Continuous variable analyses

Comparing groups of continuous data is a commonly encountered challenge in translational radiation oncology research and is prevalent everywhere from the basic science lab to randomized clinical trials. Where descriptive statistics are not sufficient, hypothesis testing is necessary to compare data and draw accurate conclusions. When there are exactly two groups of continuous data to be compared, the statistical tests to choose from are primarily: the t-test for independent samples (unpaired t-test), the t-test for dependent samples (paired t-test), the Mann–Whitney U test, and the Wilcoxon signed-rank test. Selection of the appropriate test requires an understanding of each test's unique requirements and applications to avoid erroneous conclusions and ensure high-quality analyses.