Canadian Travel Survey (CTS)

Detailed information for second quarter 2004

Status:

Inactive

Frequency:

Quarterly

Record number:

3810

The Canadian Travel Survey (CTS) is a major source of data used to measure the size and status of Canada's tourism industry. It was developed to measure the volume, characteristics and economic impact of domestic travel. It gathers data on more than 30 variables, including socio-economic profiles, trip characteristics, and expenditures.

Data release - December 6, 2004

Description

The Canadian Travel Survey (CTS) is a major source of data used to measure the size and status of Canada's tourism industry. It was developed to measure the volume, characteristics and economic impact of domestic travel. It gathers data on more than 30 variables, including socio-economic profiles, trip characteristics, and expenditures.

The CTS is conducted by Statistics Canada, as a supplement of the Labour Force Survey (LFS: Survey Number 3701), with the cooperation and support of the Canadian Tourism Commission (CTC) and ten provincial governments. The main users of the survey data are the CTC, the provinces, and tourism boards. Other users include the media, businesses, consultants and researchers.

Collection period: CTS data are gathered monthly, from the Monday of the Labour Force Survey collection week to the Wednesday of the following week. Usually the reference week follows that including the 15th day of the month.

Subjects

  • Domestic travel
  • Travel and tourism

Data sources and methodology

Target population

The target population is the civilian, non-institutionalized population 15 years of age or more in Canada's 10 provinces. Excluded are: residents of the Yukon, Northwest Territories, Nunavut, persons living on Indian reserves, full-time members of the Canadian Armed Forces, and persons living in institutions. Together, these groups represent an exclusion of less than 3% of the Canadian population aged 15 and up.

Sampling

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

As the Canadian Travel Survey is administered to a sub-sample of households in the Labour Force Survey (LFS) sample, its sample design is closely related to that of the LFS. Apart from differences in sample size and the exclusion of the Yukon, LFS design features are reflected in the CTS. LFS non-response also carries over to the CTS, except where LFS interviews could not be conducted in the current reference month because of temporary circumstances but LFS data were gathered in an earlier month. The response rate for the LFS is 95% or more. For more information on the LFS sampling method, please consult the Labour Force Survey (Survey Id 3701).

For a few years now, the Canadian Travel Survey has used two of the LFS sample's six rotation groups, representing some 15,000 households per month. One member of each household is questioned about all travel completed during the reference month. CTS coverage is the same as that of the LFS, i.e. all household members aged 15 and up.

Overall, CTS response rates are approximately 90%. These rates correspond to the proportion of eligible respondents who have provided data. They are not cumulative, meaning they do not take account of individuals who would have been eligible for the CTS but did not take part in the LFS.

Data sources

Responding to this survey is voluntary.

Data are collected directly from survey respondents.

Since 1996, the Canadian Travel Survey has used computer-assisted interviewing (CAI). The questionnaire is completed with the help of a regular computer or laptop, and the interviewer enters the information directly into the computer. One of the advantages of CAI is that data can be edited on-line as they are gathered. This method also helps prevent the errors that might occur during the electronic transcription of hard-copy information.

At the end of 1999, the Survey operating system was modified in accordance with Y2K requirements, and went from a DOS system to a Windows environment. Given this change in application software, the CTS had to be rewritten, and BLAISE was the language chosen.

Over the course of 2000, other minor changes were made to the CTS data-collection process. Telephone interviews previously conducted over the phone by interviewers working at home on laptops are now made from seven regional offices on networked office computers. In exceptional circumstances, however (respondents without a telephone, changes to households, non-responses to the LFS during the first month and problem cases), interviews are still carried out by field staff.

At the start of 2002, a more systematic interviewer monitoring system was implemented in the regional offices. This is an automated system that enables supervisors to see the interviewer's screen remotely and hear the telephone conversation between the interviewer and the respondent. Increased monitoring of interviewers served to improve the collection of information from respondents and thereby enhance the quality of the data produced by the survey.

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

Error detection

Online editing is performed at the data-capture phase. CAI controls the sequence of questions in accordance with previous responses. Other checks are also made during the interview to reduce the number of errors attributable to typos and misunderstandings. For example, if the number of nights spent in various types of accommodation does not correspond to the total number of nights spent away from home, an edit message appears. The interviewer can then correct the mistake, and less editing has to be performed at head office.

Once data files from the regional offices have been downloaded to Special Surveys Division computers, data are edited in a series of iterations to detect errors and prepare files for subsequent weighting and expenditure imputation. At this step of preliminary editing, duplicate records are detected and some minor edits are performed.

Subsequent to geocoding, data undergo secondary editing, as described below.

