# bayes

**URL:** https://discourse.datamethods.org/c/stat/bayes/23.md

[Latest](https://discourse.datamethods.org/latest.md) · [Categories](https://discourse.datamethods.org/categories.md) · [Tags](https://discourse.datamethods.org/tags.md)

---

## [About the bayes category](https://discourse.datamethods.org/t/about-the-bayes-category/46)

<div class="topic-metadata">

**Author:** [@f2harrell](https://discourse.datamethods.org/u/f2harrell)\
**Replies:** 0

</div>

Bayesian data analysis, modeling, inference

---

## [Reporting frequentist and Bayesian results side by side in physiotherapy evidence: helpful or confusing?](https://discourse.datamethods.org/t/reporting-frequentist-and-bayesian-results-side-by-side-in-physiotherapy-evidence-helpful-or-confusing/28904)

<div class="topic-metadata">

**Author:** [@Ertan](https://discourse.datamethods.org/u/Ertan)\
**Replies:** 5\
**Last updated:** [October 30, 2026, 11:47am UTC](https://discourse.datamethods.org/t/reporting-frequentist-and-bayesian-results-side-by-side-in-physiotherapy-evidence-helpful-or-confusing/28904 "2026-10-30T11:47:54Z")

</div>

Hi all, I would value the community’s views on a reporting question that came up in a recent project. I reanalysed the meta-analyses in a recent systematic review on exercise for rotator cuff-related shoulder pain (Laf…

---

## [FDA Draft Guidance: Use of Bayesian Methodology in Clinical Trials of Drug and Biological Products](https://discourse.datamethods.org/t/fda-draft-guidance-use-of-bayesian-methodology-in-clinical-trials-of-drug-and-biological-products/28598)

<div class="topic-metadata">

**Author:** [@davidcnorrismd](https://discourse.datamethods.org/u/davidcnorrismd)\
**Replies:** 15\
**Last updated:** [September 20, 2026, 11:29am UTC](https://discourse.datamethods.org/t/fda-draft-guidance-use-of-bayesian-methodology-in-clinical-trials-of-drug-and-biological-products/28598 "2026-09-20T11:29:43Z")

</div>

New DG dropped, just putting the link here as I’m sure it will be of interest! https://www.fda.gov/media/190505/download

---

## [Bayesian randomized non-inferiority trial design](https://discourse.datamethods.org/t/bayesian-randomized-non-inferiority-trial-design/28693)

<div class="topic-metadata">

**Author:** [@Indranil\_Mallick](https://discourse.datamethods.org/u/Indranil_Mallick)\
**Replies:** 1\
**Last updated:** [April 4, 2026, 1:23pm UTC](https://discourse.datamethods.org/t/bayesian-randomized-non-inferiority-trial-design/28693 "2026-04-04T13:23:22Z")

</div>

I am a clinical researcher, and I wanted to discuss a specific clinical trial design question. A recently reported randomized non-inferiority trial has demonstrated non-inferiority of a shortened (hypofractionated) cours…

---

## [Should one derive risk difference from the odds ratio?](https://discourse.datamethods.org/t/should-one-derive-risk-difference-from-the-odds-ratio/4403)

<div class="topic-metadata">

**Author:** [@arthur\_albuquerque](https://discourse.datamethods.org/u/arthur_albuquerque)\
**Replies:** 622\
**Last updated:** [March 17, 2026, 2:43pm UTC](https://discourse.datamethods.org/t/should-one-derive-risk-difference-from-the-odds-ratio/4403 "2026-03-17T14:43:25Z")

</div>

This paper (Doi et al. 2020) came out last year heavily advocating for the odds ratio (OR). https://www.jclinepi.com/article/S0895-4356(20)31171-9/fulltext I am aware of OR’s advantages over risk ratio (RR), but I have…

---

## [Prior design in a bayesian re-analysis of an RCT](https://discourse.datamethods.org/t/prior-design-in-a-bayesian-re-analysis-of-an-rct/7838)

<div class="topic-metadata">

**Author:** [@valens](https://discourse.datamethods.org/u/valens)\
**Replies:** 4\
**Last updated:** [October 20, 2024, 1:12pm UTC](https://discourse.datamethods.org/t/prior-design-in-a-bayesian-re-analysis-of-an-rct/7838 "2024-10-20T13:12:10Z")

</div>

I am conducting a Bayesian re-analysis of a non-inferiority RCT. Since it is not possible to use a meta-analytical prior, our work focuses on constructing a prior based on the synthesis of experts opinion. Following the…

---

## [Bayesian vs. Frequentist Statements About Treatment Efficacy](https://discourse.datamethods.org/t/bayesian-vs-frequentist-statements-about-treatment-efficacy/5945)

