This paper explains how to select the correct statistical test for a research project, clinical trial, or other investigation. The first step is to decide in what scale of measurement your data are as this will affect your decision-nominal, ordinal, or interval. The next stage is to consider the purpose of the analysis-for example, are you comparing independent or paired groups? Several statistical tests are discussed with an explanation of when it is appropriate to use each one; relevant examples of each are provided. If an incorrect test is used, then invalid results and misleading conclusions may be drawn from the study. (c) 2007 The British Association of Oral and Maxillofacial Surgeons. Published by Elsevier Ltd. All rights reserved.