Employment Insurance Coverage Survey (EICS)
Detailed information for 2012
The Employment Insurance Coverage Survey provides a meaningful picture of who does or does not have access to EI benefits among the jobless and those in a situation of underemployment. The survey also covers access to maternity and parental benefits.
Data release - November 15, 2013
The main purpose of this survey is to study the coverage of the employment insurance program. It provides a meaningful picture of who does or does not have access to EI benefits among the jobless and those in a situation of underemployment. The Employment Insurance Coverage Survey also covers access to maternity and parental benefits.
The survey was designed to produce a series of precise measures to identify groups with low probability of receiving benefits, for instance, the long-term jobless, labour market entrants and students, people becoming unemployed after uninsured employment, people who have left jobs voluntarily and individuals who are eligible, given their employment history, but do not claim or otherwise receive benefits. The survey provides a detailed description of the characteristics of the last job held as well as reasons for not receiving benefits or for not claiming.
Through the survey data, analysts will also be able to observe the characteristics and situation of people not covered by EI and of those who exhausted EI benefits, the job search intensity of the unemployed, expectation of recall to a job, and alternate sources of income and funds.
Survey data pertaining to maternity and parental benefits answer questions on the proportion of mothers of an infant who received maternity and parental benefits, the reason why some mothers do not receive benefits and about sharing parental benefits with their spouse. The survey also allows looking at the timing and circumstances related to the return to work, the income adequacy of households with young children and more.
Reference period: Calendar year
Collection period: There are 4 collection cycles each year: April-May, July-August, November-December and January-February. Each cycle lasts 5 weeks and begins during the month following the reference month.
- Employment insurance, social assistance and other transfers
- Non-wage benefits
Data sources and methodology
The target population for this survey is composed of unemployed individuals (as defined by the Labour Force Survey) and other individuals who, given their recent status in the labour market, could potentially be eligible for employment insurance. This population is divided into five types:
1) persons who were unemployed during the reference week;
2) persons employed part-time during the reference week;
3) persons not in the labour force during the reference week;
4) persons employed full-time during the reference week who started their current job during the previous three months
5) mothers of infants less than one year old working during the reference week.
The target population for this survey is a subset of the target population for the Labour Force Survey (LFS). Specifically excluded from the LFS coverage are residents of the Yukon, Northwest Territories and Nunavut, persons living on Indian Reserves, full-time members of the Canadian Armed Forces and inmates of institutions. These groups together represent an exclusion of approximately 2% of the population aged 15 or over.
The questionnaire developed jointly by Statistics Canada and Human Resources and Social Development Canada was tested in a Pilot Survey before its implementation in 1997. Experts from the Questionnaire Design Resource Centre used cognitive interviews and prepared an evaluation report. The main recommendations were implemented. Minor changes were incorporated over the years, either to correct application errors, broaden the target population for some questions or to implement wording changes recommended by interviewers. Several questions were incorporated in 2000 to collect comprehensive information on access and use of parental leave.
The questionnaire underwent a major redesign for 2004 collection. The main purpose of the redesign was to bring the computer application in line with current standards for structure, naming conventions and operational considerations. There was little change to the wording of questions themselves, in particular for items used to derive the key survey estimates for the unemployed. For mothers however, content was added or modified in response to data gaps and issues identified by survey analysts. The new application was thoroughly tested for compliance with the written specifications.
In 2006, a few questions were modified to reflect the change in jurisdiction of parental benefits in the province of Québec. Additionally, all questions specifically related to parental benefits are now contained in two new sections: Parental benefits for mothers (PM) and Parental benefits for fathers (PF). These new sections replace Parental benefits (PB) and Total benefits (TB) used for 2004 and 2005 collection. The sections on Employment insurance (EI) Additional Payments (AP) and Plans to return to work (PR) were modified slightly for mothers but unchanged for the majority of respondents.
This is a sample survey with a cross-sectional design.
The Employment Insurance Coverage Survey (EICS) is administered to a sub-sample of individuals in the Labour Force Survey, and therefore its sample design is closely tied to that of the LFS. The EICS uses the rotation groups that completed their six months in the LFS in March, June, October or December. Mothers from four additional rotation groups are also selected to obtain an adequate sample size.
The LFS sample is further stratified using the EICS types which are:
1) persons who were unemployed during the reference week;
2) persons employed part-time during the reference week;
3) persons not in the labour force during the reference week but with some employment during the two years prior to the reference week and all mothers not working (including on maternity leave) and not looking for work;
4) persons employed full-time during the reference week and who started their current job during the previous two months and
5) mothers of infants less than one year old, who worked during the reference week.
