Data quality, concepts and methodology: Data quality

About the Labour Force Survey

The statistics contained in this report are based on information obtained through a sample survey of 56,000 representative households across the country. The Labour Force Survey, started in November 1945, was taken at quarterly intervals until November 1952. It has been carried out monthly since then. The information generated by the survey has expanded considerably over the years with a major redesign of the survey content in 1976 and again in 1997, and provides a rich and detailed picture of the Canadian labour market.

The sample used in the Labour Force Survey has been designed to represent all persons in the population 15 years of age and over residing in the provinces of Canada, with the exception of the following: persons living on Indian reserves, full-time members of the armed forces and people living in institutions (for example, inmates of penal institutions and patients in hospitals or nursing homes who have resided in the institution for more than six months). Monthly estimates of employment, unemployment and persons not in the labour force refer to the specific week covered by the survey each month, normally the week containing the 15th day.

Definitions and explanations

The labour force is composed of those members of the civilian non-institutional population 15 years of age and over who, during the reference week, were employed or unemployed.

Employed persons are those who, during the reference week:

  1. did any work at all
  2. had a job but were not at work

A person is considered to be full-time if his/her usual hours at the main job are 30 or more hours per week. When the number of hours worked at the main job is usually less than 30 hours per week then he/she is considered to be part-time.

Unemployed persons are those who, during the reference week:

  1. were without work, had actively looked for work in the past four weeks (ending with reference week), and were available for work;
  2. had not actively looked for work in the past four weeks but were on temporary layoff and were available for work;
  3. had not actively looked for work in the past four weeks but had a new job to start in four weeks or less from the reference week, and were available for work.

Persons in the civilian non-institutional population 15 years of age and over who, during the reference week, were neither employed nor unemployed are classified as not in the labour force.

The unemployment rate represents the number of unemployed persons expressed as a percentage of the labour force. The unemployment rate for a particular group (age, sex, etc.) is the number unemployed in that group expressed as a percentage of the labour force for that group.

The participation rate represents the labour force expressed as a percentage of the population 15 years of age and over. The participation rate for a particular group (age, sex, etc.) is the labour force in that group expressed as a percentage of the population for that group.

The employment rate (formerly the employment/population ratio) represents the number of persons employed expressed as a percentage of the population 15 years of age and over. The employment rate for a particular group (age, sex, etc.) is the number employed in that group expressed as a percentage of the population for that group.

The part-time rate represents the number of persons employed part-time expressed as a percentage of the employed. The part-time rate for a particular group (age, sex, etc.) is the number employed part-time in that group expressed as a percentage of the employed for that group.

All geographic regions are based on the 2006 Census boundaries.

Seasonal adjustment

Fluctuations in economic time series are caused by seasonal, cyclical and irregular movements. A seasonally adjusted series is one from which seasonal movements have been eliminated. Seasonal movements are defined as those which are caused by regular annual events such as climate, holidays, vacation periods and cycles related to crops, production and retail sales associated with Christmas and Easter. The seasonally adjusted series contains irregular as well as longer-term cyclical fluctuations.

The seasonally adjusted series are revised each year to take into account current data and to generate new forecast factors for the next twelve months. The data are therefore subject to slight revisions in future issues of this publication.

Sampling variability of estimates

Estimates in this publication are based on the Labour Force Survey, a monthly survey of approximately 56,000 households across Canada. Because the entire population is not surveyed, the estimates are subject to sampling error. While the published estimate is the best available indicator of the real value, changes in the level of any estimates between two months can be the result of a true change or sampling variability. The sampling error can be estimated by calculating the standard error for the published estimate or statistic. These standard errors have been included in the publication tables, in order to assist users in interpreting the data.

Interpretation based on standard error

Two thirds of the time (68%), a change greater than the sampling error indicates a real change. The larger the change compared to the standard error, the better the chance that we are observing a real change, as opposed to a change due to sampling variability. At the 95% level, in order to ensure that change is real, the change in the estimate must be greater than twice the sampling error.

Movements in estimates that are smaller than the sampling error are less likely to reflect a real change and more likely to be due to sampling variability. While the above is true for monthly movements, one can have more confidence in a series of consecutive movements in the same direction, even though some of the monthly movements may be smaller than the sampling error.

Interpretation based on confidence intervals

Confidence intervals provide another way of looking at the variability inherent in estimates of sample surveys. To illustrate how to calculate the confidence interval, let us say that one month the published estimate for total employment rose by 16,000 to reach 16,500,000. The associated standard error for the movement estimate is 27,200. The standard error used to interpret the movement estimate indicates that:

  1. There are approximately two chances in three (68%) that the real value of the movement between the two months falls within the range -11,200 to +43,200 (16,000 + or – one standard error).
  2. There are approximately nine chances in ten (90%) that the real value of the movement between the two months falls within the range -27,520 to +59,520 (16,000 + or – 1.6 times the standard error).
  3. There are approximately nineteen chances in twenty (95%) that the real value of the movement between the two months falls within the range -38,400 to +70,400 (16,000 + or – two standard errors).

For more detailed explanations on sampling variability of estimates, and in particular for information on how to assess the variability of level estimates, consult the Data quality section of the Guide to the Labour Force Survey, (71-543-G) on page 27.

Documentation

For more detailed information about the Labour Force Survey, see the following documents:

  1. Overview of the Labour Force Survey
  2. Guide to the Labour Force Survey (71-543-G)
  3. Data quality statement
  4. Methodology of the Canadian Labour Force Survey (71-526-X)
  5. LFS geographical maps