On the use of some multivariate statistical methods in pharmacological research

Using an interaction experiment with apomorphine and scopolamine effects on exploratory behavior as an illustrative example, four multivariate statistical methods are described and compared with univariate statistical methods, with respect to their utility in pharmacological research. The utility of multivariate analysis of variance and Hotelling's T2 test is compared with univariate analysis of variance and Student's t-test. A novel use of principal component analysis is reported. This latter method transfers knowledge about the dose-response pattern of an agonist to subsequent interaction experiments involving the agonist and putative antagonists. The procedure considerably increases the sensitivity of the statistical analysis and reduces the risk for spurious results (statistical type I errors). Finally, some possibilities of a recently developed method for modeling with latent variables, the partial least squares method, are explored. It is demonstrated by the example how the interaction between apomorphine and scopolamine can be decomposed into one apomorphine-related pattern unaffected by scopolamine, one scopolamine-related pattern sensitive to apomorphine, and one interaction pattern. The similarities and differences between principal components and partial least squares analyses are also discussed.