Quarterly Trucking Survey (QTS)
Detailed information for fourth quarter 2011
The purpose of this survey is to collect the financial data needed to estimate value-added for the trucking industry and to analyze its impact on the Canadian economy.
Data release - April 3, 2012 (This is the final quarter for which data are available. The Quarterly Trucking Survey has been discontinued.)
- Questionnaire(s) and reporting guide(s)
- Data sources and methodology
- Data accuracy
The Quarterly Trucking Survey (QTS) is a redesigned version of the former Quarterly Motor Carriers of Freight (QMCF) survey. The survey is the only source of sub-annual information on the financial performance of the trucking industry in Canada. The survey results are used as inputs to the Canadian System of National Accounts. Federal and provincial governments use the data to formulate policies and to monitor the trucking industry in Canada. Trucking companies and associations use the published statistics for benchmarking purposes.
The Quarterly Trucking Survey (QTS) is the first component of the redesigned trucking financial surveys. It is complemented by an annual survey, the Annual Trucking Survey (ATS), which replaces the annual supplement of QMCF, namely the Annual Motor Carriers of Freight survey, and the Annual Survey of Small For-Hire Carriers of Freight and Owner-Operators.
Reference period: Quarter 1: January to March, Quarter 2: April to June, Quarter 3: July to September, Quarter 4: October to December.
Collection period: 1 week before the end of the quarter, for a period of 9 weeks.
- Transportation by road
Data sources and methodology
The survey covers all businesses located in Canada with at least one establishment classified to "Truck Transportation" according to the North American Industrial Classification System (484 - Truck Transportation (NAICS 2007)) provided that the annual revenue from the trucking establishments is $30,000 or more.
The questionnaire for this survey has been completely redesigned starting with the first quarter of 2009. By design, the QTS questionnaire is short and focuses on the main financial variables such as the total operating revenue and total operating expenses.
Two types of questionnaire are used for the QTS survey collection: a long and a short form. While the format and most of content of the two questionnaire types are the same, the long form includes an additional question related to a provincial distribution. The short form is used for companies that have all their trucking establishments in a single province (about 95% of the sample) and the long form is used for companies that have trucking establishments in more than one province (about 5% of the sample).
This is a sample survey with a cross-sectional design.
The target population for the survey consists of companies that have at least one establishment classified as truck transportation (NAICS 484) and which have annual trucking revenues of $30,000 or more.
The companies (or clusters of establishments) are first grouped (stratified) by cell (industry group by province/territory). Special reporting arrangement units and companies having establishments in more than one province are flagged as must-take units and are assigned to the must-take stratum within each cell. Also, the smallest units from each cell, representing, in aggregate, 5% of the total estimated annual revenue for that cell are assigned to the take-none stratum within that cell. For the remainder of the units residing on the target frame, stratification boundaries are determined based on cell-level target coefficients of variation (CVs) to sub-stratify each cell by size.
The size classes consist of ranges applied to the measure of size, which is based on estimated annual trucking revenue derived from tax data. For reasons of efficiency, there are five size classes (strata): one must-take stratum, one take-all and/or large take-some, two take-some and one take-none stratum per province and NAICS group.
The sample allocation is then determined using the Generalized Sampling System (GSAM), by province, type of activity (NAICS group) and size class.
Each version of the sample design is planned to last two years (8 quarters) with the exception of the first cycle that has a lifespan of three years (12 quarters).
The sample is updated each quarter, to introduce births into the sample and remain representative of the changing survey population.
Starting at year 2 (Quarter 5) of the first cycle, sample rotation will be introduced in order to reduce response burden. This rotation will be performed on the take-some strata at the rate of 1/8th of the take-some sample being rotated in/out each quarter.
Consequently, while companies in the take-all category will stay in the sample continuously for the three-year period, companies in the take-some segment should rotate out sometime during Year 2 or 3.
At the end of the three-year period, namely when the next cycle of the survey design begins, the frame will be refreshed, the stratification and allocation parameters will be redone and a new sample will be selected and surveyed.
Responding to this survey is mandatory.
