Statistics Corner: Chi-squared Test

Abstract

It is desirable to collect and analyze quantitative data with parametric tests. Researchers, however, also gather categorical variables such as cured vs non-cured and diseased vs non-diseased. And many times, they convert continuous variables such as body mass index (BMI) to high, regular, and low BMI and quality of life to good, average, and poor categories. When both independent and dependent variables are categorical—Chi-square is a standard test. A researcher designs a study and collects data with many categorical outcome variables. The literature search recommends applying the Chi-squared test. The researcher, however, has a few vital questions related to the Chi-squared test: What is Yates’ correction? When to apply Fisher’s exact test? What is the post hoc Chi-squared test? How to assess the strength of an association?