INTEGRATED APPROACH TO MEASURING ASSOCIATION.

This article present an approach to measure association such that a single basic logic is used regardless of the measurement level of the variables being associated. As data progress from nominal to ordinal to equal interval in mathematical character, association measures should simply incorporate the added properties into the format used at the lower levels. The logic is adapted to the types of measurement present in the independent and dependent variables so that a complete range of association measures is available. The approach requires little new at the interval-measurement level (dependent variable) and only modest modification of existing procedures for ordinal dependent variables. The two basic approaches to association measures appear to be assessing departure from randomness and determining extent of predictive accuracy. Departure from randomness is characteristic of the chi-squared based measures, which typically suffer from normalizing procedures that admit no easy operational interpretation.