Essential Statistical Tests
This chapter summarizes the basic steps involved in performing commonly used statistical hypothesis tests for continuous and categorical outcomes in randomized clinical trials and further describes the statistical test procedures. Statistical hypothesis tests generally fall into two broad categories, parametric and non-parametric statistical tests. Parametric tests are statistical tests that require the assumption that the data follows some known distribution. These include t-tests, analysis of variance (ANOVA), and χ2 tests. Non-parametric tests do not require this assumption, and are robust to misspecification, but are generally more conservative. Commonly used non-parametric tests include the signed-rank test, Wilcoxon rank sum test, Kruskal-Wallis test, and Fisher’s exact test. While not an exhaustive list, this chapter will describe each of these tests in detail and give an overview of their use.
KeywordsHypothesis test Parametric Non-parametric T-test Chi-square ANOVA
- Agresti A (2011) Exact inference for categorical data: recent advances and continuing controversies. Stat Med 20:17–18Google Scholar
- Guyatt G, Jaeschke R, Heddle N, Cook D, Shannon H, Walter S (1995) Basic statistics for clinicians: 1. Hypothesis testing. Can Med Assoc J 152(1):27–32Google Scholar
- Pearson K (1900) On the criterion that a given system of deviations from the probable in the case of a correlated system of variables is such that it can be reasonably supposed to have arisen from random sampling. Philos Mag 50(302):157–175. https://doi.org/10.1080/14786440009463897CrossRefzbMATHGoogle Scholar