Quarterly Survey of Telecommunications

Detailed information for fourth quarter 2007

Status:

Active

Frequency:

Quarterly

Record number:

2721

This survey collects financial and operating data for the statistical measurement and analysis of the telecommunications services subsector.

Data release - Data releases are suspended until further notice.

Description

The information collected by the Quarterly Survey of Telecommunications serves two broad objectives. The first is to measure the financial performance and economic contribution of the telecommunications services subsector. To meet this objective the survey collects information on revenues by type and on capital expenditures. 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:

- Statistics Canada for the production of the country's monthly and quarterly national accounts;
- 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;

The Quarterly Survey of Telecommunications was launched in 1999 in order to complement the annual survey by providing more timely statistics for a few key indicators. The survey was redesigned for 2007 to reflect the revised industry definition in the North American Industry Classification System (NAICS), to align its concepts on the redesigned annual survey conducted in partnership with the Canadian Radio-Television Commission (CRTC) and to reduce response burden.

Starting in 2012, the Quarterly Survey of Telecommunications is conducted in partnership with the CRTC, as is the case for the Annual Survey of Telecommunications (record number 2722). This partnership aims at reducing response burden and at improving data quality, with better coherence of data collected by government (Statistics Canada and CRTC) on the Telecommunications subsector.

Most of the content of the quarterly survey can be found in quarterly surveys conducted in previous years, while the rest of the content is found in the Annual Survey of Telecommunications, which is addressed to the same respondents.

Statistical activity

The telecommunications statistics program is a component of a broader program on science and technology indicators managed by the Science, Innovation and Electronic Information Division (SIEID).

The purpose of the broader program is to develop indicators that measure and explain the social and economic impacts of S&T activity based on a framework that ties them together in a coherent picture.

The attached document gives a short description of the main components of the broader program as well as a link to survey documentation for the last reference period for which data were released.

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

The target population of the survey consists of the largest Telecommunications service providers classified in sub-sector 517 - Telecommunication of the North American Industry Classification System (NAICS 2012). The sub-sector comprises establishments primarily engaged in providing telecommunications and/or video entertainment services over their own or leased networks, on a resale basis or over client-supplied high speed Internet connections.

Instrument design

The quarterly survey consists of a sub-set of questions from the annual survey of telecommunications conducted in partnership with the CRTC.

The questions have been tested through an annual collection of information by the CRTC. A sample of potential respondents were asked to evaluate whether the data requested is readily available in their information systems on a quarterly basis, could be estimated without undue response burden, or could not be provided. The final questionnaire was designed taking the results of this test into consideration.

Sampling

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

The list of establishments (the frame) targeted by the survey is obtained from the Annual Survey of Telecommunications (record number 2722). It is elaborated and maintained by the CRTC.

Data sources

Data collection for this reference period: 2008-01-01 to 2008-03-31

Responding to this survey is mandatory.

Data are collected directly from survey respondents.

The survey is a mail-out / mail back survey. The questionnaires are mailed out at quarter-end. The contact person for the survey is obtained prior to mail-out by negotiating reporting arrangements with the establishment.

The respondent has 30 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 30 days after the end of the quarter. A telephone contact is made with non-reporters 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 the accuracy and coherence of the reported data.
. Where possible, the reported data are compared to publicly available financial information and major discrepancies are investigated.
. A quarter-over-quarter comparison is made to identify any extreme or unexplained changes in reported data.

All unusual occurrences are queried for confirmation and clarified with the respondents concerned.

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.

Estimation

The overall estimates are derived from two components. A survey of larger establishments above a prescribed threshold is conducted using a mailed questionnaire. The annual survey, a census of telecommunications service providers, is used to produce undercoverage estimates for selected variables for those establishments that are not surveyed on a quarterly basis. Variables which may be subject to wide variation from period to period, such as capital expenditures and non-operating revenues and expenses, are not estimated for non-surveyed establishments.

Coverage rates are calculated by determining how much of total industry activity is attributed to the current quarterly respondents, using the most recent annual data available, taking into consideration buy-outs, mergers and consolidations since that period. These ratios are applied to the current quarter data.

Undercoverage estimates for access lines are not adjusted between quarters because the observed growth in surveyed establishments (large incumbents and entrants) is not expected to be replicated by non-surveyed establishments (small, often rural, service providers). The undercoverage estimate simply reflects the number of access lines of the non-surveyed establishments for the most recent annual data available. Mobile subscriber undercoverage has not been adjusted between quarters, not because non-surveyed establishments are thought to be static, but because these establishments constitute such a small share of the industry that any change attributable to them would be negligible.

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.

Revisions and seasonal adjustment

Revisions are sometimes necessary as it is not unusual for respondents to update or correct previously reported data. Revisions are made to quarterly statistics as soon as updated information becomes available.

The time series from this survey are not seasonally adjusted. The relatively small number of observations explains this situation.

Data accuracy

There are potentially four sources of non-sampling error in any given survey: coverage error, response error, non-response error and processing error. There are no objective measures of these errors.

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 services subsector, 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 quarter to quarter and any significant deviations from expected results 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 is not a major concern with this survey. There are circumstances where individual respondents are unable to participate fully in a given quarter. 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 for this purpose.

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.

The quarterly survey was designed to provide more timely estimates of the level of activity generated by the telecommunications services subsector. In order to quantify the accuracy with which this is achieved, a comparison of the results of this survey is made with the final estimates from the annual census of the same industries.

Report a problem on this page

Is something not working? Is there information outdated? Can't find what you're looking for?

Please contact us and let us know how we can help you.

Privacy notice

Date modified: