Longitudinal Employment Analysis Program (LEAP)

Detailed information for 2002

The Longitudinal Employment Analysis Program (LEAP) is a database that contains annual employment information for each employer business in Canada, starting with the 1991 reference year.

Data release - September 9, 2005

• Description
• Data sources and methodology
• Data accuracy

Description

The Longitudinal Employment Analysis Program (LEAP) file contains employment information for each employer business in Canada, for each year starting with the 1991 reference period. The LEAP has the advantage of covering the entire economy. The approximately 1 million companies in the commercial economy that paid more than $1 in payroll to employees are included in this analysis. LEAP is a longitudinal file of companies (legal entities in the taxation system), not establishments. For each business, annual estimates of total payroll and employment are calculated. The latter is an average count of employees within the firm, and does not distinguish between full-time and part-time workers. This payroll and employment information is then organized longitudinally, that is, each observation on the database corresponds to a particular firm whose employment, payroll and industry characteristics are recorded at different points in time. The longitudinal nature of LEAP allows entry and exit times to be measured with precision. Entrants (or 'births') in any given year are firms that have current payroll data, but that did not have payroll data in the previous year. Similarly, exits (or 'deaths') in any given year are identified by the absence of current payroll data, where such data had existed in the previous year.

The LEAP file has traditionally been used to support research on employment dynamics; it is the primary source for studies on employment creation and destruction, by firm size, in Canada

Subjects

• Hours of work and work arrangements
• Industries
• Labour
• Wages, salaries and other earnings

Data sources and methodology

Target population

The target population of LEAP is every employer in Canada whether incorporated or not. This universe consists of every business that issued one or more annual statements of remuneration paid for tax purposes (a T4 slip). The self-employed that do not draw a salary are not included in this universe, and thus are not counted in LEAP. Businesses comprised solely of individuals or partnerships that do not draw a salary are also excluded. LEAP is a longitudinal file of enterprises, not establishments.

Instrument design

This methodology does not apply.

Sampling

LEAP is a longitudinal file of all the companies that paid more than $1 in payroll to employees.

Data sources

Data are extracted from administrative files and derived from other Statistics Canada surveys and/or other sources.

The estimated employment for each company on LEAP is based on the payroll as reported to Canada Revenue Agency for the company. The payroll is converted to employment (called ALUs or average labour units) using conversion factors derived from the Survey of Employment, Payroll and Hours (record no. 2612). The LEAP tracks businesses through time by linking yearly T4 employment data records with company information on Statistics Canada's central frame of enterprises, i.e. the Business Register (see record no. 1105). The country of control of a corporation is an assignment of a geographical locus of control, representing the country of residence of the persons having the greatest potential to strategically influence the activities of corporation. The country of control comes from two sources: the Business Register and the Inter Corporate Ownership files (I.C.O.).

Error detection

The creation of the LEAP database requires considerable effort in distinguishing 'real' births and deaths from 'false' ones. Real births and deaths reflect actual entry and exit events (the creation of new firms and the failure of existing ones); false births and deaths may simply reflect organizational restructuring within a firm, or a change in its reporting practices. These false births and deaths are identified, and then corrected on the file, using a method of 'labour tracking'. This approach essentially tracks workers as they move from company to company from one year to the next. If a new firm (or birth) contains a large majority of employees from a 'death' in the previous year, then the status of this death and birth is subject to verification. In cases where a birth and death share the same (or a similar) name, or the Business Number, this birth and death is reclassified as a continuing business.

Most enterprises on the central frame are derived from structures of Business Numbers belonging to distinct business units; most enterprises usually maintain the same identifier from year to year. However, an enterprise's identifier can change from year to year; such changes are often of a purely administrative nature, they can by wrongly interpreted as entries and exits in the employer population. BLMA has developed a methodology to minimize the occurrence of such false entries and exits. For each year, the cluster of workers associated with each newly identified enterprise is compared with the clusters of workers in enterprises existing in the previous year. Similarly, the clusters of workers in no longer identified enterprises are compared with the clusters of workers in all enterprises existing in the following year. These comparisons identify pairs of businesses that are potentially related from one year to the next but have different identifiers. If the pairs exhibit a match on the enterprise's name (full or near name match) or Business Number, they are reconciled into a single identifier that is maintained for the enterprise records for all years.

Imputation

This methodology does not apply.

Estimation

In Canada employing business are required to register with Canada Revenue Agency using the Business Number and issue to each of their employees a T4 slip that summarizes earnings received in the year. This process creates a link between the employee and the company through the Business Number. This link is the backbone of LEAP, and the reported payroll allows estimates of annual employment to be made. The payroll is converted to employment (called ALUs or Average Labour Units) using conversion factors derived from the Survey of Employment, Payroll and Hours (SEPH). An Average Labour Unit is a calculated measure portraying the average employment represented by a business's payroll if it paid the average earnings typical in its particular 4-digit industry category, province and business size. In the absence of complete longitudinal data on employment in all businesses, the average employment is calculated by converting each business's payroll into an approximation of the annual average level of employment it represented. The ALU employment estimate is derived by dividing the business's payroll (from T4 system) by the corresponding industry/province average annual earnings per employee (from SEPH system).

Quality evaluation

The results are compared to other estimates of employment for verification purposes.

Disclosure control

Statistics Canada is prohibited by law from releasing any information it collects that 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.

In order to prevent any data disclosure, confidentiality analysis is done using the Statistics Canada Generalized Disclosure Control System (G-Confid). G-Confid is used for primary suppression (direct disclosure) as well as for secondary suppression (residual disclosure). Direct disclosure occurs when the value in a tabulation cell is composed of or dominated by few enterprises while residual disclosure occurs when confidential information can be derived indirectly by piecing together information from different sources or data series.

Revisions and seasonal adjustment

The LEAP database is updated annually with the addition of another year of data. The longitudinal information may change with each annual update as the state of enterprises changes with time. Also with each annual update some quality control work is done which may cause changes to the cross sectional files.

Data accuracy

Some industries, mostly in the government sector, are not accurately represented at the four digit NAICS industry level. For example, firms such as municipal police forces and transit systems often cannot be separated out from the larger corporate structure of the municipality.