Rex Kerr
Apr 16, 2024

--

This is exactly right--but it's infuriating when those same people who attempted to get advice and did kind of okay with the statistical analysis that they asked about then end up writing things like, "Treatment A did not significantly increase the Outcome Variable compared to control (p > 0.1). Treatment B, unlike Treatment A, significantly increased Outcome Variable (p < 0.05)". Emphasis mine, and then of course they go on to act like B and A are different from each other.

Many of the worst abuses of statistics are concluding things "from statistics" using qualitative reasoning instead of "with statistics" using the quantitative methods of statistics.

--

--

Rex Kerr
Rex Kerr

Written by Rex Kerr

One who rejoices when everything is made as simple as possible, but no simpler. Sayer of things that may be wrong, but not so bad that they're not even wrong.

Responses (1)