pairwise.t.test have different p-value than grouped_ggbetweenstats

the data are here:
I have a between subject study desing, so i use pairwise.t.test to have my p-value :

c=pairwise.t.test(GF6TOT$value, GF6TOT$Tache, p.adjust.method = "holm", paired = TRUE)

So i get p-value from this.
Now i want t do a graph so i do:

ggstatsplot::grouped_ggbetweenstats(GF6TOT,  plot.type = "boxviolin", 
 x = Tache, 
 y = value,
 grouping.var = variable,             # grouping variable
 pairwise.comparisons = TRUE,      # display significant pairwise comparisons
 pairwise.annotation = "p.value",  # how do you want to annotate the pairwise comparisons
 pairwise.display = "all", 
  p.adjust.method = "holm",   # method for adjusting p-values for multiple comparisons
 bf.message = TRUE,                
 conf.level = 0.95)

But the p-value are different and i dont understand why... can some one help me? :slight_smile:

You say you have a between-subjects design, but you are setting paired = TRUE in pairwise.t.test function, which means you are getting results from paired t-tests. Maybe that explains the discrepancy?

In ggstatsplot, ggbetweenstats is for between-subjects designs while ggwithinstats is for within-subjects designs.

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.