Topic summary

Second pass at: Regression to the mean in progress reports

Research Methods › Statistics effect size worked example heterogeneity

This is a generated summary. It shows the 9 most-liked posts from a topic of 76, in their original order, with the accepted answer included where one exists. It is a reading aid and it will miss nuance — the full topic is the record.

am.wikstromTL222 Dec 2024#6

Adding the measurement that post #5 says would settle it.

Regression to the mean explains a large share of apparent improvements in anything selected for being extreme. It is not a statistical curiosity; it is the default explanation.

29 likes 19mo

r.mensahTL213 Jan 2025#23

I read post #21 twice before replying, because I had assumed the opposite.

A request rather than an answer: could whoever has the primary source for Regression post it? I have seen the claim three times this month and each version had lost a qualifier.

31 likes 18mo

n.abernathyTL3Analytical chemist20 Jan 2025#30

d.magalhes, post #5: The opening post describes the usual case. This is about the unusual one. Checked the Regression claim against the primary source this morning. It survives, with a narrower scope than the version quoted here. Posting the narrower scope. Go to post

Effect sizes: the magnitude of a difference, not just whether it is statistically significant. A difference that is significant (p<0.05) might be too small to matter. A large effect might not be significant if sample size is small.

Reading it again, the caveat matters more than the finding.

32 likes in reply to #5 18mo

a.salcedoTL3Regular27 Jan 2025#37

Confirming post #36 from a second method, which matters more than confirming it from a second person.

On Regression, I would rather understate and be corrected upward than overstate and be quoted. That is a house style here and it is a good one.

25 likes 18mo

trough_indexTL3Regular7 Feb 2025#48

A p-value is the probability of data at least this extreme given the null hypothesis. It is not the probability the hypothesis is false, and almost every plain-language gloss gets that backwards.

I have separated what I observed from what I concluded, which does not always happen.

28 likes 18mo

ew.kuuselaTL210 Feb 2025#51

Building on post #50 rather than restating it.

Working an example through by hand once makes any of these concepts stick better than reading about them, and the arithmetic is usually a single line.

29 likes 18mo

glossary_deskTL3Regular19 Feb 2025#60

The number people quote for Regression is a central estimate presented without its interval, and the interval is wide enough that the estimate is nearly uninformative on its own.

30 likes 17mo

k.radichTL226 Feb 2025#68

Buchholz, post #58: Medians and means diverge for skewed distributions, and most of the quantities discussed here are skewed. Which one a paper reports is a choice worth noticing. Nothing above should be read as advice about what anyone else should do. Go to post

This follows post #65 rather than contradicting it.

Bayesian and frequentist analyses answer different questions and both are legitimate. What matters is that the reader knows which is on offer.

33 likes in reply to #58 17mo

e.krastevTL21 Mar 2025#72

n.silva, post #63: A standard deviation describes the spread of individuals and a standard error describes the precision of the mean. Quoting one where the other belongs changes the apparent result substantially. That distinction has done more work for me than anything else in this category. Go to post

Where I part company with post #71, and it is a narrow parting.

A p-value is the probability of data at least this extreme given the null hypothesis. It is not the probability the hypothesis is false, and almost every plain-language gloss gets that backwards.

26 likes in reply to #63 17mo

Read the full topic (76 posts)

This topic was referenced in

[2026 update] Correlation in a self-tracked dataset: what it can supportResearch Methods › Statistics · 2 replies

Suggested topics

Topic	Participants	Replies	Views	Activity
What a confidence interval means, from scratch — the long version Research Methods › Statistics effect size worked example confounding number needed to treat The question in the title: What a confidence interval means, from scratch — the long version I will give what I have already checked below so nobody repeats it. Asking about confidence interval directly,…	+16	20	2.3k	8mo
Absence of evidence and evidence of absence Research Methods › Statistics effect size worked example number needed to treat Absence of evidence and evidence of absence Writing it up because I had to work it out twice and would rather nobody else did. Asking about absence of evidence on behalf of the question I keep seeing asked…	+16	20	3.9k	5mo
Second pass at: Absence of evidence and evidence of absence Research Methods › Statistics worked example confounding number needed to treat On the subject in the title: Second pass at: Absence of evidence and evidence of absence Working notes rather than a conclusion. Two things I would like separated before anyone answers on Absence of evidence,…	+50	55	18k	16h
Correlation in a self-tracked dataset: what it can support Research Methods › Statistics effect size heterogeneity worked example number needed to treat Closed Correlation in a self-tracked dataset: what it can support — setting out what I have, and where I think it stops being reliable. Posting a small dataset on correlation. It is mine, it is uncontrolled, and the…	+152	166	48k	23mo
Multiplicity when you track fifteen variables Research Methods › Statistics effect size heterogeneity confounding worked example Solved Multiplicity when you track fifteen variables — setting out what I have, and where I think it stops being reliable. Asking about multiplicity directly, because I have read four threads on it and each answered…		2	60k	11mo

Related topics — sharing the tags effect size, worked example, heterogeneity

Topic	Participants	Replies	Views	Activity
Dead volume across syringe and needle combinations Devices › Syringes & needles needle gauge & length subcutaneous injection dead volume syringe units On the subject in the title: Dead volume across syringe and needle combinations Working notes rather than a conclusion. Something about dead volume across syringe does not reconcile and I would like a second…	+72	80	28k	5mo
Prediction intervals and why they are more honest than confidence intervals Evidence › Meta-analyses heterogeneity risk of bias effect size publication bias Solved Closed Posting this under the heading it deserves: Prediction intervals and why they are more honest than confidence intervals Everything below is what sits behind that. I have spent a fortnight trying to pin…	+21	25	46k	4mo
Comparing my trajectory with the trial curves, carefully Outcomes › Progress reports DXA effect size long read data table Solved Posting this under the heading it deserves: Comparing my trajectory with the trial curves, carefully Everything below is what sits behind that. Maintenance rather than loss, which is the part of this that…	+86	92	54k	7mo
A critique that turned out to be unfair, retracted by its author Evidence › Study critique confounding risk of bias effect size observational data Wiki Posting this under the heading it deserves: A critique that turned out to be unfair, retracted by its author Everything below is what sits behind that. Critique, and specifically the version of it that the…	+34	38	20k	17h
The "under review" status pill and when a moderator applies it Evidence › Preprints risk of bias effect size preprint Posting this under the heading it deserves: The "under review" status pill and when a moderator applies it Everything below is what sits behind that. A question about how this site should cite something that…	+96	119	17k	3mo