Seminars

For further information on any CSM events please e-mail: csm@lshtm.ac.uk.

Centre for Statistical Methodology Seminar
Thursday 12 Dec 2019, 12:45-2:00pm
Curtis Room K/LG08, Keppel Street
Fabrizia Mealli (University of Florence)

Title: Assessing causal effects in the presence of treatment switching through principal stratification.

Abstract:

Consider clinical trials focusing on survival outcomes for patients suffering from Acquired Immune Deficiency Syndrome (AIDS)-related illnesses or particularly painful cancers in advanced stages. These trials often allow patients in the control arm to switch to the treatment arm if their physical conditions are worse than certain tolerance levels. The Intention-To-Treat analysis compares groups formed by randomization regardless of the treatment actually received. Although it provides valid causal estimates of the effect of assignment, it does not measure the effect of the actual receipt of the treatment and ignores the information of treatment switching in the control group. Other existing methods propose to reconstruct the outcome a unit would have had if s/he had not switched. But these methods usually rely on strong assumptions, for example, there exists no relation between patient’s prognosis and switching behavior, or the treatment effect is constant. Clearly, the switching status of the units in the control group contains important post-treatment information, which is useful to characterize the treatment effect heterogeneity. We propose to re-define the problem of treatment switching using principal stratification and introduce new causal estimands, principal causal effects for patients belonging to subpopulations defined by the switching behavior under control. For statistical inference, we use a Bayesian approach to take into account that (i) switching happens in continuous time generating infinitely many principal strata; (ii) switching time is not defined for units who never switch in a particular experiment; and (iii) survival time and switching time are subject to censoring. We illustrate our framework using a synthetic dataset based on the Concorde study, a randomized controlled trial aimed to assess causal effects on time-to-disease progression or death of immediate versus deferred treatment with zidovudine among patients with asymptomatic HIV infection. Joint work with Alessandra Mattei and Peng Ding.

Centre for Statistical Methodology Seminar
Tuesday 17 Dec 2019, 12:45 – 2:00pm
Room LG24, Keppel Street
Tanayott Thaweethai (Harvard School of Public Health)

Title: Adjusting for selection bias due to missing data in electronic health records-based research.

Abstract:

The widespread adoption of electronic health records (EHR) over the last decade has resulted in an explosion of data available to researchers, which has transformed the landscape of observational research. Since EHR are not collected for research purposes, observational studies using EHR are particularly susceptible to issues of missing data. I present a scalable method that considers a modularization of the data provenance, which entails breaking down the path to observing ‘complete’ data in the EHR into a sequence of decisions or events. Following modularization, the analyst has the flexibility to model each ‘step’ along the sequence individually using inverse probability weighting (IPW) or multiple imputation (MI). In some settings, this approach can even handle data suspected to be missing not at random. I establish the asymptotic properties of an estimator that combines IPW with MI, finding that Rubin’s standard combining rules can be substantially biased under certain conditions. I applied this approach to two settings: first, to address missing baseline and follow-up BMI in a study of bariatric surgery among patients with renal impairment, and second, to address missing eligibility criteria in a single-arm clinical trial where a synthetic control arm is built from patient EHR data.