Does categorizing scale scores with cutoff points affect hypothesis-testing results?

This study shows that the variables that were found to be highly significant in our conventional analysis group (i.e., p < 0.01) showed statistical significance again when the tests were repeated in the "IQR", " ± 1std", "golden ratio", "10% trimmed", and "5% trimmed" subanalysis groups.

also in 132,142 other papers