The problems of analysing changes in longitudinal and treatment studies An introductory guide
- 1 January 1991
- journal article
- research article
- Published by Taylor & Francis in Nordisk Psykiatrisk Tidsskrift
- Vol. 45 (3), 215-226
- https://doi.org/10.3109/08039489109103289
Abstract
This paper aims to introduce the clinical researcher to the issues that arise in the analysis of behavioural changes within longitudinal studies. Treatment trials are considered as a special case of longitudinal study requiring the statistical analysis of repeated measurement. The value of analysis of covariance in testing for significance of differences in changes is emphasized. The use of conditional approaches based on logit analysis is illustrated for change in binary measures. (The application of some of these techniques is illustrated by reference to Elkin et al. Archives of General Psychiatry 1989; 46: 971-82.)Keywords
This publication has 8 references indexed in Scilit:
- Analysis of serial measurements in medical research.BMJ, 1990
- National Institute of Mental Health Treatment of Depression Collaborative Research ProgramArchives of General Psychiatry, 1989
- An analysis of the re-test artefact in longitudinal studies of psychiatric symptoms and personalityPsychological Medicine, 1989
- Multivariate Statistics. IV. Statistical Issues in Identifying Vulnerability and Protective Factors Log-Linear AnalysisNordisk Psykiatrisk Tidsskrift, 1989
- Multivariate Statistics. II. Using Different Types of Multivariate Statistics to Identify Types of Psychopathology Cluster Analysis and Multidimensional ScalingNordisk Psykiatrisk Tidsskrift, 1989
- Simultaneous Statistical InferencePublished by Springer Nature ,1981
- The Analysis of Contingency TablesPublished by Springer Nature ,1977
- A paradox in the interpretation of group comparisons.Psychological Bulletin, 1967