# Individual response

**URL:** <https://discourse.datamethods.org/t/individual-response/5191>\
**Category:** data analysis\
**Tags:** rct, interpretation, design\
**Created:** [December 16, 2021, 9:57am UTC](https://discourse.datamethods.org/t/individual-response/5191 "2021-12-16T09:57:24Z")\
**Posts on this page:** 7\
**Page:** 14

<div class="post-metadata">

**Author:** ![Lawrence\_Lynn](https://discourse.datamethods.org/user_avatar/discourse.datamethods.org/lawrence_lynn/32/4584_2.png) [@Lawrence\_Lynn](https://discourse.datamethods.org/u/Lawrence_Lynn)\
**Post date:** [November 12, 2025, 2:01pm UTC](https://discourse.datamethods.org/t/individual-response/5191/265 "2025-11-12T14:01:25Z")

</div>

First, I don’t have a dog in this fight but I have a lived experience of failed (nontrasportable) DT for over 3 decades. It’s very bad for the public health. So I’m going to be blunt about assumptions and consequences.

Certainly this post is brilliantly phrased as always, but this exposes the deeper vulnerability of idealized DT framing.

“Concurrent control” doesn’t remove the need for exchangeability; it merely constructs a temporary, synthetic version within the trial’s own P(X). The RCT replaces an assumed invariance across studies with an imposed balance inside one.

P(Y \do(T), X) may be stable, but P(X) rarely is.

When transportability is implied without explicitly comparing Xrct to Xicu the very covariates that define the structure of causal effect modification. Without that comparison, there is no bridge between P(X)\_trial and P(X)\_ICU the ATE is unanchored.

So yes while exchangeability across studies is not assumed between studies. it’s silently re-assumed when we pretend our RCT result applies beyond the study, at which point we assume it all over again, just without saying so.

That hidden assumption of non-assumption marks the epistemic fault line between the RCT(DT) and Causal Inference frameworks.

---

<div class="post-metadata">

**Author:** ![f2harrell](https://discourse.datamethods.org/user_avatar/discourse.datamethods.org/f2harrell/32/165_2.png) [@f2harrell](https://discourse.datamethods.org/u/f2harrell)\
**Post date:** [November 12, 2025, 4:27pm UTC](https://discourse.datamethods.org/t/individual-response/5191/266 "2025-11-12T16:27:31Z")

</div>

> [@ESMD](#):
>
> The Dawid/Senn paper was first cited back in post #222 in this thread, and again in post #250. There’s also a lot more back-and-forth about the M&P paper involving Stensrud/Sarvet- I’ve linked to all the relevant responses in post #250.

I would love to hear a response to Pearl’s response from @Stephen

---

<div class="post-metadata">

**Author:** ![Uriah](https://discourse.datamethods.org/user_avatar/discourse.datamethods.org/uriah/32/1280_2.png) [@Uriah](https://discourse.datamethods.org/u/Uriah)\
**Post date:** [November 15, 2025, 9:00am UTC](https://discourse.datamethods.org/t/individual-response/5191/267 "2025-11-15T09:00:50Z")

</div>

I’m working on some educational material regarding Causal Bounds, starting from observational data. Later on I’m planning on updating slides for experimental data, combined data and bounds with DAGs.

> **[causal\_bounds\_smoking\_example – Causal Bounds for Observational Data](https://causalbounds.netlify.app/causal_bounds_smoking_example.html#/title-slide)**

Comments are welcome!

---

<div class="post-metadata">

**Author:** ![f2harrell](https://discourse.datamethods.org/user_avatar/discourse.datamethods.org/f2harrell/32/165_2.png) [@f2harrell](https://discourse.datamethods.org/u/f2harrell)\
**Post date:** [November 15, 2025, 12:57pm UTC](https://discourse.datamethods.org/t/individual-response/5191/268 "2025-11-15T12:57:45Z")

</div>

It may be useful to supplement that with full Bayesian modeling that includes a bias parameter as exemplified [here](https://fharrell.com/post/hxcontrol).

---

<div class="post-metadata">

**Author:** ![trumanfrancis](https://discourse.datamethods.org/user_avatar/discourse.datamethods.org/trumanfrancis/32/47_2.png) [@trumanfrancis](https://discourse.datamethods.org/u/trumanfrancis)\
**Post date:** [November 15, 2025, 12:59pm UTC](https://discourse.datamethods.org/t/individual-response/5191/269 "2025-11-15T12:59:32Z")

</div>

What are the thoughts on the FDA’s new plausible mechanism pathway for approval? Is this sensible for treatments for which RCTs are infeasible? [https://www.nejm.org/doi/full/10.1056/NEJMsb2512695](https://www.nejm.org/doi/full/10.1056/NEJMsb2512695)

---

<div class="post-metadata">

**Author:** ![Uriah](https://discourse.datamethods.org/user_avatar/discourse.datamethods.org/uriah/32/1280_2.png) [@Uriah](https://discourse.datamethods.org/u/Uriah)\
**Post date:** [November 16, 2025, 4:38pm UTC](https://discourse.datamethods.org/t/individual-response/5191/270 "2025-11-16T16:38:15Z")

</div>

I promise I’ll do that as soon as I’ll be able to understand it 😅

---

<div class="post-metadata">

**Author:** ![davidcnorrismd](https://discourse.datamethods.org/user_avatar/discourse.datamethods.org/davidcnorrismd/32/3502_2.png) [@davidcnorrismd](https://discourse.datamethods.org/u/davidcnorrismd)\
**Post date:** [November 17, 2025, 8:53am UTC](https://discourse.datamethods.org/t/individual-response/5191/271 "2025-11-17T08:53:39Z")

</div>

> "There are several aspects of Baby K.J.’s story that define the FDA’s plausible mechanism pathway.
> 
> …
> 
> Fifth, there is an improvement in clinical outcomes or course. In conditions with progressive deterioration, consistent improvements will be viewed favorably by the FDA."

Here, this plausible-mechanism piece seems to describe N-of-1 _scientific_ reasoning that proceeds without need for statistics to glean a faint signal out of masses of data.

> **[The Gleaners](https://en.wikipedia.org/wiki/The_Gleaners)**
>
> The Gleaners (Des glaneuses) is an oil painting by Jean-François Millet completed in 1857. It is held in the Musée d'Orsay, in Paris.
> It depicts three peasant women gleaning a field of stray stalks of wheat after the harvest. The painting is famous for featuring in a sympathetic way what were then the lowest ranks of rural society; it was received poorly by the French upper classes.
> Millet's The Gleaners was preceded by a vertical painting of the image in 1854 and an etching in 1855. Millet unv...

Its vagueness and superficiality notwithstanding, the piece at least does not describe approvals of marginally-effective drugs such as I addressed in “ [Where are the exceptional responders?](https://discourse.datamethods.org/t/where-are-the-exceptional-responders/17961) ”.

[Previous page](https://discourse.datamethods.org/t/individual-response/5191.md?page=13)