[Clinical research XVII. χ(2) test, from the expected to the observed]

When you want to show if there is a statistical association or differences between categorical variables, it is recommended to use the χ(2) test. This nonparametric test is one of the most used in clinical research; it contrasts nominal or ordinal qualitative variables that are observed in clinical practice. This test calculates the p value that determines whether differences between groups are real or due to chance. The χ(2) test is the basis of other tests to analyze qualitative ordinal variables as χ(2) for linear trend, which compares three groups with two outcomes or McNemar test, which contrasts two related samples (a before and afterward comparison) or Mantel-Haenszel χ(2), which controls for potential confounding variables. When using small samples, where the expected results are less than 5, Fisher's exact test should be used. These tests are the most widely used in the medical literature; however, they do not give us the magnitude or the direction of the event and a proper interpretation that requires clinical judgment is needed.