Canadian Vehicle Survey (CVS)

Detailed information for third quarter 2002

The Canadian Vehicle Survey (CVS) provides quarterly and annual estimates of the amount of road vehicle activity by vehicle-kilometers and passenger-kilometers.

Data release - February 21, 2003

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

Description

The Canadian Vehicle Survey (CVS) provides quarterly and annual estimates of the amount of road vehicle activity by vehicle-kilometers and passenger-kilometers. Road vehicles dominate passenger travel and freight traffic (about 90% of all travel in Canada is by road).

The Canadian Vehicle Survey was developed at the request of Transport Canada. The results are the prime source of road vehicle use information for researchers and interested members of the public.

Statistical activity

This statistical activity is part of a set of surveys measuring various aspects of activities related to the movement of people and goods. These surveys are grouped as follows:

Transportation by air includes records related to the movement of aircraft, passengers and cargo by air for both Canadian and foreign air carriers operating in Canada as well as the financial and operating characteristics of Canadian air carriers. These data are produced by the Aviation Statistics Centre.

Transportation by rail includes records relating to rail transportation in Canada, and between the United States and Canada.

Transportation by road includes records relating to all road transport in Canada. In addition to surveying carriers and owners of registered motor vehicles, certain programs rely on aggregation of provincial and territorial administrative records.

Reference period: Quarter

Collection period: Reference quarter

Subjects

• Transportation
• Transportation by road

Data sources and methodology

Target population

The in-scope vehicles for the CVS include all motor vehicles except motorcycles, off road vehicles (e.g., snowmobiles, dune buggies, amphibious vehicles) and special equipment (e.g., cranes, street cleaners, snowplows and backhoes) registered in Canada anytime during the survey reference period that have not been scrapped or salvaged.

The population of interest consists of vehicle-days composed from the in-scope vehicles and the days within the survey reference period.

Instrument design

Each survey instrument (trip log) was first tested in a focus group and then in a pilot study.

Sampling

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

All in-scope vehicles are stratified into four vehicle types, 13 jurisdictions and two vehicle-age strata of newer and older vehicles.

A sample of vehicles from each stratum (first stage sample) is then selected.

Subsequently, seven consecutive days starting within the quarter are randomly assigned (second stage) to each vehicle selected at the first stage. Within each stratum, the first reporting day is evenly spread over the quarter to ensure a uniform number of responses over time and for each day of the week. This step is not applied to the vehicles registered in the three territories since only odometer readings are collected.

Since the sample is selected in two stages, the sampling weight is also calculated in two steps. The first-stage sampling weight is calculated for each vehicle in the first-stage sample. Then the second-stage sampling weight is calculated for each vehicle-day selected from all days within the reference period. Finally, these two weights are multiplied together to obtain the final weight for a vehicle-day. The weighted values are obtained by multiplying the final weights and the collected values.

Data sources

Data collection for this reference period: July to September 2002

Responding to this survey is voluntary.

Data are collected directly from survey respondents.

The vehicles sampled for the survey are randomly selected from all registered on road vehicles in Canada and includes cars, vans, trucks, buses, etc. Respondents are telephoned (CATI) and asked questions related to the selected vehicle and their usage of that vehicle. If the respondent agrees to complete a trip log, personal information such as name and address are verified in order to mail out a seven day trip log for the vehicle.

If the respondent can not be contacted by phone, a trip log with a short supplement (to collect some of the information normally collected during the interview) is mailed out.

There are three types of logs depending on the type of vehicle: a light log (for passenger vehicles), a bus log, a truck log for vehicles weighting more than 4,500 kg. In all cases, the respondents are requested to record all the trips made in the selected vehicle over a specified seven day period.

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

Error detection

Once all necessary information for the survey is collected, a series of verifications takes place to ensure that the records are consistent and that collection and capture of the data do not introduce errors. Reported data are examined for completeness and consistency using automated edits coupled with manual review. Outliers, i.e., respondents reporting extremely large values, are processed manually.

Imputation

Once all necessary information for the survey was collected, a series of verifications took place to ensure that the records were consistent and that collection and capture of the data did not introduce errors. Reported data were examined for completeness and consistency using automated edits coupled with manual review. Outliers, i.e., respondents reporting extremely large values, were processed manually.

Missing values and data found in error were imputed by another automated system. The system imputed the data using different imputation rules depending on the vehicle, available information and the type of data to be imputed. For example, the data can be imputed based on other responses for the same vehicle or by using data from a similar vehicle. The imputed data were then again examined for completeness and consistency.

A complete description of the procedures applied to the survey data is available upon request from the Transportation Division of Statistics Canada.

Estimation

Since the survey population differs from the population of interest, several corrections are done to assure that the estimates correspond (as closely as possible) to the population of interest. The sampling weights derived from the sample design are adjusted and improved using updated registration lists. This was possible because, during the passage of time since the sample is selected, a set of prepared vehicle lists is obtained for the beginning and for the end of the reference quarter. To improve the estimates for the vehicles registered in the ten provinces: all the days are further stratified into working days and holidays (or non-working days, including weekends). Second stage sampling weights are adjusted so that every day of vehicle activity within the same stratum contributed with equal weight to the total estimate. The final set of weights reflects as closely as possible the characteristics of the vehicle population during the reference period.

Quality evaluation

The aggregated survey results are analyzed before dissemination. In general, this includes a review of general economic conditions as well as historic trends and comparisons with other data sources.

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

Quarterly estimates are provided for the most current quarter available. The data for the previous quarter are revised if necessary. Seasonal adjustments are not made to the data.

Data accuracy

While considerable effort is put forth to ensure that a high standard is maintained throughout all survey operations, the resulting estimates are inevitably subject to a certain degree of error. The total survey error is defined as the difference between the survey estimate and the true value for the population, at which the survey estimate aims. The total survey error consists of two types of errors: sampling and non-sampling errors.

Sampling error

The sampling error is measured by a statistical quantity called the standard error. This quantity reflects the expected variability of the survey estimate of a particular population characteristic if repeated sampling is carried out. The true value of the standard error is, of course, not known but can be estimated from the sample. The estimated standard error is used in terms of a relative measure called the coefficient of variation (or CV). This measure is simply the estimated standard error expressed as a percentage of the value of the survey estimate. Therefore, a smaller CV indicates better reliability of the estimate.

Non-sampling errors

The sampling error is only one component of the total survey error. All other errors arising from all phases of a survey are called non-sampling errors. This type of error can arise when a respondent provides incorrect information or does not answer certain questions, when a unit in the population of interest is omitted or covered more than once, when a unit that is out-of-scope for the survey is included by mistake or when errors occur in data processing, such as coding and capture errors.

In general, non-sampling errors are difficult to quantify. However, certain measures such as response rates can be used as indicators of the non-sampling errors.

Based on quality indicators, the estimates are judged generally of sufficient quality at the national level; the provincial estimates are of a lesser quality in most cases.

• Additional documentation