Quarterly Industry Revenue Indices (QIRI)

Detailed information for fourth quarter 2011

Status:

Inactive

Frequency:

Quarterly

Record number:

5104

The Quarterly Industry Revenue Indices (QIRI) measure the rate of change in operating revenues for selected industries in the business and consumer services sector.

Data release - March 28, 2012

Description

The Quarterly Industry Revenue Indices (QIRI) provide sub-annual indicators of economic activity for selected business and consumer services. This program combines administrative and survey data to measure changes in the quarterly operating revenues in current dollars for selected 4-digit North American Industrial Classification System (NAICS) industries.

For each industry covered by the program, unadjusted as well as seasonally adjusted series are available, at both the national and provincial levels. Results are produced in the form of indices of operating revenues in current dollars with 2007 as the base year. For each industry by geography time-series, the average value of the quarters in the base year is set to 100 and forms the scale for calculating the index values for every reference period in the series.

QIRI has been developed to increase the scope of sub-annual economic statistics within the service sector by providing a timely indicator of change in industrial output.

The data are used by Statistics Canada as input to the Canadian System of National Accounts.

Reference period: Quarter

Collection period: The two months following the reference quarter

Subjects

  • Business, consumer and property services
  • Business performance and ownership
  • Financial statements and performance

Data sources and methodology

Target population

Currently, the target population of the Quarterly Industry Revenue Indices (QIRI) comprises all establishments on the Business Register classified to the following industries at the four-digit level of the North American Industry Classification System (NAICS):

5111 Newspaper, periodical, book and directory publishers
5312 Offices of real estate agents and brokers
5322 Consumer goods rental
5323 General rental centres
5412 Accounting, tax preparation, bookkeeping and payroll services
5413 Architectural, engineering and related services
5414 Specialized design services
5416 Management, scientific and technical consulting services
5418 Advertising, public relations and related services
5613 Employment services
5621 Waste collection
5622 Waste treatment and disposal
5629 Remediation and other waste management services
7131 Amusement parks and arcades
7139 Other amusement and recreation
7211 Traveller accommodation
8111 Automotive repair and maintenance
8112 Electronic and precision equipment repair and maintenance
8113 Commercial and industrial machinery and equipment repair and maintenance
8121 Personal care services
8122 Funeral services
8123 Dry cleaning and laundry services

Descriptions of these industries are available through the link below.

Instrument design

The indices incorporate both administrative and survey data. For simple establishments, levels of operating revenues reported to Canada Revenue Agency for the purposes of the Goods and Services Tax (GST) are used. A questionnaire gathers information from complex establishments, and is collected at the establishment level.

The Quarterly Services Indicators Survey questionnaire was designed to collect quarterly operating revenue data from complex enterprises. Given the broad range of industries being surveyed, the questionnaire had to be of a sufficiently generic design to adequately capture the required data and yet specifically exclude data that were deemed outside the scope of interest.

The questionnaire is designed to allow the respondent to report revenues for all thirteen provincial and territorial jurisdictions.

Questionnaire testing was performed by Statistics Canada's Questionnaire Design Resource Center in 2005. A series of one-on-one interviews was conducted with firms in Ottawa, Toronto and Montreal.

Sampling

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

Data are collected for all units of the target population, therefore there is no sampling. The survey portion of the QIRI is a census of complex units.

Data sources

Responding to this survey is mandatory.

Data are collected directly from survey respondents and extracted from administrative files.

For simple enterprises, levels of operating revenues reported to Canada Revenue Agency for the purposes of the Goods and Services Tax (GST) are used. A simple establishment is defined as a firm that undertakes only one business activity at the 4-digit NAICS level and operates in only one province. A survey component gathers information from complex enterprises. Complex enterprises are defined as those that operate in more than one provincial jurisdiction and/or have some economic activity in more than one industry designation.

