Margarita Moreno-Betancur

Assumptions and analysis planning in studies with missing data in multiple variables: moving beyond the MCAR/MAR/MNAR classification Abstract. Researchers faced with incomplete data are encouraged to consider whether their data are ‘missing completely at random’ (MCAR), ‘missing at rando

Woops, here is the corrected
second one: doi.org/10.1093/ije/...

Canonical Causal Diagrams to Guide the Treatment of Missing Data in Epidemiologic Studies Abstract. With incomplete data, the “missing at random” (MAR) assumption is widely understood to enable unbiased estimation with appropriate methods. While

Hi both! Thanks for tagging me :) A couple from my team are: (1) doi.org/10.1093/aje/... (+ correction) (2) doi.org/10.1093/aje/... (perhaps more accessible) and (3) doi.org/10.1002/bimj... (perhaps more theoretical). We're also doing a virtual workshop for SER in Aug epiresearch.org/annual-meeti...

Summer school starts in less than a month - make sure you secure you spot soon!

Course details and links to register can be found here 👇 www.vicbiostat.org.au/short-courses

Start the year well by registering for the ViCBiostat Summer School 😊 👉 www.trybooking.com/events/landi...

Yes, no recording I’m afraid

ViCBiostat Summer School: Register now below so you don’t miss out on e.g. Eric Tchetgen Tchetgen’s causal inference course covering a range of topics in “quasi-experimental” approaches: difference-in-differences, instrumental variables, synthetic controls etc. #EpiSky #CausalSky

Incredibly honoured to receive the Rising Star Award at MCRI Staff Awards ✨ Thank you to my mentors, especially @margaritamb.bsky.social for championing the nomination, and to colleagues and collaborators @mcri.bsky.social who nominated me. Grateful to be part of such a supportive community 💛

Registrations now open for the ViCBiostat Summer School - Feb 13-20, 2026 (Melbourne/online)!

Features courses by local & international experts in causal inference, estimands, meta-analysis and cluster RCTs

Info: www.vicbiostat.org.au/short-courses
Register: www.trybooking.com/events/landi...

Mark your diaries! The ViCBiostat Summer School returns from 13-20 Feb 2026, in Melbourne and online.
Courses include causal inference, cluster randomised trials, meta-analysis and the estimand framework.
Further details TBA shortly - sign up to our mailing list at www.vicbiostat.org.au
#statistics

@cebu-melbourne.bsky.social @vicbiostat.bsky.social
@mcri.bsky.social @unimelb.bsky.social

A few weeks ago I went to Canberra to receive the Moran Medal at the lovely Shine Dome of the Australian Academy of Science (@science.org.au). It was a huge honour, and wonderful to hear talks from all corners of science and to learn about the Academy's great work supporting science
- pics below!

Causal Machine Learning Methods and Use of Cross‐Fitting in Settings With High‐Dimensional Confounding Observational epidemiological studies commonly seek to estimate the causal effect of an exposure on an outcome. Adjustment for potential confounding bias in modern studies is challenging due to the p...

NEW PAPER!!! "Causal Machine Learning Methods and Use of Cross‐Fitting in Settings With High‐Dimensional Confounding"

led by Susie Ellul, with Stijn Vansteelandt & John Carlin
Published in Stats in Med

Check it out 👇
onlinelibrary.wiley.com/doi/10.1002/...

#EpiSky #CausalSky

😄

Without getting into the Hume/Kant debate that Ivan raised above, if we focus on target trial emulations or actual trials, the estimand can indeed (though doesn't have to!) be defined as the effect in an ideal trial (per my other message, given the asymptotic result)

So specifying the components of the ideal trial (up to the contrasts) is an intuitive (but not necessary!) way of defining some causal estimands (but maybe not all of them!). And as I argue can help being clear about some things that are often forgotten in the math notation

I am not sure what you think my premise is, but as I explain in the paper under asymptotic conditions the ACE defined using potential outcomes is mathematically equivalent to the effect in an ideal trial randomizing the target pop to the two interventions of interest

My take on the addendum estimands (from afar), is that the approach overlooks causal identification assumptions (step 2 in my Figure 1) and suggests some estimands that are not actually proper (mathematically defined) defensivle estimands - they are more “analysis approaches”, ie skip steps 1 and 2

My 2 cents to clarifying links between formal causal inference and target and actual trials: arxiv.org/abs/2405.10026 @timpmorris.bsky.social @idiaz.bsky.social

@rush-099.bsky.social @cebu-melbourne.bsky.social @vicbiostat.bsky.social

The ideal trial: defining causal estimands that balance relevance and feasibility in target trial emulations and actual randomized trials Causal inference is the goal of randomized trials and many observational studies. The first step in a formal causal inference framework is to define the causal estimand, and in both types of study thi...

