View the most recent version.

Non-Response follow-up

Low response rate to the survey within a specific industry and province/territory represents the primary reason for follow-up. Initially, a general reminder is sent in the form of a mailout to the entire delinquent portion of the sample. If non-response continues, establishments in areas of lowest coverage are solicited by telephone for the return of the completed questionnaire. Actively canvasing sampled non-response establishments increases the response rate and, as a result, estimation for the non-sampled portion of the frame are made more accurate (see "Data quality, concepts and methodology — Methodology").

Editing

After the questionnaires have been completed and returned, the process of quality assurance continues through data editing. Data are screened at the micro level for internal, survey over survey and year over year inconsistencies.

Add-check edits identify expenditure data that are incorrectly reported in dollars rather than thousands, percentage data failing to add to 100 percent and/or inconsistencies related to the reported totals. Large difference edits evaluate the consistency of reported expenditures by comparing the current data with reports from a previous survey within the same year and from a different year. On the actual survey for respondents receiving long forms, asset detail edits identify all establishments reporting expenditures on assets or asset details which are inconsistent with previous questionnaire returns or inconsistent with assets commonly used in the respondent's industry. Edit tests will flag reported data for confirmation based on thresholds which are set after evaluating industry coverage and geographic location. In addition, new and large project data are collected from newspapers, trade journals and industry reports. This information is compared to reported data and any inconsistencies are flagged for confirmation.

Once an establishment's reported expenditures data have been flagged by the edit process, additional questionnaire data are consulted for an explanation. For example, the questionnaire section entitled, "Reasons for changes in capital expenditures", contains respondent supplied explanations for changes in capital expenditure. However, if the reason for the inconsistency cannot be ascertained from the questionnaire or other industry information, the reporting establishment is contacted directly for confirmation. Based on this inquiry the data reported are updated to include either new data or an explanation of expenditures.

Other micro data editing may occur for reported Gross Book Value or Capacity Utilization. Gross book value edits occur when the reported gross book value of an establishments assets does not coincide with the previously reported gross book value plus current investment in new capital net of disposals. In this case, the establishment is contacted for confirmation of (or an update to) the reported data. Capacity utilization edits identify all those manufacturing and mining establishments operating at less than expected manufacturing or mining capacity. If previous reports are significantly different from the current questionnaire response, the establishment is contacted to confirm or update the reported data.

Macro data evaluation

After the estimation process (see "Estimation"), a comprehensive data set exists for the surveyed and non-surveyed portions of the universe (frame) and therefore trend analysis for the various industries can begin. Commencing with an evaluation of the year over year (or percentage) change in each industry, provinces/territories that have industries or sub-industries experiencing unusual activity are highlighted. In addition, this type of analysis also identifies industries which have the largest impact on Canadian aggregates.

Macro analysis continues with the assessment of information which may be effecting the expenditures in a specific province or industry. This additional information might come in the form of economic indicators such as GDP, productivity, capacity utilization, profits or technological innovation. Factors influencing the expenditures might also include government policies (fiscal policy, monetary policy, grants and/or subsidies) or industry specific information such as meters drilled, import/export data or building permits. Although causality is not drawn, the analysis attempts to link information directly and indirectly related to the industry with recent trends in capital expenditures. As a by product of this analysis, those industries experiencing exceptional activity will undergo further micro data evaluation to determine the reason for the large year over year change.