Applied Longitudinal Data Analysis for Medical Science
A Practical Guide

Discusses methods available for longitudinal data analysis in non-technical language, allowing readers to apply techniques to their work.

Jos W. R. Twisk (Author)

9781009288033, Cambridge University Press

Paperback / softback, published 27 April 2023

300 pages
25.4 x 17.8 x 1.4 cm, 0.479 kg

Essential for non-statisticians and researchers working with longitudinal data from medical studies, this updated new edition discusses the most important techniques available for analysing data of this type. Using non-technical language, the book explores simple methods such as the paired t-test and summary statistics as well as more sophisticated regression-based methods, including mixed model analysis. The emphasis of the discussion lies in the interpretation of the results of these different methods, covering data analysis with continuous, dichotomous, categorical and other outcome variables. Datasets used throughout the book are provided, enabling readers to re-analyse the examples as they make their way through chapters and improve their understanding of the material. Finally, an extensive and practical overview of, and comparison between, different software packages is provided. Readers will be able to use this book as a practical manual in their everyday work without needing a strong background in statistics.

1. Introduction
2. Continuous outcome variables
3. Continuous outcome variables – regression based methods
4. The modelling of time
5. Models to disentangle the between- and within-subjects relationship
6. Causality in observational longitudinal studies
7. Dichotomous outcome variables
8. Categorical and count outcome variables
9. Outcome variables with floor or ceiling effects
10. Analysis of longitudinal intervention studies
11. Missing data in longitudinal studies
12. Sample size calculations
13. Software for longitudinal data analysis.

Subject Areas: Epidemiology & medical statistics [MBNS]