Timescales in Time-to-Event Analyses in Pregnancy
Abstract
The target trial framework is increasingly used to define the causal estimand for an observational analysis. However, designing time-to-event analyses that align with the causal estimand is challenging in pregnancy because the timescale on which outcomes are often defined, "gestational age", differs from the timescale on which outcomes are measured, "time since study entry". We argue that neither timescale is "best" but that each aligns with a different estimand. In this article, we use the target trial framework to define the causal estimands corresponding to each timescale. We consider a (hypothetical) target trial comparing randomization to 17-alpha hydroxyprogesterone caproate (17-OHPC) versus placebo between 16-20 weeks of gestation to prevent delivery before 37 weeks' gestation, whether by miscarriage, stillbirth, or live birth. We define the estimand of time-to-event analyses on the "time since study entry" timescale as the effect of randomization to 17-OHPC versus placebo between 16-20 weeks of gestation on delivery before 37 weeks'. In contrast, the causal estimand of time-to-event analyses using the "gestational age" timescale corresponds to the effect had, counter to fact, all participants been randomized at one gestational age (e.g., 16 weeks). We review specific challenges to estimation and possible solutions for each timescale.
Related
- Comment on "Event-Triggered Stabilization of Linear Time-Delay Systems via Halanay-Type Inequality"
- Using the spsurv R package for semi-parametric time-to-event analysis
- Event-Time Order-Flow Memory, Operational-Time Impact, and Subordinated Market Observables
- Extended Joint Models for Longitudinal and Time-to-Event Data: A Tutorial
- tteICE: An R Package for Estimating Treatment Effects on Time-to-Event Outcomes with Intercurrent Events in Two-Arm Trials
BibTeX
@misc{latour2026timescales,
title = {{Timescales in Time-to-Event Analyses in Pregnancy}},
author = {Chase D Latour and Shalini S. Ramachandra and Daniel A. Xu and Elizabeth Diemer and Viktor H. Ahlqvist and Kristin Palmsten and Stefanie Hinkle and Sunni L. Mumford and Enrique Schisterman and Jessie K. Edwards and Ellen C. Caniglia},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.23862},
eprint = {2609.23862},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.23862},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Timescales in Time-to-Event Analyses in Pregnancy
AU - Chase D Latour
AU - Shalini S. Ramachandra
AU - Daniel A. Xu
AU - Elizabeth Diemer
AU - Viktor H. Ahlqvist
AU - Kristin Palmsten
AU - Stefanie Hinkle
AU - Sunni L. Mumford
AU - Enrique Schisterman
AU - Jessie K. Edwards
AU - Ellen C. Caniglia
PY - 2026
DA - 2026/09/20
PB - arXiv
DO - 10.48550/arxiv.2609.23862
UR - https://arxiv.org/abs/2609.23862
AB - The target trial framework is increasingly used to define the causal estimand for an observational analysis. However, designing time-to-event analyses that align with the causal estimand is challenging in pregnancy because the timescale on which outcomes are often defined, "gestational age", differs from the timescale on which outcomes are measured, "time since study entry". We argue that neither timescale is "best" but that each aligns with a different estimand. In this article, we use the target trial framework to define the causal estimands corresponding to each timescale. We consider a (hypothetical) target trial comparing randomization to 17-alpha hydroxyprogesterone caproate (17-OHPC) versus placebo between 16-20 weeks of gestation to prevent delivery before 37 weeks' gestation, whether by miscarriage, stillbirth, or live birth. We define the estimand of time-to-event analyses on the "time since study entry" timescale as the effect of randomization to 17-OHPC versus placebo between 16-20 weeks of gestation on delivery before 37 weeks'. In contrast, the causal estimand of time-to-event analyses using the "gestational age" timescale corresponds to the effect had, counter to fact, all participants been randomized at one gestational age (e.g., 16 weeks). We review specific challenges to estimation and possible solutions for each timescale.
ER -