraints, by applying to previously used values, the month-to-month and year-to-year changes in similar values of responding municipalities and the historical pattern of the missing municipalities. No estimation is done for lack of coverage, concealment or the underevaluation of permits issued. For this reason, the sampling error cannot be computed.
The monthly statistics are not corrected for cancelled or expired permits. According to the municipal officers, the proportion of cancelled and unused permits is below 5%.
Reference period: The reference period for data collection purposes is the calendar month. Reports from municipalities which are part of a census metropolitan area or a census agglomeration must be received within 20 days following the month of reference. The other municipalities have 30 days to produce their reports. Results are released between 35 and 40 days after the end of the reference month. Annual data for the preceding calendar year are released with the data for the January survey month.
Revisions: Two types of revisions can affect the results of the Building Permits Survey:
Revisions due to the correction of coding errors
These types of revisions are done on a monthly basis only to the data pertaining to the month preceding the reference period.
Revisions due to the addition of late reports
Late reports for the month preceding the reference period are incorporated into the survey results on a continuing basis. However, reports received after the two-month deadline following the reference month are introduced only at the end of the year. As a result, the data for the last twelve months are subject to revision.
Seasonal adjustment: Components of the building permits for which seasonal variation is present are seasonally adjusted using the X-12 ARIMA method. Seasonally adjusted data for the total number of housing units and the aggregate value of building permits are obtained indirectly, i.e., by adding up their seasonally adjusted components. Specifically, the total number of dwelling units is obtained by summing the seasonally adjusted data for single-family and multi-family units. The total value of building permits is obtained by summing the following components: residential, industrial, commercial and institutional. In cases where the component series contains no apparent seasonality, unadjusted values are used in the place of seasonally adjusted values in these aggregations.
At the end of the year, the seasonally adjusted time series are revised to take into account the most recent seasonal fluctuations at the same time as a revision to the previous year of the unadjusted data. In general, revisions for the seasonally adjusted estimates extending back three years are made with the release of January building permits data.
For more information on seasonal adjustment, see Seasonally adjusted data – Frequently asked questions.
As a complement to the seasonally adjusted series, trend-cycle estimates are produced to indicate the long-term underlying movement of a series and may also be used as early indicators of the direction of the short-term trend (within the current year). Both the seasonally adjusted and trend-cycle estimates are subject to revision as new data points are added to the series. These revisions could be large and even lead to a reversal of movement, especially at the end of the trend series. The higher variability associated with the trend-cycle estimates is indicated with a dotted line for the most recent four months on the graphs.
Starting with the release of January 2016 data, the Monthly survey of building permits trend-cycle is estimated using a standard method employed by several monthly economic indicators at Statistics Canada. For more information on this method, see the StatCan Blog and Trend-cycle estimates – Frequently asked questions.
- Date modified: