Tobacco Vendor Compliance Survey - Data Sources

Data Source

The Leeds, Grenville and Lanark District Health Unit conducted the survey in Octorber 1998. The purpose of the survey was to determine the level of compliance among vendors with the Tobacco Control Act. Overall, 81 Leeds, Grenville and Lanark County premises who sold tobacco products were surveyed.

Data Limitations

The estimates in this report are based upon a sample of tobacco vendors in Leeds, Grenville and Lanark. Two types of survey errors can affect the quality of estimates: sampling and non-sampling error.

The sampling error of an estimate refers to the difference attributable to using a sample of the population as opposed to a complete census. This error can make the sample unrepresentative of the population. To lessen the impact of sampling error, it is important to have a large enough sample and to sample using a simple random method. The survey sample was of sufficient size to make statements about the total population of vendors and a stratified random sampling method was utilized to ensure all regional subgroups were equally represented

Non-sampling errors can occur at almost every phase of a survey operation. The major non-sampling error in this survey, which may affect the results, is the use of a defective sampling frame. Some surveyed premises no longer sold cigarettes. Also, there may be newly opened tobacco vendors in the county, which did not have an equal chance of selection for the survey. The very best sampling frame is one in which every member of the target population is listed once and only once. Such a list allows us to select a random sample without worrying whether we over or under sampled any particular group.