Proposal for a composite index of alcohol problems.

This study proposes constructing a composite index to measure the severity of alcohol problems in Canada. Composite summary indicators are used in many areas, particularly in economics where the Consumer Price Index is well known. The composite indexes developed for this analysis were constructed using the index number method. The indexes were based on the statistical series for alcohol consumption, alcohol morbidity, alcohol mortality and alcohol-related traffic offences in the ten provinces and cover the years 1975, 1980, 1985 and 1990. The selected statistical series were compared using both Spearman and the Pearson correlations. In addition, Kendall's coefficient of concordance was used to determine the degree of association among all the statistical series together. The initial results indicated that there were different provincial rankings for each of the four statistical series, demonstrating that in comparing provinces the ranking of the "alcohol problem" depends on the statistical series selected. The construction of a composite index can be an effective strategy for resolving these differences in the rankings. Provincial rankings for the composite indexes on the severity of alcohol problems were fairly consistent for each time period. In terms of general trends among the provinces, Prince Edward Island, Alberta, British Columbia and Saskatchewan had the highest composite indexes; Manitoba, Nova Scotia and Ontario the mid-range; and New Brunswick, Newfoundland and Quebec the lowest.