How to Choose the Appropriate Statistical Method

APRIL 2005 • VOLUME 9, NUMBER 2 • CLINICAL JOURNAL OF ONCOLOGY NURSING This is the second in a series of articles to help nurses use and understand statistics. The purpose of the series is to assist nurses in critically reviewing published studies and implementing the fi ndings of research into clinical practice. The fi rst article addressed basic statistical considerations and types of variables (Oliver & Mahon, 2005). This article will describe appropriate statistical methods to use when summarizing data collected from a research project. Additionally, this article will introduce the infamous p value. A p value is a probability that determines whether a difference between two or more treatment types or interventions is big enough, or statistically signifi cant, to change the current standard of care. However, interpretation of a p value requires that subjects were assigned randomly into the two or more groups being compared. Therefore, a variety of randomization techniques will be described to illustrate the infl uence that sampling choices might have on the interpretation of p values. Finally, this article will discuss the interpretation of statistical signifi cance in terms of clinical signifi cance.