0

I have a large dataframe 2000 subjects (into 3 groups) x 80 observations . I have multiple questions.

  1. They are not normally distributed. Do I check normality for each observation group-wise or whole data?
  2. I need to perform kruskal-wallis/anova for all 80 observations between these groups. I found a code:
    R: Kruskal-Wallis test in loop over specified columns in data frame

but this doesn't account for confounders. Is there a way to add it in the formula?

Najeha Mohamed
  • 21
  • 2
  • Statistics depend highly on the data and question you want to answer. Without further details, it is not possible to give detailed advice here. Why do you want to make 80 Kruskal tests instead of just one? Which potential confounders have you measured? Depending on the sampling design, you might not be able to control for all confounders. – danlooo Mar 30 '22 at 11:02
  • Kruskal-Wallis is a bivariate test. You can't add confounders – shs Mar 30 '22 at 11:06
  • Thank you for your responses. I am now moving on to ANOVA (after log-transformation) in a loop with confounders (Age and BMI), since I am working with human data, age and BMI are potential confounders when assessing differences in biomarkers. I am having issue trying to extract the p value of Group differences. – Najeha Mohamed Mar 30 '22 at 11:33

0 Answers0