FAQ/ENH: observed, post-hoc power: don't make invalid conclusions

Open
#6,615 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
5/5
Estimated time
Over a week
Newbie friendliness
25/100
Issue type
Feature
Clarity
Needs clarification
Activity status
Stale
Tech stack
python
Domain
data

Research direction

Start by reviewing the existing ANOVA PR mentioned in the issue and the project's current power-analysis entry points. Determine how observed and prospective power and sample-size calculations should be scoped, including appropriate interpretation of observed power. Done means an agreed implementation plan that supports the requested analyses without invalid conclusions.

Written by the indexing model from the issue text.

Description

comp-stats FAQ type-enh

Computing observed power, i.e. power at observed effect sizes, have been strongly criticized in recent literature, but mainly because it is used to argue in favor of null or alternative hypothesis.

However, I'd like to include them together with effect sizes, mainly so we get an additional statistic that complements p-value with a measure of type 2 error.
Also, we should be able to use the same functions to compute prospective power and sample size computation at different effect sizes and sample sizes.
(currently I have observed power in anova PR)

O’Keefe, Daniel J. 2007. “Brief Report: Post Hoc Power, Observed Power, A Priori Power, Retrospective Power, Prospective Power, Achieved Power: Sorting Out Appropriate Uses of Statistical Power Analyses.” Communication Methods and Measures 1 (4): 291–99. https://doi.org/10.1080/19312450701641375.

Onwuegbuzie, Anthony J., and Nancy L. Leech. 2004. “Post Hoc Power: A Concept Whose Time Has Come.” Understanding Statistics 3 (4): 201–30. https://doi.org/10.1207/s15328031us0304_1.

There are more articles, but I don't find them anymore at the moment.

Dominant language
Python
Stars
11.6k
Forks
3.6k
Avg merge
7h 37m
Merged PRs (30d)
96

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from statsmodels/statsmodels

All issues in statsmodels/statsmodels

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.