<div class="topic-metadata">

**Author:** [@f2harrell](https://discourse.datamethods.org/u/f2harrell)\
**Replies:** 5\
**Last updated:** [June 10, 2024, 3:34pm UTC](https://discourse.datamethods.org/t/bayesian-vs-frequentist-statements-about-treatment-efficacy/5945 "2024-06-10T15:34:52Z")

</div>

This is a place for discussing Bayesian vs. Frequentist Statements About Treatment Efficacy. Archive These comments were made using disqus on an old blog platform. Most of them were made between 2017 and 2021. Ahmed:…

---

## [How to infer the analysts' priors from this figure?](https://discourse.datamethods.org/t/how-to-infer-the-analysts-priors-from-this-figure/6342)

<div class="topic-metadata">

**Author:** [@davidcnorrismd](https://discourse.datamethods.org/u/davidcnorrismd)\
**Replies:** 6\
**Last updated:** [February 22, 2023, 11:10am UTC](https://discourse.datamethods.org/t/how-to-infer-the-analysts-priors-from-this-figure/6342 "2023-02-22T11:10:16Z")

</div>

Here is Figure 1B from Fourie Zerkelbach &al (2021) \[1\]. In the text, it is presented as evidence for a “bell-shaped” exposure-response relationship: No doubt the modeling here was done in a frequentist framework …

---

## [First approach to the rmsb package - issues](https://discourse.datamethods.org/t/first-approach-to-the-rmsb-package-issues/3617)

<div class="topic-metadata">

**Author:** [@albertoca](https://discourse.datamethods.org/u/albertoca)\
**Replies:** 44\
**Last updated:** [January 20, 2023, 2:39am UTC](https://discourse.datamethods.org/t/first-approach-to-the-rmsb-package-issues/3617 "2023-01-20T02:39:56Z")

</div>

I’ve decided to test the rmsb library on a cohort of women with breast cancer. Most authors have evaluated quality of life at the end of treatment by comparing median scores in women with or without intervention, usually…

---

## [Discrepancies between the rmsb package and RStan](https://discourse.datamethods.org/t/discrepancies-between-the-rmsb-package-and-rstan/6053)

<div class="topic-metadata">

**Author:** [@arthur\_albuquerque](https://discourse.datamethods.org/u/arthur_albuquerque)\
**Replies:** 2\
**Last updated:** [September 29, 2022, 9:56pm UTC](https://discourse.datamethods.org/t/discrepancies-between-the-rmsb-package-and-rstan/6053 "2022-09-29T21:56:29Z")

</div>

I’ve been trying to fit and learn how to wrangle results from Bayesian models fitted with the rmsb package. Below, I fit a cumulative proportional odds model with the blrm function. I then check parameters summaries gen…

---

## [Rmsb: Relative Explained Variation of Clustering Variable](https://discourse.datamethods.org/t/rmsb-relative-explained-variation-of-clustering-variable/5487)

<div class="topic-metadata">

**Author:** [@EricTesdahl](https://discourse.datamethods.org/u/EricTesdahl)\
**Replies:** 8\
**Last updated:** [September 7, 2022, 10:32am UTC](https://discourse.datamethods.org/t/rmsb-relative-explained-variation-of-clustering-variable/5487 "2022-09-07T10:32:16Z")

</div>

Hello everyone, I have some reviewer comments back on a paper where we used rmsb to assess some predictors of survival for patients on ECMO due to COVID-19. One aspect of the analysis that the reviewers (and my co-author…

---

## [A Bayes-Frequentist approach to the Analysis of Credibility of meta-analyses using p-values](https://discourse.datamethods.org/t/a-bayes-frequentist-approach-to-the-analysis-of-credibility-of-meta-analyses-using-p-values/5004)

<div class="topic-metadata">

**Author:** [@R\_cubed](https://discourse.datamethods.org/u/R_cubed)\
**Replies:** 10\
**Last updated:** [October 11, 2021, 6:44pm UTC](https://discourse.datamethods.org/t/a-bayes-frequentist-approach-to-the-analysis-of-credibility-of-meta-analyses-using-p-values/5004 "2021-10-11T18:44:23Z")

</div>

I wanted to post this for some input to see if there was any flaw in my reasoning for the proposed procedure. It incorporates a lot of ideas from dozens of papers and posts. Following the ideas from A Theory of Experi…

---

## [How to model an outcome measure bounded between 0 and 100 using Bayesian analysis](https://discourse.datamethods.org/t/how-to-model-an-outcome-measure-bounded-between-0-and-100-using-bayesian-analysis/4440)

<div class="topic-metadata">

**Author:** [@micah](https://discourse.datamethods.org/u/micah)\
**Replies:** 9\
**Last updated:** [September 22, 2021, 2:49pm UTC](https://discourse.datamethods.org/t/how-to-model-an-outcome-measure-bounded-between-0-and-100-using-bayesian-analysis/4440 "2021-09-22T14:49:59Z")

