Methodology

General Social Survey on Victimization
Sampling
Data limitations
Aggregate Uniform Crime Reporting Survey

General Social Survey on Victimization

In 2004, Statistics Canada conducted the victimization cycle of the General Social Survey for the fourth time. Previous cycles were conducted in 1988, 1993 and 1999. The objectives of the survey are to provide estimates of the extent to which people experience incidences of eight offence types, examining risk factors associated with victimization, reporting rates to police, and measures fear of crime and public perceptions of crime and the criminal justice system.

Top of Page

Sampling

The 2004 GSS on victimization had a sample size of 24,000 households in the provinces that were selected using Random Digit Dialing (RDD). Once a household was chosen, an individual 15 years or older was selected randomly to respond to the survey. The use of telephones for sample selection and data collection means that the 2004 GSS sample in the provinces only covers the 96% of the population that had telephone service.

The 2004 GSS also included a test collection of telephone survey data in the northern territories. In an attempt to improve the coverage of the survey, the sample of 1,300 households was selected from the respondents to the 2003 Canada Community Health Survey rather than using RDD. It is estimated that a sample Selected and interviewed this way in the North only covers 60% of the population of the territories.

Top of Page

Data limitations

The 2004 GSS on victimization was conducted in Yukon, Northwest Territories and Nunavut as part of a pilot test. Compared to other areas in Canada, collection in the territories poses additional challenges, due to higher rates of incomplete telephone service and language difficulties. As a result, sampling and data collection are more difficult in the territories. The 2004 victimization data from the territories produce estimates with known biases and may include unknown biases. For example, the sample over-estimates the population with English as a household language and under-estimates the Aboriginal population whose mother tongue is not English. Between slippage and non-response, only 60% of the northern population is represented in the GSS-18 northern sample. It is unknown whether the other 40% are similar with respect to all characteristics. As a result the data contained in these files should be used with caution.

This profileuses the coefficient of variation (CV) as a measure of the sampling error. Any estimate that has a high CV (over 33.3%) has not been published because the estimate is too unreliable. An estimate that has a CV between 16.6 and 33.3 should be used with caution and the symbol ‘E’ is used.

When comparing estimates for significant differences, we test the hypothesis that the difference between two estimates is zero. We construct a 95% confidence interval around this difference and if this interval contains zero, then we conclude that the difference is not significant. If, however, this confidence interval does not contain zero, then we conclude that there is a significant difference between the two estimates.

Top of Page

Aggregate Uniform Crime Reporting Survey

The aggregate UCR survey records the number of incidents reported to the police. It includes the number of reported offences, actual offences, offences cleared by charge or cleared otherwise, persons charged (by sex and by an adult/youth breakdown) and those not charged. It does not include victim characteristics.

The aggregate UCR survey classifies incidents according to the most serious offence in the incident (generally the offence that carries the longest maximum sentence under the Criminal Code). In categorizing incidents, violent offences always take precedence over non-violent offences. As a result, less serious offences are under-represented by the UCR survey.

The aggregate UCR survey scores violent incidents (except robbery) differently from other types of crime. For violent crime, a separate incident is recorded for each victim (i.e. if one person assaults three people, then three incidents are recorded; but if three people assault one person, only one incident is recorded). Robbery, however, is counted as if it were a non-violent crime in order to avoid inflating the number of victims (e.g. for a bank robbery, counting everyone present in the bank would result in an over-counting of robbery incidents). For non-violent crimes, one incident (categorized according to the most serious offence) is counted for every distinct or separate occurrence.