Design, methodological and statistical issues in prediction research of neuroleptic response
Inclusion and exclusion criteria definition and stratification are instruments for using prognostic factors in the design of clinical studies. In the evaluation phase logistic regression, Cox regression and CART-analysis are highly valuable multivariate methods for detecting prognostic factors.
KeywordsStatistical Issue Prodromal Symptom Intermittent Therapy Neuroleptic Treatment Social Scale
Unable to display preview. Download preview PDF.
- Breiman L, Friedman JH, Olshen RA, Stone CJ (1984) Classification and regression trees (CART). Wadsworth, Monterey.Google Scholar
- Cox DR (1972) Regression models and life tables. J Roy Stat Soc 34: 187–220.Google Scholar
- Gaebel W, Köpcke W, Linden M, Müller P, Müller-Spahn F, Pietzcker A, Tegeler J (1994) Prediction of neuroleptic response in the ANI-schizophrenia study (under publication).Google Scholar
- Hosmer DW, Lemeshow S (1989) Applied logistic regression. John Wiley, New York.Google Scholar
- Mantel N (1963) Chi-Square tests with one degree of freedom: extensions of the Mantel-Haenszel procedure. J Am Stat Assoc 58: 690–700.Google Scholar
- Schlesselman JJ (1982) Case-control-studies-design, conduct, analysis. Oxford University Press, New York.Google Scholar
- Sonquist JA (1970) Multivariate model building. Institute for Social Research, University of Michigan, Ann Arbor.Google Scholar
- Spilker B (1991) Guide to clinical trials. Raven Press, New York.Google Scholar