Latent Class Models to Describe Changes Over Time: A Case Study
By means of a case study we describe the statistical analysis of repeated measures as they may be found in a typical quality-of-life trial that studies the effect of some intervention on quality-of-life. We will show that latent class models are a very useful to tool to discover patterns in the follow-up data. Once the patterns have been found, data-driven summary statistics can be defined that are more useful than simple pre-defined measures of response.
KeywordsPain Score Principal Curve Multivariate Normal Distribution Latent Class Model Intermediate Response
Unable to display preview. Download preview PDF.
- Little, R.J.A. and Rubin, D.B. (1987). Statistical Analysis with Missing Data, New York: Wiley.Google Scholar
- McLachlan, G.F. and Krishnan, H. (1997). The EM Algorithm and Extensions, New York:Wiley.Google Scholar
- Meng, X.-L. and Van Dyk, D. (1997). The EM algorithm-an old folk-song sung to a fast new tune. Journal of the Royal Statistical Society Series B 58, 511–567.Google Scholar
- Steenland, E., Leer, J., van Houwelingen, H., Post, W.J., van den Hout, W.B., Kievit, J., de Haes, H., Martijn, H., Oei, B., Vonk, E., van der Steen-Banasik, E., Wiggenraad, R.G.J., Hoogenhout, J., Warlam-Rodenhuis, C., van Tienhoven, G., Wanders, R., Pomp, J., van Reijn, M., Mierlo, T. and Rutten, E. (1999). The effect of a single fraction compared to multiple fractions on painful bone metastases: a global analysis of the Dutch Bone Metastasis Study. Radiotherapy and Oncology 52, 101–109.PubMedCrossRefGoogle Scholar