National Construction Industry Wage Rate Survey
Detailed information for May 2003 to June 2004 (Ontario)
This survey collects data on wages paid for specific occupations in the construction industry in all provinces and territories except Québec and Yukon on behalf of the Labour Branch of Human Resources and Social Development Canada.
Data release - December 6, 2004
- Questionnaire(s) and reporting guide(s)
- Data sources and methodology
- Data accuracy
This survey collects data on wages paid for specific occupations in the construction industry in all provinces and territories except Québec and Yukon on behalf of the Labour Branch of Human Resources and Social Development Canada (HRSDC). Estimates are produced for three wage rates -- starting, maximum and most frequently paid wages -- by occupation for both unionized and non-unionized workers, by province / territory and by economic region. The estimates are used by HRSDC to establish wage schedules for workers on federal construction projects. Quebec and Yukon are excluded because equivalent wage schedules are established by the provincial or territorial government.
Reference period: The 12-month period prior to the collection date
- Wages, salaries and other earnings
Data sources and methodology
The commercial or institutional construction industry encompasses all establishments coded to construction industry in the 1980 Standard Industrial Classification - (SIC). For the provinces, the target population consists of all establishments in the commercial or institutional construction industry in business during the reference period with 6 or more employees. In the Northwest Territories and Nunavut, all establishments in the commercial or institutional construction industry comprise the target population, regardless of the number of employees.
The questionnaire was based on previous general wage rate surveys undertaken by Small Business and Special Surveys Division of Statistics Canada. The questionnaire was slightly modified for each province and territory based on consultations with provincial and territorial unions and employer associations in the construction industry.
This is a sample survey with a cross-sectional design.
Targeting for occupations was done using census tabulations that show the number of people employed in a specific province by 4-digit level NAICS and by 4-digit level National Occupation Classification (NOC) combinations. In each 4-digit level NAICS, a maximum of 12 occupations, whether possible, in terms of percent coverage was selected. In cases where fewer than 12 occupations had employment in a 4-digit NAICS according to 1996 Census data, tabulations were collapsed to the 3-digit NAICS level to fill the remaining list of 12 occupations. If the list of occupations was still fewer than 12 due to there being fewer than 12 occupations with employment at the 3-digit NAICS level, then we would go with a list of fewer than 12 occupations. Each sampled establishment within a certain NAICS and province had the same 12 occupations but in a different order (the order of the occupations was randomized). These establishments were asked, from this list of occupations, to identify up to six of them for which they have had employees in the last 12 months. As a result, in order to keep the response burden low, questions were only asked for a maximum of these six occupations.
Data collection for this reference period: May 2004 to June 2004
Responding to this survey is voluntary.
Data are collected directly from survey respondents.
The survey is a Computer Assisted Telephone Interview (CATI) survey. Each establishment contacted is asked to provide a representative who could provide wage rate information. Some establishments refer the interviewer to their head office.
Some respondents report wage rates that potentially have a large impact on the estimates. Follow up activities are conducted with those respondents that meet the following criteria: if the number of employees reported by the establishment is at least 100 more than the number of employees according to the BR; when the total number of employees reported in each of the occupations is considerably more than the establishment reported they had in total; if there is at least 100 employees reported by the establishment and there is no response for the number of employees in a particular occupation; if the weight assigned to an establishment for an estimate is at least 33% of the total weights for the estimate; and, if an establishment had at least a $0.25 impact on the wage estimate for a given occupation.
If an establishment is selected for verification, then the data is verified for all the occupations that the establishment reported. The interviewers conducting the verification clarify whether or not the establishment is in scope for the survey (i.e. commercial and institutional construction), that the occupations are classified properly, that the number of employees reported are correct and that the wages reported are correct (i.e. wages exclude vacation pay and benefits).
View the Questionnaire(s) and reporting guide(s) .
In order to identify, minimize and correct errors, the data are subjected to the following quality control measures:
. Various validity and consistency edits are built into the CATI system to allow corrections to be made during the collection phase. The consistency edits ensure that the relationships between wage variables, as well as the "number of employee" variables, are reasonable. These various edits are applied again after collection, in order to ensure that the data is consistent.
. The data is then converted from an "establishment level" format to an "occupation level" format, as the responses from an establishment on a specific occupation became a unique record. Each occupation record is examined to ensure that at least one wage question had a response. Records that do not have at least one response to a wage question are removed from the file and are not processed further.
. Wage rates are provided by respondents according to the time period of their choice: hourly, daily, weekly, biweekly, twice per month, monthly or annually. They are reviewed for anomalies, which primarily are cases where the hourly wage is below the provincial minimum wage or over $75.00.
. Outlier detection is performed on the wage questions in order to detect values that are improbable or influential using standard deviation. If a declared wage rate is further than three standard deviation from its mean, then it is flagged as an outlier. All unusual values and outliers are resolved using computer programs or manually on a case-by-case basis.
For the wage variables, imputation is done whenever an expected wage value is missing or flagged for imputation. Relationships (trends) between all non-missing wage variables that are not flagged for imputation are calculated for each occupation. Values are imputed based on the wage variable trend. Edits are re-run on the imputed records and adjustments made to the imputed values, if necessary.
For the number of employees' variables, if the total number of employees in the establishment is missing, the number of employees variable is imputed from the survey frame. The number of full time employees for a specific occupation is imputed based on the total for the establishment using a trend.
Before estimation and weighting, sample counts are adjusted for non-response. The adjustment of counts is based on the assumptions that the non-response is random and that a non-respondent is not characteristically different from a respondent.
For all provinces, estimates are produced using the Generalized Estimation System (GES).
Records are assigned weights based on the number of employees in the occupations; establishments with more employees for an occupation have a larger contribution to the estimates for that occupation. A weighted-average, hourly wage rate is estimated for every occupation pertaining to full-time employees and for the three different wage concepts (starting wage, most frequently paid wage, maximum wage). Estimates are also produced by sub-provincial area and union status. Domain estimation is applied. For this survey, the domain regroups all records for a given occupation for the purposes of calculating statistics, regardless of industry and, in some cases, region.
The province of Ontario survey is a census.
The main quality evaluation activity is to compare the wave 2 wage estimates to the previous estimates from wave 1. Wage estimates are compared with published data from both Statistics Canada and other sources. From Statistics Canada, comparisons are made with the Labour Force Survey (survey ID 3701), and the Survey of Employment Payroll and Hours (survey ID 2612). If possible, comparisons are also made with provincial wage rate schedules published by provincial construction industry unions.
Statistics Canada is prohibited by law from releasing any data which would divulge information obtained under the Statistics Act that relates to any identifiable person, business or organization without the prior knowledge or the consent in writing of that person, business or organization. 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.
Confidentiality analysis includes the detection of possible "direct disclosure", which occurs when the value in a tabulation cell is composed of a few respondents or when the cell is dominated by a few companies.
In the Construction Industry Wage Rate Survey, all estimates created with four or fewer occupational records have not been released for confidentiality reasons.
Revisions and seasonal adjustment
This methodology does not apply to this survey.
Since the National Construction Industry Wage Rate Survey estimates are based on sample results, they are subject to sampling error. This error can be expressed as a coefficient of variation (CV). The CV is the standard error expressed as a percentage of the estimate. In the output tables, the CVs are converted to a code. Code A indicates a coefficient of variation in the range 0 to .05 (very good quality), B is .051 to .15 (good quality), C is .151 to .33 (good to poor quality -- use with caution) and D is .331 or higher (very poor quality).
Survey estimates may also contain non-sampling error, for example population coverage errors, differences in the interpretation of questions, incorrect information from respondents, and mistakes in recording, coding and processing data. Non-response is an important source of non sampling error. While the impact of non-sampling errors is difficult to evaluate, measures such as response rates and imputation rates can be used as indicators of the potential level of non-sampling error. The 2005 survey covering British-Columbia, Northwest Territories and Nunavut had a response rate of 69.9%, which is considered very good for a voluntary survey.
The imputation rates for the 2005 survey were as follows:
- Total number of employees working on commercial or institutional construction -- 0.00%
- Number of employees working on commercial or institutional construction by occupation -- 1.39%
- Number of unionized employees -- 0.42%
- Starting wage -- 1.10%
- Most frequently paid wage -- 1.00%
- Maximum wage -- 1.03%
- National Construction Industry Wage Rate Survey in the Province of Ontario - Methodology Report