Data are collected directly from survey respondents.
Companies selected are pre-contacted by telephone when they first appear in the sample. In addition to reviewing their contact information, the status of their business and their activity codes, the respondents are asked to answer a few questions related to business type.
At the end of each quarter, a QTS questionnaire is sent to each sampled company. The data are collected by mail-out/mail-back, with telephone and fax follow-up. The survey data are captured by using an imaging application (KFI or key from image) and checked for errors and inconsistencies. If required, inconsistent, questionable or missing data are referred back to the respondent for clarification or revision.
View the Questionnaire(s) and reporting guide(s).
The survey data are captured and checked for errors and inconsistencies. If required, inconsistent, questionable or missing data are referred back to the respondent for clarification or revision. Editing is done with the use of the generalized edit and imputation system, Banff.
Fields requiring imputation are imputed using the generalized edit and imputation system (Banff). The system imputes the data using different imputation methods and taking into account criteria such as the size and the activity (NAICS) of the carriers, as well as the type of data to be imputed.
Since only a sample of carriers is contacted, the individual values are weighted to make inferences for the surveyed population. However, the initial design weights of the respondents are adjusted i) to compensate for complete non response, ii) to reflect the contribution of the take-none portion in terms of counts and revenue and iii) calibrated based on auxiliary information available for all units on the frame. Domain estimates and coefficients of variation (CVs) are obtained using the estimation software StatMx.
The survey results are analyzed before dissemination. In general this includes a detailed review of the individual responses (especially for the largest enterprises), a review of general economic conditions as well as historic trends and comparisons with industry averages and ratios.
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
Quarterly estimates are provided for the most current quarter available. The data may be revised if necessary.
While considerable effort is made to ensure high standards throughout all stages of collection and processing, the resulting estimates are inevitably subject to a certain degree of error. These errors can be broken down into two major types: non-sampling and sampling.
Non-sampling error is not related to sampling and may occur for many reasons. For example, non-response is an important source of non-sampling error. Population coverage, differences in the interpretation of questions, incorrect information from respondents, and mistakes in recording, coding and processing data are other examples of non-sampling errors.
Non-sampling errors are controlled through a careful design of the questionnaire, the use of a minimal number of simple concepts and consistency checks. Coverage error is minimized by using multiple sources to update the frame. Measures such as response rates are used as indicators of the possible extent of non-sampling errors.
A weighted response rate is provided in Table 1 (see the link below). This rate represents the proportion of the revenue of the target population accounted for by units that responded to the survey. The higher the weighted response rate is, the more representative of the population is the published estimate.
Sampling error occurs because population estimates are derived from a sample of the population rather than the entire population. Sampling error depends on factors such as sample size, sampling design, and the method of estimation. An important property of probability sampling is that sampling error can be computed from the sample itself by using a statistical measure called the coefficient of variation (CV). The assumption is that over repeated surveys, the relative difference between a sample estimate and the estimate that would have been obtained from an enumeration of all units in the universe would be less than twice the CV, 95 times out of 100. The range of acceptable data values yielded by a sample is called a confidence interval. Confidence intervals can be constructed around the estimate using the CV. First, we calculate the standard error by multiplying the sample estimate by the CV. The sample estimate plus or minus twice the standard error is then referred to as a 95% confidence interval.
CVs were calculated for each estimate. A coefficient of variation (CV) for total operating revenue at the Canada level is presented in Table 1 (see the link below). CV's for other estimates may be obtained from the Transportation Division upon request. Note that the provided CV estimates do not consider the fact that some of the data were imputed and thus may underestimate the true CV's. The CV and the relative imputation rate should be considered simultaneously to make an assessment of the reliability of an estimate.
The qualities of CVs are rated as follows:
. Excellent 0.01% to 4.99%
. Very good 5.00% to 9.99%
. Good 10.00% to 14.99%
. Acceptable 15.00% to 24.99%
. Use with caution 25.00% to 34.99%
. Unreliable 35.00% or higher
- Quarterly Trucking Survey : Table 1 (fourth quarter 2011)