NEW PAPER! (in press in EPIDEMIOLOGY)

Have you wondered:
- How to specify a target trial: as an ideal trial or something else?
- What biases do target trial emulations and actual RCTs share?
- How does it all relate to potential outcomes?

Read here! 👉 arxiv.org/abs/2405.10026
#EpiSky #CausalSky

🎯 TARGET Guideline published 🎉

TARGET is a reporting guideline for observational studies of interventions that use the target trial framework.

Over 3 years the @TARGETGuideline was rigorously developed and was co-published today in @jama.com & @bmj.com

doi.org/10.1001/jama.2025.13350

#episky

@ghazalehd.bsky.social @cebu-melbourne.bsky.social @vicbiostat.bsky.social

To what extent could eliminating racial discrimination reduce inequities in mental health and sleep problems among Aboriginal and Torres Strait Islander children? A causal mediation study Targeted policy interventions that eliminate racial discrimination against Aboriginal and Torres Strait Islander children could have high potential to reduce inequities in mental health and sleep prob...

6/ And more: Impact of eliminating racial discrimination in reducing inequities in mental health and sleep problems among Aboriginal and Torres Strait Islander children (tinyurl.com/5nej5vch)

Preventing postnatal depression: a causal mediation analysis of a 20-year preconception cohort | Philosophical Transactions of the Royal Society B: Biological Sciences Postnatal depression (PND) is common and predicts a range of adverse maternal and offspring outcomes. PND rates are highest among women with persistent mental health problems before pregnancy, and ant...

5/ Even more examples: Impact of potential interventions to reduce postnatal depression (tinyurl.com/3ej5mee4) and mid-life mental health disorders (tinyurl.com/yy8jbpwr) in those with a history of mental illness

Adiposity and breast, endometrial, and colorectal cancer risk in postmenopausal women: Quantification of the mediating effects of leptin, C‐reactive protein, fasting insulin, and estradiol Background Mechanisms underlying the adiposity–cancer relationship are incompletely understood. We quantified the mediating roles of C-reactive protein (CRP), leptin, fasting insulin, and estradiol ...

4/ More examples: Impact of potential interventions to reduce the heightened cancer risk in postmenopausal women with obesity (tinyurl.com/5b3kwjwk) and to reduce sex differences in melanoma cancer survival (tinyurl.com/57prtyr7)

3/ Examples: Impact of potential early childhood interventions to reduce socioeconomic disparities in children’s mental health (tinyurl.com/muttxx7j) and literacy skills (tinyurl.com/mvz8bxk8)

Mediation effects that emulate a target randomised trial: Simulation-based evaluation of ill-defined interventions on multiple mediators - Margarita Moreno-Betancur, Paul Moran, Denise Becker, George ... Many epidemiological questions concern potential interventions to alter the pathways presumed to mediate an association. For example, we consider a study that i...

2/ The methodology uses interventional effects mapped to a “target trial” assessing the treatment strategies of interest, as proposed here tinyurl.com/yztb2hxs

1/ NEW R PACKAGE! For estimating the impact of potential interventions on multiple mediators in countering exposure effects (led by @cttc101.bsky.social)

- Paper👉 tinyurl.com/ye26jsps
- Package👉 tinyurl.com/yuh4kens

Thread shows published examples of how the method can be used! #EpiSky #CausalSky

Rejoinder to Commentaries on: On the Uses and Abuses of Regression Models: A Call for Reform of Statistical Practice and Teaching Click on the article title to read more.

NOW PUBLISHED! Featured article + 6 Commentaries + Rejoinder: “On the Uses and Abuses of Regression Models: A Call for Reform of Statistical Practice and Teaching” with my colleague John Carlin
tinyurl.com/2z2tmkhh
@cebu-melbourne.bsky.social @vicbiostat.bsky.social #EpiSky #CausalSky #StatsSky

Invited commentary: Descriptive social epidemiology: putting the question before the methods Abstract. In studies describing socioeconomic inequities in health outcomes, the choice of estimand and the planned analytic approach are central to the in

📢 New Commentary: We discuss how analytic choices impact interpretation of studies on socioeconomic health inequities. We review 1) descriptive analogues of causal estimands (à la Young et al) with competing events; 2) timescale choice; and 3) covariate adjustment.
👉 academic.oup.com/aje/advance-...