One hundred percent of the available LFS sample available is kept for some stratum and a sub-sample of 70 or 50% is taken for others, using simple random sampling. In order to reduce the response burden within the household, a maximum of three persons per household are selected.
Only the full-time employed (Type 4) who have experienced an interruption in work in the two months prior to the survey reference week need to be interviewed. Since this information was not available from the LFS interview, all full-time workers with short job tenure at their current job were selected. The question on work interruption was asked in the EICS and respondents who worked continually over the two months prior to the reference week were not asked further questions. They are out-of-scope for the survey.
The total sample size for 2012 was 11,244.
Responding to this survey is voluntary.
Data are collected directly from survey respondents.
Individuals selected for the EICS are contacted three to seven weeks after their last LFS interview. All interviews are conducted over the telephone using a computer assisted interviewing application. Proxy response is not allowed in the EICS. Responses to survey questions are captured directly by the interviewer using the computerized questionnaire.
Similar to the LFS, the interviewers are asked to make all reasonable efforts to obtain the EICS interview. Refusals at first contact are followed up by a senior interviewer. However, contrary to the LFS, no letters are sent to help obtain the respondent's cooperation.
View the Questionnaire(s) and reporting guide(s) .
Some editing is done online at the time of the interview. Where the information entered is out of the range of expected values (too large or small), or inconsistent with the previous entries, the interviewer is prompted to seek correction of confirmation from the respondent (for instance employment earnings).
The main type of error treated after collection was in questionnaire flow, where questions which did not apply to the respondent were found to contain answers, or conversely, where relevant questions were missed. A computer edit automatically eliminated superfluous data. All questions not included on the valid path based on previous answers were set to Valid Skip (6, 96, 996 ...). The 'Not stated' reserved codes (9, 99, 999...) were used to identify missing data resulting from issues with the computerized questionnaire or questions that were skipped because the respondent could not answer previous filter questions (Don't Know or Refusal).
There was no other type of editing done on questionnaire items. Therefore, some internal consistency errors may become apparent when conducting analysis. One notable example is the item on hourly earnings (HRLYEARN) which does include a small number of outliers and internal inconsistencies (working individuals reporting zero earnings).
No imputation is done for this survey.
The calculation of the weights for the EICS incorporates the individual weights calculated for the LFS, as well as some estimates from this survey. Further adjustments are made to the LFS individual weights to take into account special features of the EICS.
The LFS individual weights are multiplied by 6, reflecting the use of one in six rotation groups per collection cycle (for mothers, the LFS weight is multiplied by 3). Another adjustment accounts for the EICS sub sampling for some strata; non-response is compensated taking geography, respondent type (1 to 5) and gender into consideration.
A final adjustment is done using two external non-overlapping independent sources: counts for regular beneficiaries with and without earnings (for groupings of administrative regions) and LFS estimates for each respondent type (the unemployed, part-time workers, not in the labour force having worked in the past two years and some full-time workers). Mothers who do not also meet the criteria for one of these 4 groups are not impacted by the adjustment for LFS characteristics. This calibration process ensures that the estimates produced with the EICS data are comparable the counts from the external sources.
Bootstrap weights are calculated to facilitate the calculation of variance for specific estimates. The Bootstrap weights were also used to create quick reference tables for variance estimates.
The data were mainly evaluated against recent historical trends, focusing on the derived variables that are created to provide comparable historical data with earlier years of the survey.
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.
It should be noted that the "Public Use" Microdata Files (PUMF) may differ from the survey "master" files held by Statistics Canada. These differences usually are the result of actions taken to protect the anonymity of individual survey respondents. The most common actions are the suppression of data items and the grouping of values into wider categories. For certain variables that risk identifying individuals, the PUMF may have been treated with local suppression, where some of the values in the master file have been coded as "not stated" on the PUMF.
Revisions and seasonal adjustment
This methodology does not apply to this survey.
While considerable effort is made to ensure high standards throughout all stages of collection and processing, the resulting estimates are inevitably subject to a certain degree of error. These errors can be broken down into two major types: non-sampling and sampling.
The basis for measuring the potential size of sampling errors is the standard error of the estimates derived from survey results. Because of the large variety of estimates that can be produced from a survey, the standard error of an estimate is usually expressed relative to the estimate to which it pertains. This resulting measure, known as the coefficient of variation (CV) of an estimate, is obtained by dividing the standard error of the estimate by the estimate itself and is expressed as a percentage of the estimate.