Once linked, files are subject to further editing. Gross errors, such as variations in the number of nights spent away from home from one question to another, as well as sequencing errors, are reviewed and corrected.

This series of edits consists of more thorough validity checks to detect inconsistencies and outliers. This step occurs after origin and destination place names have been geocoded. Once again, errors are reviewed and corrected.

Imputation

Expenditure data are the only CTS data that are imputed. All other missing or erroneous values are either corrected or converted to a "not stated" code. However, these data must be complete so that aggregate estimates of expenditures can be produced.

Missing expenditure information is imputed based on the average expenditures of trips for which expenditure information has been reported. These "donor" trip expenditures are used to compute average expenditures, which are then used to impute the missing expenditure values.

Donor expenditure averages are calculated by type of trip, since expenditures vary considerably depending on trip characteristics. Averages are computed for trips with the following common characteristics: destination; duration (one overnight stay or more vs. same-day); number of people in party; reason for trip (business or other); type(s) of accommodation; and mode of transportation used.

There must be at least three donor records for each imputation category; if not, trip characteristics are collapsed to a less specific level, and a set of averages is calculated for this next level of trip type. If there are insufficient donors for this level, trip characteristics are collapsed further and another set of averages is computed. This process is repeated until all levels of collapsing have donor averages computed, using at least three records.

For example, the first level of imputation may involve trips of one or more nights to a Canadian destination, a party of two adults, hotel accommodation, travel by air and business as the reason for the trip. If insufficient numbers of donors are available at this level, then trip characteristics will be collapsed to include trips with any type of commercial accommodation; if sufficient donors are still not available, the characteristics will be collapsed to include trips made for any reason, and so on.

Once a set of donor averages has been computed for all levels of trip characteristics, trips requiring imputation are then matched to the averages for trips with the same characteristics, and the missing expenditures are calculated.

An additional step in the imputation process is the distribution of package-tour expenditures to specific expenditure categories. This is accomplished in the same fashion as expenditure imputation: donor averages are used to impute the expected value of the expenditure items included in the package; these imputed amounts are then ratio-adjusted to arrive at the total amount reported for the package deal.

Imputed expenditures are then re-edited to ensure that no outlier values have been created by the expenditure imputation process.

Estimation

CTS estimates are thus produced based on raw survey findings to which a weight is attributed, making it possible to inflate these data to agree with the Canadian non-institutionalized population 15 years and older. The weights calculated to produce CTS estimates are person, household-trip and person-trip weights. For more details on weighting and weight-use procedures, please consult chapters 6 and 7 of the Canadian Travel Survey Microdata User's Guide (Cat. No. 87M0006GPE).

Quality evaluation

Data quality is systematically evaluated every quarter. Statistical tables required for analysis are produced and compared with related data sources. A list of indicators is also established for use in determining whether general tourism trends reflect those of the CTS. Furthermore, we work in close cooperation with provincial tourism departments, which provide additional viewpoints and information sources, helping us evaluate data quality at a broader geographic level.

Disclosure control

Statistics Canada is prohibited by law from releasing any data which would divulge information obtained under the Statistics Act that relates to any identifiable person, business or organization without the prior knowledge or the consent in writing of that person, business or organization. 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.

Disclosure of results is very closely monitored, especially as regards microdata files. The smallest geographic level for which information is available to the public, as regards traveller and travel records, is that of the census division and census metropolitan area. Furthermore, socio-economic variables such as respondent's age and occupation have been deleted or recoded in order to eliminate any possibility of identification, and each official disclosure of microdata must be approved by the Micro Data Release Sub-Committee.

Data accuracy

Sampling variability is the error in the estimates caused by the fact that we survey a sample rather than the entire population. Standard error and the related concepts of coefficient of variation (CV) and confidence interval provide an indication of the magnitude of sampling variability. The standard error and coefficient of variation do not measure systematic biases in survey data that might affect estimates. Rather, they are based on the assumption that sampling errors follow a normal probability distribution.

Usually, the larger of the two estimates will have a smaller CV, and therefore be more reliable. Also, for two estimates of the same size, the one associated with a characteristic more evenly distributed throughout the population will tend to have a smaller CV.

Simply speaking, the CV is used to identify four major classes of data:

Approximate CV Dissemination Restriction

0.0 - 16.5 GOOD
16.6- 25.0 FAIR
25.1 - 33.3 POOR
33.4 or more VERY POOR

Data classified as "POOR" and "VERY POOR" are not contained in the CANSIM data bank. However, in the publication entitled Canadian Travel Survey (87-212-XPB or XIE), estimates classified as "POOR" appear with a warning.

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: