I have a dataset (find an example below) in which there are many factor variables (group_a, group_b, group_c, etc.; some factor variables fave missing values) and a numeric variable (value). I want to test if value differs significantly among levels of factor variables (value between levels of group_a, value between levels of group_b, etc.). After I did all the tests, should I correct p-values for multiple comparisons? What are the reasons for and what are against doing the corrections?

An example of dataset:

my_data <- read.table(text = "
   object group_a group_b group_c value
1       1       A       G       T  65.0
2       2       B       H       Y  13.8
3       3       B       G       Y  34.2
4       4       B       H       Y   9.0
5       5       A       G       Y  73.2
6       6       B       G       Y  58.8
7       7       A      NA       T  18.2
8       8       B       G       Y  10.1
9       9       B       H       Y   9.5
10     10       A      NA       Y  86.9")

(This is a simplified and extended version of the dataset used in this question).


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.