</div>

I’m trying to create a Bayesian regression model for the purpose of parameter estimation. The outcome PROM that can take any value between 0 and 100. I initially created a model in jags mod1\_string = " model { for (i …

---

## [Prior distributions for observational studies - Is it worth it?](https://discourse.datamethods.org/t/prior-distributions-for-observational-studies-is-it-worth-it/4758)

<div class="topic-metadata">

**Author:** [@arthur\_albuquerque](https://discourse.datamethods.org/u/arthur_albuquerque)\
**Replies:** 6\
**Last updated:** [September 9, 2021, 7:15pm UTC](https://discourse.datamethods.org/t/prior-distributions-for-observational-studies-is-it-worth-it/4758 "2021-09-09T19:15:40Z")

</div>

Recently I read a retrospective cohort published in BMJ (https://www.bmj.com/content/351/bmj.h3190.short) using an approach I hadn’t seen yet. They studied the association of SSRIs with birth defects in their database u…

---

## [Multiplicity Adjustments in Bayesian Analysis](https://discourse.datamethods.org/t/multiplicity-adjustments-in-bayesian-analysis/2649)

<div class="topic-metadata">

**Author:** [@albertoca](https://discourse.datamethods.org/u/albertoca)\
**Replies:** 22\
**Last updated:** [August 29, 2021, 1:23pm UTC](https://discourse.datamethods.org/t/multiplicity-adjustments-in-bayesian-analysis/2649 "2021-08-29T13:23:19Z")

</div>

I’ve been trying to understand the Bayesian approach to multiple comparison adjustments, and I’ve made a mess of it. I wanted to please ask for your perception of this. For example, I have recently been reading the resu…

---

## [Discussion: Why Bayes for Clinical Trials](https://discourse.datamethods.org/t/discussion-why-bayes-for-clinical-trials/2331)

<div class="topic-metadata">

**Author:** [@f2harrell](https://discourse.datamethods.org/u/f2harrell)\
**Replies:** 7\
**Last updated:** [August 12, 2021, 7:06am UTC](https://discourse.datamethods.org/t/discussion-why-bayes-for-clinical-trials/2331 "2021-08-12T07:06:25Z")

</div>

This topic is for discussion of the presentation Why Bayes for Clinical Trials? and the Introduction to Bayes for Evaluating Treatments resource.

---

## [How to replace p-value on Bayes statistics?](https://discourse.datamethods.org/t/how-to-replace-p-value-on-bayes-statistics/4630)

<div class="topic-metadata">

**Author:** [@KirovDoc](https://discourse.datamethods.org/u/KirovDoc)\
**Replies:** 2\
**Last updated:** [July 27, 2021, 6:45am UTC](https://discourse.datamethods.org/t/how-to-replace-p-value-on-bayes-statistics/4630 "2021-07-27T06:45:49Z")

</div>

You know some investigators want to cancel the p-value as a statistical parameter. And some of them suggest Bayes statistics. Can you show how it will work on a simple example? E.g. I want to compare the two groups. I ca…

---

## [Frequentist vs Bayesian debate applied to real-world data analysis: any philosophical insights?](https://discourse.datamethods.org/t/frequentist-vs-bayesian-debate-applied-to-real-world-data-analysis-any-philosophical-insights/1695)

<div class="topic-metadata">

**Author:** [@albertoca](https://discourse.datamethods.org/u/albertoca)\
**Replies:** 10\
**Last updated:** [April 6, 2021, 12:16pm UTC](https://discourse.datamethods.org/t/frequentist-vs-bayesian-debate-applied-to-real-world-data-analysis-any-philosophical-insights/1695 "2021-04-06T12:16:28Z")

</div>

I’ve been reading about the benefits of the Bayesian versus frequentist approach in clinical trials. However, I don’t know if there are any specific insights applicable to the real-world data scenario, with observational…

---

## [What would get Stan more use in FDA IND applications?](https://discourse.datamethods.org/t/what-would-get-stan-more-use-in-fda-ind-applications/3909)

<div class="topic-metadata">

**Author:** [@syclik](https://discourse.datamethods.org/u/syclik)\
**Replies:** 14\
**Last updated:** [November 18, 2020, 1:50pm UTC](https://discourse.datamethods.org/t/what-would-get-stan-more-use-in-fda-ind-applications/3909 "2020-11-18T13:50:37Z")

</div>

Lately, I’ve been thinking about how to get Bayesian methods and software used more for FDA approvals. Right now, we have been working with customers on internal decision-making, but we would love to do the community a s…

---

## [Bayesian Solutions for Challenges to Frequentist Statistics](https://discourse.datamethods.org/t/bayesian-solutions-for-challenges-to-frequentist-statistics/3764)

