Annual Survey of Telecommunications

Detailed information for 2001

This survey collects financial and operating data for the statistical measurement and analysis of the telecommunications industry (telecom carriage or resale).

Data release - December 19, 2003

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

Description

The information collected as part of the Annual Survey of Telecommunications serves two broad objectives. The first is to measure the financial performance and economic contribution of the telecommunications sector. To meet this objective the survey collects information on revenues and expenses by type, employment and investments. The second broad objective is to measure the deployment and use of the telecommunications infrastructure. To meet this objective the survey collects data on the number of fixed and wireless accesses by type and on telecommunications traffic.

The estimates from this survey are used by:

· Policy and industry analysts to monitor the performance of the industry and assess the impact of policy;
· International telecommunications organizations such as the International Telecommunications Union and the OECD to study the importance of this sector and of the ICT sector in various economies;
· Investment dealers, consultants and others for market analysis;
· Statistics Canada for the production of the national and provincial input-output accounts.

The Annual Survey of Telecommunications is an output of the Telecommunications Statistical Infrastructure and Economic Analysis Program undertaken by Statistics Canada and Industry Canada in 1996. This program's objective is to update statistics concerning the telecommunications industries. The many technological and regulatory changes affecting the industry motivated the redesign of the statistical program.

The survey was launched for the 1997 year to provide more relevant information on an industry that was going through significant structural changes as a result of a new competitive environment and rapid technological changes. This annual survey is complemented by a quarterly survey of the industry that collects selected key variables on a more timely basis (see survey number 2721).

Statistical activity

Science and technology (S&T) and the information society are changing the way we live, learn and work. The concepts are closely intertwined: science generates new understanding of the way the world works, technology applies it to develop innovative products and services and the information society is one of the results of the innovations.

People are looking to Statistics Canada to measure and explain the social and economic impacts of these changes.

The purpose of this Program is to develop useful indicators of S&T activity in Canada based on a framework that ties them together in a coherent picture.

Reference period: Calendar year

Collection period: Spring (March-June)

Subjects

• Business, consumer and property services
• Business performance and ownership
• Financial statements and performance
• Information and communications technology
• Information and culture
• Telecommunication industries

Data sources and methodology

Target population

This survey targets establishments of the telecommunications sector, as defined by category 5133 -Telecommunications of the North American Industry Classification System (NAICS). The telecommunications sector consists of establishments primarily engaged in the provision of fixed or mobile telecommunications services. It includes establishments offering full or limited range of voice and data telecommunication products and services using their own network or reselling the services of others. This sector does not include Internet Service Providers.

The list of establishments (the frame) targeted by the survey is elaborated from a variety of sources, the most important being a CRTC database, Statistics Canada's Business Register, trade publications and the media.

Instrument design

The survey instruments were developed with the assistance of an Advisory Group consisting of data users and suppliers. The Group was convened to provide subject matter expertise, to reflect industry and academic insights and to take into consideration industry needs and constraints.

The questionnaires proposed by the Advisory Group were tested with a sample of potential respondents. These respondents were asked to evaluate whether the information requested was readily available in their information systems, could be estimated without undue response burdens, or could not be provided. The final questionnaire was designed taking the results of this test into consideration.

The annual survey currently uses industry specific questionnaires. Large operators are asked to supply more detailed information than their smaller counterparts.

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.

The survey is a mail-out / mail back survey collected on an annual basis. The survey questionnaires are mailed out at the end of March following the end of the reference year. The contact for the survey is obtained prior to mail-out by contacting the company and making reporting arrangements.

The respondent has 45 days after reception of the survey to complete and return the questionnaire to Statistics Canada. Non-reporters are sent a reminder notice by e-mail or fax 45 days after the end of the reporting period. A telephone contact is made with non-reporting enterprises 15 days later to discuss reporting delinquency and possible special arrangements.

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

Error detection

In order to identify, minimise and correct errors, the following quality control measures are applied to the data:

· A manual audit is performed to ensure that the questionnaire coverage is as anticipated and that a complete response has been provided.
· During the capture process, the data are subjected to computerised edits. These edits are designed to ensure that accounting relationships are respected and that related variables have been reported on a consistent basis.
· Where possible, the reported data are compared to publicly available financial information and major discrepancies are investigated.
· A year-over-year comparison is made to identify any extreme or unexplained changes in output or input structures.

All unusual occurrences are queried for confirmation and clarified with the respondents concerned. However, most financial data collected are derived from audited financial statements resulting in minimal errors and inconsistencies.

Imputation

Manual imputations are done at the establishment level. One of 3 methods is normally used to impute for a missing, invalid or inconsistent response:

· Data submitted by a respondent for a previous period are used to impute data for the current period.
· Imputation for partial or total non-response by a respondent is made on the basis of a full response by a respondent with similar characteristics.
· Total industry or sub-industry weights or averages are used to impute missing variables.

Quality evaluation

As the last step of the data quality control process, the analyst responsible for the survey undertakes a critical assessment of the main facts portrayed by the aggregated data. The assessment includes a systematic review of historical trends, a coherence check based on analytical ratios, a comparison with other data sources and a confrontation with independent sector analysis. If this process leads to concerns about the quality of survey results, a series of steps to identify and eliminate potential errors in the micro data are repeated. These steps are described in the section "Data editing".

At this stage in the process, the evaluation of quality depends to a large extent on the expertise of the analyst responsible for the survey. The expertise is developed over time in several ways including networking with other analysts in the public and private sectors, participation in conferences and by reading relevant material.

Disclosure control

Statistics Canada is prohibited by law from releasing any information it collects which 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.

Data for a specific industry or variable may be suppressed (along with that of a second industry or variable) if the number of enterprises in the population is too low.

Data accuracy

The annual survey of telecommunications is not a sample survey and therefore sampling errors do not occur. Non-sampling errors, however may occur. There are potentially four sources of non-sampling error that can be identified in any given survey: coverage error, response error, non-response error and processing error.

Coverage error results from inadequate representation of the intended population. This error may occur during selection of the survey population, or during data collection and processing. In order to avoid such errors, a number of sources describing the population of the industry are used and compared. However, given the relatively small population and high concentration of the telecommunications industries, the coverage error has no material impact on the results of this survey.

Response error may be due to many factors, including faulty design of the questionnaire, respondents' misinterpretation of questions, or respondents' faulty reporting. Frequent changes in company personnel may also lead to response error. Several features are in place to help respondents complete the questionnaire, including logic and consistency checks, and a glossary of terms and concepts. Responses are compared from year to year and any significant deviations are queried by analysts to ensure their accuracy. However, even with these checks, the quality of data depends on the respondent's willingness to consult their records.

Non-response error occurs because not all respondents cooperate fully. This has not been a major concern with this survey. All major carriers participate in the survey. There are circumstances where individual respondents are unable to participate fully. To alleviate the impact on the survey, respondents are usually asked to provide key variables and the others are estimated. Publicly available information is also used.

The average response rate to the survey is close to 70% and the weighted response rate close to 99.0%. Non-response is limited to smaller operators. Imputations made for total and partial non-response are subject to errors. This error applies to approximately 17% of the data points collected by this survey (5.6%). Imputations are generally limited to details for which the respondent supplies a control total. Imputations represent less than 2.5% of the value of the key variables produced by this survey such as operating revenues and expenses, labour costs, access lines and subscribers. Imputations are more frequent in the case of small operators (short questionnaire), and these imputations account for a larger proportion of values.

Processing errors may also occur during coding, entry, editing and tabulation of the data. In this survey, procedures for quality control are used during the processing of data to keep such errors to a minimum.