Statistics in medicine
-
Statistics in medicine · Oct 1997
ReviewUsing the general linear mixed model to analyse unbalanced repeated measures and longitudinal data.
The general linear mixed model provides a useful approach for analysing a wide variety of data structures which practising statisticians often encounter. Two such data structures which can be problematic to analyse are unbalanced repeated measures data and longitudinal data. Owing to recent advances in methods and software, the mixed model analysis is now readily available to data analysts. ⋯ The extra complexity involved is compensated for by the additional flexibility it provides in model fitting. The purpose of this tutorial is to provide readers with a sufficient introduction to the theory to understand the method and a more extensive discussion of model fitting and checking in order to provide guidelines for its use. We provide two detailed case studies, one a clinical trial with repeated measures and dropouts, and one an epidemiological survey with longitudinal follow-up.
-
Multi-centre databases are making an increasing contribution to medical understanding. While the statistical handling of randomized experimental studies is well documented in the medical literature, the analysis of observational studies requires the addressing of additional important issues relating to the timing of entry to the study and the effect of potential explanatory variables not introduced until after that time. A series of analyses is illustrated on a small data set. ⋯ The aim of each analysis, the choice of data used, the essentials of the methodology, the interpretation of the results and the limitations and underlying assumptions are discussed. It is emphasized that, in contrast to randomized studies, the basis for selection and timing of interventions in observational studies is not precisely specified so that attribution of a survival effect to an intervention must be tentative. A glossary of terms is provided.
-
Statistics in medicine · Jun 1996
ReviewThe role of external evidence in data monitoring of a clinical trial.
Data monitoring of interim results from a randomized clinical trial should take into consideration evidence from other trials. This article presents both scientific and practical issues regarding the pros and cons of formally incorporating such external evidence into the decision making process for the current trial. Guidelines on how to use other trials' data are presented, along with cautiously sceptical comments on the impracticality of using formal meta-analyses in data monitoring. The arguments are illustrated by recent examples from specific trials, and the article concludes with some general recommendations.
-
Statistics in medicine · Jun 1996
ReviewMeta-analysis and meta-analytic monitoring of clinical trials.
Randomized trials are effective and usually unbiased for showing the average results in a selected outcome variable for treatment A versus treatment B, and meta-analyses produce an average of these averages. The results of both the trials and meta-analyses are often pragmatically unsatisfactory, however, because they do not reflect cogent distinctions desired by practising clinicians in the heterogeneous subgroups formed by diverse components in the patients' baseline states, in proficiency of therapy, and in additional outcome phenomena. If the inadequacies of previous trials have led to performance of a suitable new trial, it should not be stopped by the numbers emerging from meta-analyses of prior non-pertinent results.
-
There has been a heightened awareness of the dangers of selection bias over the past two decades. Certainly coverage in statistical and 'statistics for medicine', and epidemiology textbooks have allocated pages to warn investigators and readers of investigations to be aware of its presence. ⋯ It is the intent of this paper to present examples of selection bias in a variety of areas which have resulted in misleading or entirely incorrect results. We hope to help make such research scientifically 'politically incorrect' to the degree that the scientific community 'just says no' to such studies, either proposed or reported.