• Publications
  • Influence
Covariate association eliminating weights: a unified weighting framework for causal effect estimation
TLDR
A unified framework for constructing weights such that a set of measured pretreatment covariates is unassociated with treatment assignment after weighting is proposed, which extends to longitudinal settings.
Two-part models with stochastic processes for modelling longitudinal semicontinuous data: Computationally efficient inference and modelling the overall marginal mean
  • S. Yiu, B. Tom
  • Mathematics, Computer Science
    Statistical methods in medical research
  • 27 March 2017
TLDR
An efficient method of implementation is described by demonstrating how the high dimensional integrations involved in the marginal likelihood can be computed efficiently by using a property of the multivariate normal distribution and the standard marginal cumulative distribution function identity.
Two-Part and Related Regression Models for Longitudinal Data
TLDR
Two-part models for semicontinuous and zero-heavy count data are examined, and models for count data with a two-part random effects distribution are considered.
A joint modelling approach for multistate processes subject to resolution and under intermittent observations
  • S. Yiu, B. Tom
  • Environmental Science
    Statistics in medicine
  • 17 October 2016
TLDR
A multistate model that includes the state space of the original multistates process but partitions the state representing absent symptoms into a latent absorbing resolved state and a temporary transient state of absent symptoms is proposed.
Clustered multistate models with observation level random effects, mover–stayer effects and dynamic covariates: modelling transition intensities and sojourn times in a study of psoriatic arthritis
TLDR
A novel model parameterization which allows easily interpretable covariate effects to act on these quantities is proposed and is found to provide further understanding of the activity–damage relationship beyond that provided by previous analyses.
Exploring the existence of a stayer population with mover–stayer counting process models: application to joint damage in psoriatic arthritis
TLDR
It is demonstrated that the choice of model for the movers can lead to widely varying conclusions on a stayers population, thus implying that, if interest lies in a stayer population, a single analysis should not generally be adopted.
Joint calibrated estimation of inverse probability of treatment and censoring weights for marginal structural models
TLDR
A joint calibration approach to CBW estimation for MSMs that can accommodate both time-varying confounding and dependent censoring, binary and non-binary treatments, eventual outcomes and longitudinal outcomes is proposed and applied to a natural history study of HIV.
SAT0186 DEVELOPING PREDICTORS OF GLOBAL BILAG TREATMENT RESPONSE IN PATIENTS WITH LUPUS NEPHRITIS: MORE LESSONS FROM THE ASPREVA LUPUS MANAGEMENT STUDY GROUP (ALMS) DATA
TLDR
Being a responder (RR or SR) was significantly associated with activity in constitutional, musculoskeletal and cardiorespiratory BILAG domains, higher baseline and cumulative steroid exposure, and receiving active drug.
Sensitivity analysis for calibrated inverse probability-of-censoring weighted estimators under non-ignorable dropout.
Inverse probability of censoring weighting is a popular approach to handling dropout in longitudinal studies. However, inverse probability-of-censoring weighted estimators (IPCWEs) can be inefficient
...
1
2
...