Administrative data

The GST file is sent by the Canada Revenue Agency (CRA) to Tax Data Division (TDD) at Statistics Canada. TDD then carries out further processing which is solely for statistical purposes at Statistics Canada. The TDD processing is not intended to administer or monitor the GST program and no edits or modifications are ever sent back to CRA.

This processing ensures a clean and complete database to be accessed by the various business survey programs at Statistics Canada. TDD processing includes outlier detection, correction of erroneous data, and replacement of missing data through edit, imputation and extrapolation.

TDD also breaks multi-weekly, quarterly or annual transactions into monthly data, through a calendarization process. In this process sales figures are distributed over the calendar months covered by non-monthly transactions using a calculated industry specific seasonal pattern. Finally, monthly data are allocated to their corresponding enterprise(s) and establishment(s) using information from Statistics Canada's Business Register. The allocation process splits enterprises into two types of units, simple and complex.

The Quarterly Industry Revenue Indices program utilizes the allocated file for the simple units provided by TDD, to generate quarterly revenue figures for the universe of simple units covered by the program.

Survey data

The survey portion of QIRI is a census and is mandatory. The survey uses e-questionnaire, fax and mail as modes of collection. The survey is establishment based and is based exclusively on the Business Register from which the survey universe is drawn once a year. Data are collected at the establishment level. The data are collected, edited and compiled within a 45-day period of the end of the calendar quarter. The TDD allocated file for complex units is used as an auxiliary file in the process of imputing values for the nonresponding complex units.

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

Error detection

Data are examined for inconsistencies and errors using automated edits coupled with analytical review. Historical and internal consistency edits of reported sales values are done for the responding complex units. Where possible, data will be verified using alternate sources.

Imputation

Imputation is done for records that failed edits and for units that did not respond to the survey.

For the surveyed units that fail the edits, some can be imputed automatically by deterministic imputation, while others can be imputed automatically based on a set of survey-specific rules. Those that fail the edits and cannot be imputed automatically are manually inspected by subject matter experts and are corrected as necessary.

For the survey data, imputation is done using historical trends when historical survey data are available, or ratio imputation, where the ratio is obtained by dividing the sum of reported revenues (from the survey) by the sum of GST revenue at the 4-digit NAICS level. This ratio is applied to the GST revenue of non-respondents to obtain an imputed survey value for each applicable 4-digit NAICS industry. The ratio is a proxy to allow for allocation differences that the GST value will not yield if used on its own. If the number of units available to compute the ratio is too small, industries are collapsed to the 3-digit NAICS level.

Statistics Canada uses a probabilistic approach to identify inactive units based on a combination of reporting frequency and number of delinquent months. When a business fails to report for a given period and is considered inactive, the system stops imputing values.

The initial file received from the tax authority may contain only one value to cover all units for complex enterprises. In order to adequately represent activity at the enterprise level, Tax Data Division (TDD) allocates reported revenue from the tax file across the entire profile for each complex entity. The allocated file becomes, in essence, the default estimate for all complex entities on the universe file. Information received from the surveyed portion of the universe file is used as a replacement for data generated through the allocation process.

For the administrative portion, the data have already been processed as part of the larger tax data program at Statistics Canada. Missing or late filers are imputed, any non-monthly GST remitters are calendarized and, for complex enterprises that operate in more than one province, the revenue is allocated by province. During QIRI processing, there can be some additional correction to the administrative data by subject matter experts.

Estimation

This methodology type does not apply to this statistical program.

Quality evaluation

Prior to dissemination, combined administrative and survey data are analyzed for overall quality; in general, this includes a detailed review of individual responses (especially for the largest companies), an assessment of the general economic conditions portrayed by the data, historic trends, and comparisons with other data sources.

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

The preliminary raw and seasonally adjusted estimates that are released each quarter are revised according to the following schedule.

With the release of a quarter's estimate, the preliminary raw estimates from the previous quarter are revised with new information. Revisions are made to the data to correct for late-filers to GST, late survey data, industry misclassification, and to correct errors discovered during the analysis phase.

