Section 2: Survey 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.
Target population
The program’s target population consists of all businesses in Canada that have at least one paid employee receiving a T4 slip and have thus issued at least one payroll deduction remittance during the reference month. Excluded are businesses that are primarily involved in agriculture, fishing and trapping, private household services, religious organizations, international and other extraterritorial public administration and the military personnel of defense services. The BPS population is taken from the list of businesses appearing on the Business Register, which is maintained by the Business Register Division of Statistics Canada.
The Business Register is updated monthly using data from various surveys, business profiling, and administrative data. It is built from a CRA list of businesses participating in one or more of the following programs: payroll deduction, goods and services tax, importer and exporter tax, and corporation tax. The payroll deduction source includes all employers with remittances for employee income taxes, CPP/QPP, and Employment Insurance contributions.
Reference period
The reference period for the SEPH is the last seven days of the month. When a reported pay period is longer than one week, the data are proportionally adjusted to reflect the number of worked days during the reference period. In certain cases, adjustments are also made to exclude employees on strike, lockout, or layoff during the reference week.
Data sources
Data can be collected directly from survey respondents, extracted from administrative files or derived from other Statistics Canada surveys and other sources. Responding to the survey component of the SEPH is mandatory, as is the case with most business surveys.
The statistics compiled by the SEPH are based on a census of administrative records for all in-scope establishments with employees that can be found on the Business Register. The total payroll employment estimates and the monthly payrolls are derived from the administrative source. Administrative information for total gross monthly payrolls and the total number of employees for the last pay period in the month are obtained from payroll deduction accounts maintained by CRA.
The Public Sector Employment Survey provides information for general government services at the provincial and federal levels (see record number 1713).
The BPS, conducted monthly, is used to estimate the SEPH variables not available from the administrative source. Estimates from the administrative source and the BPS are combined to produce the full range of the SEPH variables.
Administrative records
Since 1993, CRA has used PD7 payroll deduction forms remitted by employers to gather data on two variables: (1) total gross payrolls and (2) total number of employees for the reporting period.
The payroll deductions program covers all employers who make income tax remittances, CPP/QPP, and Employment Insurance contributions for their employees. Depending on the size of the remittance made to CRA, employers are required to remit on a monthly, quarterly, or accelerated basis. 1 The remittance period for which the payroll is reported on the PD7 form varies accordingly. For quarterly and accelerated remittances, the payroll is converted to correspond to a monthly period. These payroll deduction data are then linked to the Statistics Canada Business Register.
The Business Register is a structured list of businesses that produce goods and services in Canada. Because of the census nature of the Business Register, it is always made up of the same units, except when new businesses are created and when existing businesses cease their activities during the month.
An agreement with CRA gives Statistics Canada access to total gross payrolls and total number of employees. To produce estimates, the SEPH aggregates the PD7 forms (from establishments covered by the survey) to determine these two variables in the last pay period of the month.
The use of administrative data reduces survey cost and response burden. Furthermore, the overall estimates of employment and payroll are enhanced because of the timeliness of administrative records, better coverage of the surveyed population, and because the survey is a census of all employing businesses.
The Business Payrolls Survey
The BPS is the questionnaire component of the SEPH program. It is used to collect monthly data on the weekly components of gross monthly payrolls, total hours and the allocation of certain variables (employment, payroll and hours) among the categories of employees (paid by the hour, salaried and others) to derive variables not available from administrative records. Since 2011, the BPS has also collected summary information on job vacancies.
The survey uses a combination of methods for data collection to provide maximum flexibility for the respondent. For mail units, questionnaires are mailed to the payroll office of employers each month. Computer-assisted telephone interviews are used when respondents express a preference for being surveyed by telephone. Respondents can also report their data electronically. Reporting units, which are non-respondents to the initial mailing, are followed up by telephone by the staff of Statistics Canada’s regional offices.
Sample design
The BPS uses a stratified simple random sample of 15,000 establishments, out of a population of 1,000,000 establishments listed in the Business Register. Generally, sampled units are removed from the BPS sample after 12 months, and are not eligible for re-selection for one year. However, some 800 establishments are permanent in the sample, either because they represent a significant share of employment in their sector or because they are sufficiently different from other establishments in their sector that they can only be represented by themselves.
The sample is stratified based on province, NAICS 2012 sub-sector and employment size. Sample allocation aims to maximize the accuracy of the estimate of weekly payroll and the total number of hours at the NAICS 2012 sub-sector level for all of Canada, the provinces and the territories. The sample size and stratification are determined to meet specific coefficients of variation (CVs) for estimated weekly payroll and the total number of hours at the national and provincial/territorial level and selected industry groups. CVs at more detailed geographic and industrial levels are subsequently derived as a function of the available sample.
Each month, the BPS sampling frame is updated to reflect new establishments created on the Business Register and to eliminate those that no longer exist.
Although the sample is too small to produce detailed estimates directly, it is possible to provide the full range of the SEPH published variables by combining data from the BPS and data from the administrative records.
Estimation methods
Estimating population characteristics from a survey is based on the premise that each sampled unit represents, in addition to itself, a certain number of other units in the population. A basic survey weight is attached to each record to indicate the number of units in the population that are represented by that unit in the sample.
Two adjustments are applied to the basic BPS weights to improve the reliability of the estimates. These basic BPS weights are first inflated to compensate for non-response. The non-response adjusted weights are then calibrated to ensure that estimates of total monthly payroll employment and monthly payrolls match estimates from the Canada Revenue Agency PD7 administrative source.
The calibration is done using a generalized regression estimator. The model groups are mostly defined at the national and sub-sector levels (i.e., three-digit NAICS code or, in a few instances, four-digit); in a few cases, the enterprise size (measured by number of employees) and the provincial dimensions are used. Regression coefficients, calculated at the model group level, are applied to the estimates of total employment and payrolls from the administrative sources to estimate the additional variables.
Non-farm payroll employment data are for all hourly and salaried employees, as well as for the ’other employees’ category, which includes piece-rate and commission-only employees. Average weekly hours’ data are for hourly and salaried employees only. They exclude businesses that could not be classified with a NAICS code by the time monthly processing was completed.
All earnings data include overtime pay, and exclude businesses that could not be classified to a NAICS code. Earnings data are based on gross taxable payroll before source deductions.
Average weekly earnings are derived by dividing total weekly earnings by the total number of employees.
- Date modified: