Basic concepts of statistical analysis for surgical research

Appropriate statistical analyses are an integral part of surgical research. The purpose of this work is to assist surgeons and clinicians with the interpretation of statistics by providing a general understanding of the basic concepts that lead to choosing an appropriate statistical test for common study designs. It is extremely important to understand the nature of the data before embarking on a statistical analysis. A researcher must design an appropriate study around the research hypothesis. Initially, data should be inspected using frequency distributions and graphical techniques. If the data are continuous, the normality of the distribution must be assessed. In addition, the data must be defined as independent or dependent. For normally distributed and independent samples, a two-sample t test is appropriate. A paired t test should be used for dependent data. The nonparametric counterpart to the t test is the Mann-Whitney U and the paired counterpart is the Wilcoxon signed rank. For binary data, contingency table methods such as a chi(2) test apply unless the expected value is < 5; then, use the Fisher's exact test. The McNemar test applies to paired binary data. Correlation coefficients assess the association between two continuous distributions. Linear regression assesses trend. Multiple regression analysis is appropriate for multivariate analyses with a continuous outcome variable. Logistic regression methods would apply for binary outcomes. The quality of the analysis and subsequent results of any research project depend on an appropriate study design, data collection, and analysis to make meaningful conclusions. (c) 2005 Elsevier Inc. All rights reserved.