|
|
|
|
Biostatistics
|
|
|
| Content |
|
Introduction
Biostatistics is a branch of the statistical sciences concerned with the analysis of data from clinical studies. Basic knowledge of biostatistics is a prerequisite for understanding the principles of evidence-based medicine.
The main topics of biostatistics are: trial design, summarizing data and inference. Trial design (methodology) should give guidance on the best way to collect clinical data: for example, clinical data should be collected in a blinded manner and patients should be randomly assigned to a particular treatment, regimen, group, etc. When summarizing data, no information should be lost and this can be ensured through the selection of appropriate summary statistics. For example, using the mean and the standard deviation for normally distributed data, and the incidence when studying the occurrence of a disease in a population during a period of time. Finally, inference is concerned with drawing valid conclusions from clinical data. Is treatment A better than treatment B? (e.g. are deaths prevented?) and, if so, how strong is the effect of treatment A? (e.g. how many deaths are prevented?). Here the tools of biostatistics are P values (e.g. is A significantly better than B?) and confidence intervals (e.g. how strong is the effect?). The key statistical topics will be reviewed in this section.
|
|
|