Head Office Survey

Detailed information for 2006

This survey is conducted to improve the accuracy and completeness of statistics on businesses in Canada.

Data release - The information reported in the questionnaire is used in calculating estimates of economic activity for the industries surveyed by the Unified Enterprise Survey (UES) Program.

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

Description

This survey is conducted to improve the accuracy and completeness of statistics on businesses in Canada.

When combined with information from other sources, these data will be used to produce official estimates of economic and provincial output in Canada, along with official estimates of activity by industry. These estimates will be used by governments to set up national and regional programs and to plan policies, and by the private sector to measure industries' performance and to develop markets.

Statistical activity

The survey is administered as part of the Unified Enterprise Survey program (UES). The UES program has been designed to integrate, gradually over time, the approximately 200 separate business surveys into a single master survey program. The UES aims at collecting more industry and product detail at the provincial level than was previously possible while avoiding overlap between different survey questionnaires. The redesigned business survey questionnaires have a consistent look, structure and content. The unified approach makes reporting easier for firms operating in different industries because they can provide similar information for each branch operation. This way they avoid having to respond to questionnaires that differ for each industry in terms of format, wording and even concepts.

Subjects

• Labour
• Workplace organization, innovation, performance

Data sources and methodology

Target population

The target population of this survey is those head offices which are part of enterprises which are in the Unified Enterprise Survey (UES) which have operating revenues greater than $25 million.

Instrument design

The basic content for the Head Office questionnaire has remained constant for several years. The content of this questionnaire was tested with a group of test respondents to determine whether or not it was possible for the respondents to understand the content of the questions and report the information requested.

Sampling

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

This methodology does not apply.

Data sources

Responding to this survey is mandatory.

Data are collected directly from survey respondents.

This survey is collected using a paper based questionnaire which is mailed to respondents. If the respondent does not mail back the questionnaire within a month, the respondent is contacted to obtain the questionnaire. After a month, there are three attempts made to contact the respondent. If the respondent has not returned the questionnaire before the collection period is terminated, the subject matter experts try to contact the respondent for the information prior to the publication of the data.

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

Error detection

In order to ensure data quality, when the data are initially captured, the captured data are compared to historical data the respondent reported in the last collection period. If the data vary considerably, the respondent is contacted to confirm the reasons for the large change in their data between reference periods.

In addition, the captured data is edited to ensure that it is internally consistent, as well as, consistent with other sources of data collected by Statistics Canada, where possible.

Imputation

In cases where the respondent has not completed the questionnaire in time for the current production cycle, the data for the respondent are imputed using historical information if the respondent has completed this questionnaire in the previous production cycle. In cases of non-response, but the respondent is new to the survey, then the data for the respondent is imputed using information taken from the Business Register's frame. The only information that is imputed is the number of employees and total labour remuneration.

Estimation

This methodology type does not apply to this statistical program.

Quality evaluation

There are two broad methods of evaluating data quality: certification or validation of the data and sources of error studies. The first type aims to analyze and verify the data prior to its release in order to avoid gross errors and to eliminate poor quality data. Since this survey is designed to represent the economic activity of a sub-population of head offices, changes in the economic aggregates of this sub-population are verified to determine the source of these changes. For example, the economic data from the head office survey are compared with the economic data of the other business surveys which are part of the Unified Enterprise Survey. In general, the trends in the head office data should be similar to the trends in the economic data of the establishments which these head offices support.

In addition, several certification methods are used to validate the quality of the data. First, the head office establishment level data is compared to the enterprise level data to ensure the coherence of the head office data with other data produced by Statistics Canada. Second, the data of the head offices which are the most important in terms of size are carefully analyzed to ensure that these data are accurate and complete.

The second method for evaluating data quality is that of studies which aim to determine and measure the sources of error. For example, from time to time, there are studies on the sources of error which aim to measure the level of measurement error which is caused when the response provided differs from the real value. This type of error can be attributable to the respondent, the questionnaire, and the collection method, or the respondent's record keeping system.

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

Data may be revised to include questionnaires which come in after the end of the production cycle or due to errors that have been detected either in the information collected from respondents or in the processing of these data. The revisions are reflected in the final version of the data produced one year after its initial production. These data are not seasonally adjusted.

Data accuracy

Data accuracy refers to how accurately the estimates from a survey represent the population that the survey is designed to cover. There are two major types of errors that can have an affect on the accuracy of a survey's results: sampling error and non-sampling error. Sampling error can occur when the results of a survey are obtained from a sample of the population, rather than from the whole population. Non-sampling errors refer to those types of errors that result from the survey process. In the case of the Head Office survey, since the sample for the Head Office survey is designed as a census of all head offices which are part of enterprises with in the Unified Enterprise Survey, there in no sampling error. The only types of error which can potentially impact on the accuracy of the head office data are non-sampling errors.

There are several potential sources of non-sampling errors and they are: coverage error; data response error; non-response error; and processing error. Coverage errors which consist of omissions, erroneous inclusions, and duplications in the frame used to conduct a survey can impact on survey estimates. Data response errors may be due to questionnaire design, the characteristics of a question, the inability or unwillingness of the respondent to provide correct information, the misinterpretation of the questions or definitional problems. Non-response errors occur when there is no response to a questionnaire or a question or series of questions. Processing errors can occur because of the way the data are captured, edited, or tabulated.

In the case of the survey, several measures have been put in place with the goal of diminishing the potential sources of non-sampling error. To ensure that there are no coverage errors in the Head Office survey's coverage of the head office population, during each survey cycle, the frame is evaluated to ensure that it represents the population of Head Offices by comparing it with outside information and by contacting respondents to determine the status of the operations, if necessary. Data response error is not a significant problem because the questionnaire has been thoroughly tested with respondents through focus groups. Non-response errors are lowered by maintaining a response rate that is greater than 80%. Processing errors are lowered by several processes which aim to control and lower these types of errors. For example, data entry and editing are performed simultaneously which allows errors to be quickly detected.