Residential Telephone Service Survey (RTSS)
Detailed information for December 2006
The objectives of this survey are to collect information on telephone penetration rates across Canada and to collect information on non-subscriber characteristics.
Data release - May 4, 2007
- Questionnaire(s) and reporting guide(s)
- Data sources and methodology
- Data accuracy
The Residential Telephone Service Survey (RTSS) has been conducted since the fall of 1996. The RTSS monitors residential phone penetration rates. Initially, the survey was sponsored by Bell Canada to assess reasons why certain households did not have telephone service. Later, with the increased popularity of cellular phones, the focus of the survey switched to the types of telephone service used by households. Survey results will be used by statisticians to calculate chances of reaching households by telephone.
Collection period: The collection period is the Labour Force Survey (LFS) interview week, usually the third week of the month.
- Information and communications technology
- Telecommunication industries
Data sources and methodology
All households in Canada with the following two exceptions:
1) households located in the Yukon, Northwest Territories and Nunavut, and
2) households located on Indian Reserves.
This short and simple questionnaire was designed by the project team. It asks respondents for the total number of different telephone numbers for their residence including cell phone numbers and those used for business. It asks if all of the reported numbers are for cell phones only and asks for confirmation if they report to having cell phones only. If they report having no phone lines the questionnaire goes on to determine the reasons for not having a phone and if the respondent has alternative access to a phone in case of emergency. Finally, everyone is asked if their total annual household income is more or less than the low income cut-off value for their geographic area.
The questionnaire has remained the same since the start of the survey in 1997, except for the addition of the cell phone only question in May 2002 and the follow-up confirmation of having cell phone(s) only in May 2003.
In 2006, the first major change to the survey questionnaire was made since the start of the survey in 1996. The questionnaire was modified to reflect the changing telephone service market. The questionnaire includes information on the various types of phone service provided (land-line, cellular, cable and Voice over IP (VoIP)), and the number of personal and business telephone numbers associated with the household. In 2006 only, respondents were also asked about the reasons for not having land-line phone service and the use of a cellular phone during periods without land-line telephone service.
This is a sample survey with a cross-sectional design.
The Residential Telephone Service Survey (RTSS) used five of the six rotations groups in the December 2006 Labour Force Survey (LFS) sample. For the RTSS, the coverage of the LFS was set at the household level. However, unlike the LFS where information is collected for all eligible household members, the RTSS only collected information from one household member who reported about the household.
Data collection for this reference period: 2006-12-10 to 2006-12-18
Responding to this survey is voluntary.
Data are collected directly from survey respondents.
Information for the Residential Telephone Service Survey is obtained from a knowledgeable household member. Upon completion of the Labour Force Survey interview, the interviewer introduces the RTSS and proceeds with the interview with the respondent's permission.
View the Questionnaire(s) and reporting guide(s) .
The first type of error treated was errors in questionnaire flow, where questions which did not apply to the respondent (and should therefore not have been answered) were found to contain answers. In this case a computer edit automatically eliminated superfluous data by following the flow of the questionnaire implied by answers to previous, and in some cases, subsequent questions.
The second type of error treated involved a lack of information in questions which should have been answered. For this type of error, a non-response or "not-stated" code was assigned to the item.
During processing of the December 2006 RTSS, it was discovered that there was an error in the way question RTS_Q12 was implemented in the field. This resulted in 17,178 respondents providing invalid responses for their total household income. These responses were automatically imputed from valid responses collected for the survey using a logistic regression technique developed in SAS to provide a more reliable estimate of total household income levels.
Overall, 43.9% of responses to RTS_Q12 are imputed. When the model was tested using valid survey responses it accurately estimated the correct value of RTS_Q12 for 84.7% of records. The model misclassified 8.7% of records as having a value of 2 (household income above the LICO) and 6.7% of records as having a value of 1 (household income below the LICO).
The principles behind the calculation of the weights for the Residential Telephone Service Survey are nearly identical to those for the LFS. However, this survey is a household-weighted survey, not a person-weighted survey. Also, further adjustments are made to the LFS sub-weights in order to derive a final weight for the individual records on the Residential Telephone Service Survey microdata file.
1) An adjustment to account for the use of a five-sixths sub-sample, instead of the full LFS sample.
2) An adjustment to account for the additional non-response to the supplementary survey, i.e., non-response to the Residential Telephone Service Survey for individuals who did respond to the LFS or for which the previous month's LFS data was brought forward. An analysis was undertaken to determine homogeneous non-response groupings. The groups were defined within the design (old versus new) and accounted for such things as household size, number of attempts to contact the household, whether the interview was done by proxy and other demographic and geographic variables.
3) The final adjustment ensured that estimates produced for a province-household size group would agree with the known population totals for that province-household size group. The adjustments were made for household size groupings of one person, two people and three or more people.
A comparison with results of previous cycles and with other surveys is done.
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.
It should be noted that the 'Public Use' microdata files differ in a number of important respects from the survey 'master' files held by Statistics Canada. These differences are the result of actions taken to protect the anonymity of individual survey respondents. Confidentiality is ensured by suppressing and collapsing variables that may be used to identify individuals.
Revisions and seasonal adjustment
This methodology type does not apply to this survey.
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-response is an important source of non-sampling error. The household response rate for the Residential Telephone Service Survey, December 2006 was 90.2%.
The basis for measuring the potential size of sampling errors is the standard error of the estimates derived from survey results. Because of the large variety of estimates that can be produced from a survey, the standard error of an estimate is usually expressed relative to the estimate to which it pertains. This resulting measure, known as the coefficient of variation (CV) of an estimate, is obtained by dividing the standard error of the estimate by the estimate itself and is expressed as a percentage of the estimate.
The coefficients of variation for the main estimates at the Canada level expressed as a percentage are as follows:
One or more telephone numbers: 0.1%
No phone: 5.9%
No land-line phone service: 2.3%
Cannot afford land-line phone service: 5.1%
Penetration rate: 0.1%
No phone: 5.9%
Cannot afford land-line phone service: 4.5%
Please refer to the Microdata User Guide for detailed information.
- Residential Telephone Service Survey - Microdata User Guide (December 2006)