Estimating sample size in dental research

Abstract

Determination of sample size is critical, however not easy to do. Sample size defined as the number of observations in a sample should be big enough to have a high likelihood of detecting a true difference between groups. Practical procedure for determining sample size, using G*power and previous dental articles, is shown in this study. Examples involving independent t-test, paired t-test, one-way analysis of variance(ANOVA), and one-way repeated-measures(RM) ANOVA are used. The purpose of this study is to enable researchers with non-statistical backgrounds to use in practice freely available statistical software G*power to determine sample size and power.