<div class="topic-metadata">

**Author:** [@f2harrell](https://discourse.datamethods.org/u/f2harrell)\
**Replies:** 0\
**Last updated:** [September 22, 2020, 1:08pm UTC](https://discourse.datamethods.org/t/bayesian-solutions-for-challenges-to-frequentist-statistics/3764 "2020-09-22T13:08:25Z")

</div>

Ability to Use External Information A skeptical prior distribution may be used when it is known that a therapy is incremental and not curative. In the less common situation where one has excellent data about the same tr…

---

## [Empirical Bayes for RCT Interpretarion](https://discourse.datamethods.org/t/empirical-bayes-for-rct-interpretarion/2922)

<div class="topic-metadata">

**Author:** [@fgzampieri](https://discourse.datamethods.org/u/fgzampieri)\
**Replies:** 8\
**Last updated:** [August 11, 2020, 2:13pm UTC](https://discourse.datamethods.org/t/empirical-bayes-for-rct-interpretarion/2922 "2020-08-11T14:13:56Z")

</div>

Hello everyone, So @f2harrell suggested I moved a Twitter discussion on using Bayesian update for interpretation of clinical trials to datamethods. I am a little bit concerned that my code and concepts may not be polish…

---

## [Who should define reasonable priors and how?](https://discourse.datamethods.org/t/who-should-define-reasonable-priors-and-how/2935)

<div class="topic-metadata">

**Author:** [@akerenyi](https://discourse.datamethods.org/u/akerenyi)\
**Replies:** 15\
**Last updated:** [May 29, 2020, 11:10am UTC](https://discourse.datamethods.org/t/who-should-define-reasonable-priors-and-how/2935 "2020-05-29T11:10:33Z")

</div>

Hi! Clinician and very amateur stats nerd here, trying to take in the BBR course one step at a time. I wanted to ask a question that was inspired by the discussions around the course but doesn’t directly relate to any c…

---

## [Conditional Independence Assumption](https://discourse.datamethods.org/t/conditional-independence-assumption/2384)

<div class="topic-metadata">

**Author:** [@ursus](https://discourse.datamethods.org/u/ursus)\
**Replies:** 2\
**Last updated:** [September 30, 2019, 2:05pm UTC](https://discourse.datamethods.org/t/conditional-independence-assumption/2384 "2019-09-30T14:05:27Z")

</div>

Tagged with bayes, but this is a usual MLE assumption as well. Typically, the likelihood of a model, makes use of the conditional independence assumption (CIA) to simplify the joint conditional distribution: p(\\mathbf{…

---

## [Choice of Bayesian priors in an observational study](https://discourse.datamethods.org/t/choice-of-bayesian-priors-in-an-observational-study/2015)

<div class="topic-metadata">

**Author:** [@albertoca](https://discourse.datamethods.org/u/albertoca)\
**Replies:** 11\
**Last updated:** [September 5, 2019, 8:54pm UTC](https://discourse.datamethods.org/t/choice-of-bayesian-priors-in-an-observational-study/2015 "2019-09-05T20:54:49Z")

</div>

Hi, I have a cohort of patients with a rare type of tumor. These patients have received two different therapies, A and B, and there are currently no clinical trials comparing them. After reading Datamethods I am convince…

---

## [Bayesian approach to diagnostic validity?](https://discourse.datamethods.org/t/bayesian-approach-to-diagnostic-validity/916)

<div class="topic-metadata">

**Author:** [@eric](https://discourse.datamethods.org/u/eric)\
**Replies:** 3\
**Last updated:** [January 25, 2019, 2:04pm UTC](https://discourse.datamethods.org/t/bayesian-approach-to-diagnostic-validity/916 "2019-01-25T14:04:29Z")

</div>

I posted a question to cross validated that might be a better fit for datamethods. I’m planning a study that will evaluate a new method of identifying cases in need of treatment. Let’s say we’ll evaluate 100 people with …

---

## [Interim Analysis & "Alpha Spending" in RCT's using Bayesian Analyses](https://discourse.datamethods.org/t/interim-analysis-alpha-spending-in-rcts-using-bayesian-analyses/1259)

<div class="topic-metadata">

**Author:** [@ADAlthousePhD](https://discourse.datamethods.org/u/ADAlthousePhD)\
**Replies:** 15\
**Last updated:** [January 25, 2019, 1:42pm UTC](https://discourse.datamethods.org/t/interim-analysis-alpha-spending-in-rcts-using-bayesian-analyses/1259 "2019-01-25T13:42:56Z")

</div>

Some folks already know - I’m a trained frequentist statistician that’s become progressively more Bayesian by philosophy, though my technical knowledge is still very much a work in progress, and many of the trials that I…