Saved in:
Bibliographic Details
Main Authors: de Villa, A. Ruiz, Badiella, Ll.
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.05939
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917069437534208
author de Villa, A. Ruiz
Badiella, Ll.
author_facet de Villa, A. Ruiz
Badiella, Ll.
contents The analysis of randomized trials is often complicated by the occurrence of intercurrent events and missing values. Even though there are different strategies to address missing values it is still common to require missing values imputation. In the present article we explore the estimation of treatment effects in RCTs from a causal inference perspective under different missing data mechanisms with a particular emphasis on missings not at random (MNAR). By modelling the missingness process with directed acylcic graphs and patient-specific potential response variables, we present a new approach to obtain an unbiased estimation of treatment effects without needing to impute missing values. Additionally, we provide a formal that the average conditional log-odds ratio is a robust measure even under MNAR missing values if adjusted by sufficient confounders.
format Preprint
id arxiv_https___arxiv_org_abs_2511_05939
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Estimating Treatment Effects with Missings Not At Random in the Estimand Framework using Causal Inference
de Villa, A. Ruiz
Badiella, Ll.
Methodology
62D20
The analysis of randomized trials is often complicated by the occurrence of intercurrent events and missing values. Even though there are different strategies to address missing values it is still common to require missing values imputation. In the present article we explore the estimation of treatment effects in RCTs from a causal inference perspective under different missing data mechanisms with a particular emphasis on missings not at random (MNAR). By modelling the missingness process with directed acylcic graphs and patient-specific potential response variables, we present a new approach to obtain an unbiased estimation of treatment effects without needing to impute missing values. Additionally, we provide a formal that the average conditional log-odds ratio is a robust measure even under MNAR missing values if adjusted by sufficient confounders.
title Estimating Treatment Effects with Missings Not At Random in the Estimand Framework using Causal Inference
topic Methodology
62D20
url https://arxiv.org/abs/2511.05939