Variable-oriented and person-oriented perspectives of analysis: the example of alcohol consumption in adolescence.

This article presents person-oriented and variable-oriented approaches to data analysis. To illustrate these two approaches and the types of information they provide the researcher, data from 3,558 control group youth from the National Cross-Site Evaluation of High Risk Youth Programs were analysed. The relationship, over time, between parent attitudes and gender as it relates to youth alcohol consumption were examined. Data were analysed and compared using a variable-oriented approach (repeated measures ANOVA) and a person-oriented approach (Configural Frequency Analysis). Data analysis demonstrated that variable- and person-oriented approaches provide the researcher with different information that can be complementary. The ANOVA identified an overall trend that accounted for little variance; the CFA explained why this was the case by identifying groups of respondents whose behaviour was different from the overall trend. The implications of these results and the use of both types of approaches are discussed.