top of page

Causal Inference in RCTs: ITT, CACE, and Estimands in Practice

Causal Inference inside an RCT – STATA-First Edition

0 Glossary of Key Abbreviations

Short-form

Stands for

Meaning in this document

R

Randomised assignment

The arm a participant is assigned to by the randomisation algorithm (sometimes noted Z).

D

Delivered (received) treatment

What the participant actually gets; equals R only if compliance is perfect.

ACE

Average Causal Effect

Generic label for “true” causal effect; equals ATE/ATT/ATU when R = D for everyone.

ATE

Average Treatment Effect

Mean effect in the entire target population.

ATT / ATU

Effect on the Treated / Untreated

Mean effect restricted to those who did / did not receive treatment.

ITT

Intention-to-Treat

Primary estimator that compares arms exactly as randomised, ignoring crossover.

PP / AT

Per-Protocol / As-Treated

Analyses restricted by compliance (PP) or re-labelled by actual D (AT); lose randomisation protection.

CACE

Complier Average Causal Effect (also called LATE)

The causal effect among participants who would comply with their assignment, estimated with an IV approach when R ≠ D.


1 Why an RCT Usually Satisfies the Four Causal Assumptions

  1. Exchangeability – Randomisation balances both measured & unmeasured baseline risk.

  2. Positivity – By design, every participant has a non-zero chance of landing in each arm.

  3. No-Interference (part of SUTVA) – Each patient’s assignment rarely affects another’s outcome; use cluster randomisation if it might.

  4. Consistency (second part of SUTVA) – The protocol specifies one clear version of each arm; monitor adherence to keep it that way.

Result ➜ The standard ITT contrast is already a causal estimator.

2 Perfect Compliance ⇒ All Average Effects Collapse

If every subject receives exactly what they were assigned (R = D):

ACE  =  ATE  =  ATT  =  ATU

So you only need to report the ITT contrast.

3 Continuous Outcomes – ATE via Mean Difference

3·1 Crude ITT

* assume variable treat = 1 treatment arm, 0 control
ttest outcome, by(treat)          // mean difference + CI

3·2 Precision-boosted ITT (ANCOVA)

regress outcome i.treat baseline_outcome age sex
margins, dydx(treat)               // adjusted mean diff = ATE

Adding baseline prognostic covariates shrinks the standard error; it is not for confounder control in an RCT.

4 Binary Outcomes – Risk & Odds Scales

4·1 Collapsible Measures → Risk Difference / Risk Ratio

cci events_treat total_treat  events_ctrl total_ctrl  // crude RD & RR

4·2 Non-collapsible Measure → Marginal Odds Ratio

  1. Fit logistic model with covariates (conditional OR):

logit event i.treat age sex
  1. Re-average to recover a marginal effect:

margins treat, predict(pr)            // get arm-specific risks
lincom _b[1.treat]/(1-_b[1.treat]) / (_b[0.treat]/(1-_b[0.treat])) , eform

Margins calculate arm-level predicted probabilities; the lincom line converts those risks into a marginal OR.

5 When Compliance Is Imperfect (R ≠ D)

Goal

Recommended estimator / Stata tool

Effectiveness (policy)

ITT – as above; remains primary.

Efficacy in compliers

CACE via two-stage least squares (IV): ivregress 2sls outcome (D = R) covariates ; estat firststage to diagnose instrument strength.

Supportive PP / AT

Restrict or relabel using keep if or replace treat = D – report as sensitivity only.


6 Typical Pitfalls & How to Fix Them

Pitfall

Why it matters

Stata-first fix

Adjusting for too many baseline covariates “for balance”

Up-weights noise → wider CIs

Limit to ≤ 5 strong prognostic factors; pre-specify.

Using conditional OR as final result

Mis-matches causal estimand

Always run margins to obtain marginal effect.

Multiple versions of treatment emerge

Breaks Consistency

Add arm indicator for version or stratify analysis.

>15 % event rate yet reporting OR

Odds mislead at common events

Prefer RD/RR: riskrr (user package) or cci above.


7 Quick Analysis Checklist

  1. Write the estimand sentence (e.g., “ATE of 30-day mortality for Drug X vs placebo in adults with septic shock”).

  2. Check adherence – if < 90 %, plan CACE alongside ITT.

  3. Pre-select covariates for precision only.

  4. Decide risk vs odds scale before looking at results.

  5. Use margins for all marginal effects; bootstrap (vce(bootstrap)) if you need robust CIs after complex modelling.

8 Take-Home Messages

  • Randomisation makes all four identifiability assumptions hold by design.

  • With perfect compliance, ITT delivers the single average causal effect you need.

  • Covariate adjustment in an RCT targets precision, not confounding.

  • For binary outcomes, translate conditional logistic results into marginal metrics using margins.

  • Non-compliance? Keep ITT for policy, add CACE (IV) for efficacy, and treat PP/AT as secondary.


Recent Posts

See All

コメント

5つ星のうち0と評価されています。
まだ評価がありません

評価を追加
Post: Blog2_Post

​Message for International and Thai Readers Understanding My Medical Context in Thailand

Message for International and Thai Readers Understanding My Broader Content Beyond Medicine

bottom of page