Annual Survey of Engineering Services

Detailed information for 1999





Record number:


The survey objective is the collection and publication of data necessary for the statistical analysis of the engineering services industry.

Data release - December 13, 2001


The survey objective is the collection and publication of data necessary for the statistical analysis of the engineering services industry.

The information from the survey can be used by businesses for market analysis, by trade associations to study performance and other characteristics of their industry, by government to develop national and regional economic policies, and by other users involved in research or policy making.

Statistical activity

This survey is part of the Service Industries Program. The survey data gathered are used to compile aggregate statistics for over thirty service industry groupings. Financial data, including revenue, expense and profit statistics are available for all of the surveys in the program. In addition, many compile and disseminate industry-specific information.

Reference period: Calendar year

Collection period: January to August


  • Business, consumer and property services
  • Business performance and ownership
  • Financial statements and performance
  • Professional, scientific and technical services

Data sources and methodology

Target population

The target population consists of all statistical establishments (sometimes referred to as firms or units) classified as Engineering Services (NAICS 541330) according to the North American Industry Classification System (NAICS) during the reference year.


This is a sample survey.

The survey design covered only the portion of the frame subject to direct data collection. Prior to the selection of a random sample, units are grouped in homogeneous groups defined using industrial (NAICS) and geographic (province/territory) attributes. Similar quality requirements are targeted for each group which is then divided into four sub-group called strata: must-take, take-all, large take-some and small take-some.

The take-all stratum includes the largest firms in terms of industrial performance, which are selected in the sample with certainty making such units self-representing. The must-take stratum is also comprised of self-representing units that have a complex structure (multi-establishments, multi-legal, multi-NAICS or multi-province enterprises). Units in the two take-some strata are subjected to a random sample where each sampled firm represents a number of other, similar firms in the industry/province combination according to the inverse of their probability of selection.

Finally, the size of the sample was increased to compensate for such situations as non-response and firms which cannot be contacted because they have moved or gone out of business. The resulting sample size for this survey after removing firms that should not have been included in the frame (out of scope, duplicate records or out of business) was 604 companies.

Data sources

Responding to this survey is mandatory.

Data are collected directly from survey respondents and extracted from administrative files.

Data is collected through a mail-out/mail-back process, while attempting to provide respondents with the option of telephone or other electronic filing methods as required. Even though the sampling unit was the statistical establishment, the statistical company was chosen as the collection entity in order to reduce respondent burden and simplify collection procedures. Therefore, companies with production at more than one locale were mailed only one questionnaire, and were instructed to report for all their operations in the surveyed industry. Summary data were collected for each province or territory in which the company operated.

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


Several checks are performed on the data to verify internal consistency and identify extreme values. For non-response, imputation is performed using a "nearest neighbour" procedure (donor imputation) using available auxiliary information to substitute the data from a company with similar characteristics. In addition to the donor imputation approach, imputation can also be done using historical responses.


Prior to estimation, data for companies with production in more than one province or territory were allocated to the provincial level. The survey data collected from the sample were then weighted using the inverse of the probability of selection of each sampled unit to produce estimates representative of the target population. Administrative data were used to estimate the portion that was excluded from survey activity (i.e. unincorporated firms and incorporated firms with revenue less than $50,000).

The combined survey results were analyzed before publication; in general this included a detailed review of the individual responses (especially for the largest companies), a review of general economic conditions as well as historic trends and comparisons with tax data information and other administrative data sources (e.g. industry and trade associations).

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.

Data accuracy

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

Non-sampling errors are not related to sampling and may occur for many reasons. For example, non-response is an important source of non-sampling error. Population coverage, differences in the interpretation of questions, incorrect information from respondents, mistakes in recording, coding and processing of data are other examples of non-sampling errors.

The response rate for this survey was 84%, after taking into account the fact that some firms were no longer in business, or had changed their primary business activity.

Sampling errors can occur because estimates are derived from a sample of the population rather than the entire population. These errors depend on factors such as sample size, sampling design and the method of estimation. An important property of probability sampling is that sampling errors can be computed from the sample itself by using a statistical measure called the coefficient of variation (CV). Over repeated surveys, the relative difference between a sample estimate and the estimate that would have been obtained from an enumeration of all the units would be less than twice the coefficient of variation, 95 times out of 100. Confidence intervals can be constructed around the estimate using the CV's. First, we calculate the standard error by multiplying the sample estimate by the CV. The sample estimate plus or minus twice the standard error is then referred to as 95% confidence interval.

For the 1999 Annual Survey of Engineering Services, CVs were calculated for each estimate. Generally, the more commonly reported variables obtained very good CVs (10% or less) while the less commonly reported variables were associated with higher but still acceptable CVs (under 25%). These CVs are available upon request.

Date modified: