Survey of Information Technology Occupations

Detailed information for 2000

This survey is conducted to collect statistical information on employment trends in information technology (IT) occupations.

Data release - September 29, 2000

• Questionnaire(s) and reporting guide(s)
• Description
• Data sources and methodology
• Data accuracy

Description

This is a pilot survey.

The main objective of the pilot survey is to test the possibility of producing statistical information on required skills and employment-related issues of employers and employees in twenty-one Information Technology (IT) related occupations for a national survey and to test the new classification of IT occupations.

Statistics Canada conducts this survey on behalf of the Human Resources Investment Branch of Human Resources Development Canada. This pilot survey is part of a project addressing concerns that employers have in finding skilled labour and sufficient numbers of employees in these occupations to meet the demand.

Subjects

• Information and communications technology
• Information and communications technology sector
• Labour
• Occupations

Data sources and methodology

Target population

For the pilot survey, the target population is limited to locations on Statistics Canada's Business Register (BR), with at least six employees, coded to three specific industry categories (classified to the North American Industrial Classification System (NAICS)) and found in specific geographical regions. The locations must employ workers in at least one of the targeted IT occupations (classified to National Occupational Classification).

The sampling frame of employers is approximated by a list of 5,760 locations on the BR as of December 1999. The target population of employees is the workers in the 5,760 locations who are employed in the target IT occupations.

• Additional documentation

Instrument design

The content questionnaire for the employer and employee surveys is developed by Statistics Canada in collaboration with Industry Canada. Statistics Canada formats the employee questionnaire and ensures both questionnaires comply with Statistics Canada policy.

Sampling

This is a sample survey.

For the pilot survey of employers, the target population is all business locations, with six or more employees, in the targeted industries and regions. Twenty-one strata are used to ensure adequate representation of locations by region, industry and size. Locations in each region-industry combination are divided into three size categories to improve the representation of the sample. The region-industry combinations are: the Atlantic provinces NAICS 5415, Quebec NAICS 5413 and NAICS 5415, Ontario NAICS 5241 and 5415, the Prairie provinces (including the Northwest Territories and Nunavut) NAICS 5415, and British Columbia (and Yukon) NAICS 5415. The size categories are 6 to 25 employees, 26 to 50 employees, 51 or more employees.

A sample of 3,500 locations is drawn from the sampling frame, with a further 315 drawn during the collection period in anticipation of low response rates in certain strata.

For the pilot survey of employees, the sampling frame is derived from the locations who responded to the employer survey. Employers are asked, at the end of the interview, whether they would be willing to allow Statistics Canada to survey their employees in the two randomly selected IT occupations on which they provided detailed information. Employees from the consenting employers become part of the sampling frame for the employee survey.

No stratification techniques are used for the pilot survey of employees. Sample selection depends on the number of employees the consenting employer has in the selected occupations. If an employer has ten or fewer employees in the selected occupations, all employees are part of the sample. If, however, an employer has more than ten employees, then ten employees are randomly selected from that employer to participate in the employee survey.

The sample for the pilot survey of employees contains 4,251 employees from 859 locations.

Data sources

Responding to this survey is voluntary.

Data are collected directly from survey respondents.

The pilot survey of employers uses the Computer Assisted Telephone Interview (CATI) method. A pre-contact of large locations (those with 100 or more employees) is conducted to identify the most appropriate person(s) to respond to the survey. Each location is sent an introductory letter describing the purpose of the survey, a list of the questions that would be asked and definitions of the occupations that are being targeted. In the course of an interview, CATI interviewers ask for the number of employees in each of the twenty-one occupations of interest. Then, the CATI system randomly selects two occupation categories for which there are one or more employees.

For the pilot employee survey, a mail-back questionnaire is sent to employees at their place of work, if employers had provided employee names. Employers that have not provided employee names are sent questionnaires along with instructions to distribute them randomly to the employees in the occupation(s) of interest at that location. Follow-up is done by phone and by e-mail.

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

Error detection

For the employer survey, both qualitative and quantitative variables are subjected to the following quality control measures:

- Edits for qualitative variables ensure answers are within a range of allowable answers, as every answer is compared to the set of possible coded answers for that question.

- For questions concerning the numbers of employees (e.g. vacancies), online edits in the CATI application require responses of a magnitude consistent with the number of employees in that occupation. For example, if vacancies are more than 300% of the number of employees in that occupation, the answer for vacancies would be flagged as an edit failure.

- Online consistency edits for quantitative variables ensure all answers are within the minima and maxima calculated from other answers to the questionnaire.

- Extreme or unexpected values are identified using frequency tables. Unexpected values are investigated individually.

For the employee survey, the data are subjected to the following quality control measures during the data processing stage:

- Validity edits ensured answers to questions collecting qualitative information is within a range of possible answers according to the answer key;

- Consistency edits verify skip patterns and check for consistency of responses across several questions.

In both surveys, edit failures are viewed manually, and no formal outlier detection method is used.

Imputation

For the employer pilot survey, imputation of the numbers of employees and contract workers is done at the location level using ratio imputation.

Imputation of data from the sections of the questionnaire profiling specific occupations (i.e., hiring and recruitment for the occupation, employee retention, and training and development) are done after the data file is converted from one line per location to one line per location-occupation. Where possible, imputation of these data is done by occupation and stratum. In strata with no observations of particular occupations, data are imputed by occupation and size, or if not possible, by occupation only. Values for the number of permanent and temporary full-time and part-time employees are imputed using ratio imputation whereas mean imputation is used to impute values for all other quantitative variables.

The hot deck donor imputation procedure is used in the pilot survey of employees.

Estimation

In the pilot surveys of both employers and employees, estimates are generated using the Statistics Canada Generalized Estimation System (GES). Estimates are produced by domain (e.g. occupation and province category). Coefficients of variation are provided for quantitative point estimates. Standard errors are provided for estimates of proportions and ratios.

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.

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 Survey of Information Technology Occupations, all estimates created with three or fewer records have been suppressed for confidentiality purposes.

Data accuracy

Since all the estimates produced from the pilot survey are based on sample results, they are subject to sampling error. Sampling error for quantitative variables is expressed as a coefficient of variation (CV), and as the standard error (SE) for qualitative variables. The following tables provide a guideline of the quality of an estimate of a total.

• Additional documentation