Statistical issues in long-term followup studies.

Abstract

The thesis of this article is that since followup studies of patients with schizophrenia have provided a rich body of informative knowledge, emphasis should now be on hypothesis testing in future studies. The consumer of research needs to have a general appreciation of statistical thinking, design, and methods to make an informed synthesis of results presented. This article presents a brief discussion of relevant statistics and statistical issues, as free of jargon as possible. Given the multivariable nature of psychiatric research, the natural focus is on multivariate statistics. A strong background in statistics is not required to understand the methods described and how and why they might be applied. Reference material for more detailed discussions is provided. It is a truism to say that the highest quality scientific work is dependent on an intimate collaboration with the expert in statistics and the expert in clinical methods, and this merits repeating only because it is so often ignored.