Revisions are also made to the seasonally adjusted data. In part, they need to reflect the revisions identified for the raw data. Also, the seasonally adjusted estimates are calculated using X-12-ARIMA, and the trend is sensitive to the most recent values reported in the raw data. For this reason, with the release of each quarter of new seasonally adjusted data not only is the previous quarter revised, but revisions are also made to prior quarters, going back to the first quarter of the previous year. Revising seasonally adjusted data back to the first quarter of the previous year ensures that the sum of the four quarters of seasonally adjusted data is equal to the sum of the four quarters of raw data.

The first quarter of each calendar year requires special treatment. In addition to making revisions to the previous quarter additional revisions are needed. Both raw and seasonally adjusted data are revised four years or sixteen quarters back. Revisions may also be made on an occasional basis (i.e. changes to the design of the survey).

QIRI time series may be subject to seasonal or calendar effects. Seasonal effects are the quarterly fluctuations which repeat more or less regularly from year to year. They result from composite effects of climatic events, institutional decisions or modes of operation which repeat with a certain regularity within the year. Calendar effects are related to the composition of the calendar. They include trading-day effects associated with the weekday composition of the quarter, moving holiday effects associated with non-fixed date holidays such as Easter, and other predictable events from the calendar.

As these effects conceal the fundamental trend-cycle component of the series, QIRI series are also available in seasonally adjusted form, where seasonal and calendar effects have been estimated and removed using the X-12-ARIMA method.Time series with no identifiable seasonal pattern remain unchanged from the official series.

To identify a seasonal pattern, time series must be at least 5 years long and preferably between 10 and 15 years. In the absence of the survey component for the period pre-dating the launch of the QIRI program, only administrative data was available to enable seasonal factor estimation.

National estimates are seasonally adjusted directly, as are the provincial and territorial estimates. As seasonal adjustment is a non-linear process, the sum of the directly adjusted provincial and territorial estimates do not add up to the direct adjustment of the national series. To restore coherence, a raking adjustment, also referred to as reconciliation, is applied to the provincial and territorial series. Indices are computed after this process and may further hide the linear relationship of the series.

Data accuracy

Data from the survey are subject to non-sampling error such as coverage error, non-response, incorrect information from respondents and errors introduced during the capture or processing of data. Efforts are made to limit these errors through thoughtful questionnaire design, data capture edits, follow-up with respondents to confirm data, as well as other consistency edits during processing.

For all indices published by the QIRI program, a quality indicator is provided. In most Statistics Canada programs, quality indicators are derived for the coefficient of variation, which is a measure of variability due to sampling. Since QIRI collects data via a census for both its survey and administrative portions, another measure had to be developed to evaluate the accuracy of the estimates.

The QIRI quality indicators measure the accuracy of the estimates using three criteria: (i) the combined reported rate of the survey and administrative data portions, (ii) the coefficient of variation due to imputation for the survey portion and (iii) the revision rate.

The reported rate represents the proportion of data obtained directly from the respondents. The coefficient of variation due to imputation is a measure of variability of the imputed data caused by the imputation methods, historical imputation with a trend and ratio imputation. A low coefficient of variation means that the imputation is of good quality and compensates for a lower response rate. Finally, the revision rate is used as a measure of the stability of the estimates. This includes many effects, including some that are out of the control of the QIRI program, such as changes to the business frame and revisions to the GST data.

For each estimate, a score from 1 to 10 (10 representing the best quality) is given for each criterion. The three criteria scores are then combined to produce a final score, using different weights as all criteria do not have the same importance. The response rate is the most important criterion. The final score obtained is then translated into a letter, A (excellent), B (very good), C (good), D (acceptable), E (use with caution) or F (poor).
The data quality indicators are published alongside their corresponding data points on CANSIM.

Documentation

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: