Statistical Tools for Study Design: Replication

Abstract

The ability to collect massive amounts of data relevant to hydrocarbon microbiology from marine and terrestrial environments continues to grow. Given the potential expense and effort of collecting this data however, it is important that careful consideration of experimental design is given before undergoing data collection to maximize the probability that experimental results will lead to statistically significant conclusions. One of the most important aspects of experimental design is the selection of appropriate number of experimental replications. The number of experimental replicates needed to achieve a desired level of statistical significance is dependent upon the known or estimated distributions of the experimental system, the statistical tool that will be used in data analysis, the size of the effect that is anticipated from the experiment, and the desired power of the statistical results. Here, protocols are presented for identifying the most appropriate number of experimental replications to achieve a desired level of statistical power.