Interpretation of research data: other multivariate methods

Four techniques of multivariate data analysis are described: discriminant analysis, factor analysis, cluster analysis, and multidimensional scaling. Objectives and applications, data requirements, mechanism of operation, methods of evaluation, and advantages and disadvantages of each method are covered. Multivariate methods are not substitutes for the researcher's use of proper study design. Investigators should try to avoid using a favorite or familiar technique across all research situations.