How many subjects do I need to?

Jeanette Adams, RN, DrPH, is an Assistant Professor in the School of Nursing at The University of Texas Health Science Center at Houston, Texas. Dr. Adams is a member of the APON Research Committee. Although this is a typical question posed when considering the development of a research study, there are no easy answers. In many statistical texts, the mere computation of sample size is enough to discourage the aspiring investigator! While requirements related to numbers of subjects vary by the specialty field and are influenced by the research questions, design and feasibility issues, the basic reason for the concern with sample size, in quantitative studies at least, is having adequate numbers of observations to support statistical analysis of the data. There are commonly held &dquo;rules of thumb&dquo; which offer some general guidance, such as having approximately twenty subjects per variable or having at least five observations in each &dquo;cefl&dquo; of data. Because of the impetus to develop a more researchbased practice, ways to more scientifically determine sample size have received increasing attention. Power analysis’ is a concept that has proven useful in this endeavor and will be briefly discussed. The power of a statistical test is related to the concept of Type I and Type II error. A Type I error is rejection of the null hypothesis when it is true, i.e., stating that a significant result has occurred when it actually has not. The probability of Type I error is the Alpha level of significance allowed. A Type II er-