Statistics in Medical Research : Misuse of Sampling and Sample Size Determination

One of the major issues in planning a research is the decision as to how large a sample and the method to be employed to select the estimated sample in order to meet the objective of the research. Sampling is an essential tool for research in medicine. A good number of the medical literature while reporting their sampling method go by stating that the sample was collected by random sampling and no further explanation as how the sample has been drawn as if the word random is generic to all the known sampling methods. The aim of this paper is to sensitise our researchers on the importance of proper sampling and sample size determination. Using a few examples we demonstrated that investigators adhere poorly to the statistical precondition of simple random sampling, have poor understanding of simple random technique, and quite a number of estimated sample sizes were bloated without appreciating the implications of that. Finally, we recommended, among others that investigators should consult biostatisticians at the design stages of their research work and a competent biostatistician should review any article containing even the most elementary statistical procedure.