National Graduates Survey (NGS)

Detailed information for 2013 (class of 2009/2010)

This survey was designed to determine the following factors: the extent to which graduates of postsecondary programs had been successful in obtaining employment since graduation; the relationship between the graduates' programs of study and the employment subsequently obtained; the graduates' job and career satisfaction; the type of employment obtained related to career expectations and qualification requirements; and the influence of postsecondary education on occupational achievement.

Data release - March 31, 2014

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

Description

This survey is designed to determine such factors as: the extent to which graduates of postsecondary programs have been successful in obtaining employment since graduation; the relationship between the graduates' programs of study and the employment subsequently obtained; the graduates' job and career satisfaction; the rates of under-employment and unemployment; the type of employment obtained related to career expectations and qualification requirements; and the influence of postsecondary education on occupational achievement.

Subjects

• Education, training and learning
• Employment and unemployment
• Fields of study
• Labour
• Outcomes of education

Data sources and methodology

Target population

Graduates from Canadian public postsecondary education institutions (universities, colleges, trade schools) who graduated or completed the requirements for degrees, diplomas or certificates during the reference school year are the targeted population for this survey. Excluded are: graduates from private postsecondary education institutions; completers of continuing-education programs (unless these led to a degree, diploma or certificate); persons who completed programs lasting less than three months; persons who completed programs other than in the skilled trades (e.g., basic training and skill development); completers of provincial apprenticeship programs and those living outside of Canada or the United States at the time of the survey.

Instrument design

For the most part, the questionnaire used was the same as for the 2007 National Graduates Survey (Class of 2005).

Sampling

This is a sample survey with a cross-sectional design.

The National Graduates Survey uses a stratified simple random sample design. The sample selection of graduates within strata is done without replacement and using a systematic method.

Data sources

Data collection for this reference period: 2013-04-02 to 2013-09-01

Responding to this survey is voluntary.

Data are collected directly from survey respondents.

Interviewers collected the data using a computer-assisted telephone interviewing method (CATI). They were instructed to make all reasonable attempts to obtain interviews with the selected graduates. Proxy response was not allowed. For graduates who refused to participate, a letter was sent from the Regional Office to the dwelling address stressing the importance of the survey and the graduate's cooperation. This was followed by a second call from the interviewer. For cases in which the timing of the interviewer's call was inconvenient, an appointment was arranged to call back at a more convenient time. For cases in which there was no one home, numerous call backs were made. If graduates had moved, various tracing methods were used to locate them.

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

Error detection

The first stage of survey processing undertaken at head office was the replacement of any "out-of-range" values on the data file with blanks. This process was designed to make further editing easier.

The first type of error treated was errors in the questionnaire flow, where questions that did not apply to the graduate (and should therefore not have been answered) were found to contain answers. In this case, a computer edit automatically eliminated superfluous data by following the flow of the questionnaire implied by answers to previous questions.

The second type of error treated involved a lack of information in questions which should have been answered. For this type of error, a non-response or "not-stated" code was assigned to the item.

The third type of editing performed was related to inconsistencies in some of the responses received. In a situation where an inconsistency was found, depending on the nature of the inconsistency, various actions could be taken. The inconsistent variable (or one of the variables involved) could either be changed to "not stated", corrected or left unchanged. For example, if a respondent reported an hourly salary of 35,000 dollars, the "hourly" was changed to "annually". However, in situations where it was not possible to determine which variable was most likely to be wrong, no action was taken and a flag was derived.

For quantitative variables such as financial variables, editing which included outlier detection was performed. These variables include reported information on earnings, income, and student loans. Potential outliers were identified and manual investigations were made on these cases to confirm their outlier status. Outliers were changed to "not stated" or replaced by a more plausible value when a realistic value could be deduced from the other variables.

Imputation

No imputation was done for the National Graduates Survey - Class of 2009/2010 (NGS2013).

Estimation

In order for estimates produced from survey data to be representative of the target population, and not just of the sample itself, users must incorporate the survey weights into their calculations. A survey weight is given to each person included in the final sample, that is, the sample of persons who responded to the survey questions. This weight corresponds to the number of persons represented by the respondent for the target population. If the frame used was perfect (covering exactly the population of interest) and all selected units were traced, contacted and completed the survey, then the design weight assigned to each unit, given by the inverse of the probability of selection of each unit in the sample, would represent accurately and exactly the number of graduates in the target population. In this situation, using this weight would yield unbiased estimates. However, this is not the case when surveys are faced with non-response and imperfect frames. Weight adjustments are traditionally used to compensate for these different issues. Response patterns have to be studied carefully to appropriately adjust for non-response by creating response homogeneous groups (RHG) based on the characteristics of the respondents and the non-respondents.

For weighting purposes, this survey can be seen as a two-phase survey. The first phase corresponds to the selection of the sample and the responding units correspond to the second phase sample. The first phase weight is the inverse of the probability of selection of the graduate. This first phase weight is then multiplied by a second phase adjustment factor. For the purpose of the second phase adjustment, response homogeneous groups (RHG) are created based on the characteristics of the respondents and the non-respondents. The second phase adjustment factor reflects the response rate within these RHGs, as well as other weight adjustments that were performed (e.g., post-stratification and weight trimming).

For variance estimation, the two-phase approach of the Generalized Estimation System (GES) was used.

Quality evaluation

A few inaccuracies on the frame were discovered only during the collection process. For example, the initial frame included young adults taking short courses (e.g. hunting safety), as well as foreign students that had done their studies remotely. Such units shouldn't have been on the frame, so they were immediately coded as out of scope and removed from the collection process.

The same criteria used to remove them from collection were used to remove them from the frame. The stratum jumpers also provided an opportunity to update the totals on the frame. The non-response-adjusted weights were therefore re-calibrated such that they would yield the updated frame totals.

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

This methodology does not apply to this survey.

Data accuracy

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: sampling and non-sampling. Frame imperfection and non-response are important sources of non-sampling error.

The sample was designed to yield estimates of a minimal proportion of 5.5% with a maximum coefficient of variation (CV) of 16.17% for any of the NGS 2013's marginal. A marginal is defined as: i) a given field of study regardless of the province of institution; or ii) a given province of institution regardless of the field of study; and that for each of the five levels of certification. There were two exceptions to this rule: the sample sizes for "Other" fields of study were reduced by two thirds (since they aren't as important from an analytical point of view), and all PhDs were drawn into the sample.