Multiple imputation of missing covariates for the Cox proportional hazards cure model

Beesley, Lauren J.; Bartlett, Jonathan; Wolf, Gregory T.; Taylor, Jeremy M. G.

doi:10.1002/sim.7048

Cited by 20 publications

(47 citation statements)

References 31 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Beesley et al . () explores imputation‐based approaches for dealing with the missing covariate data for this study. The analysis in Beesley et al .…”

Section: Application To Head and Neck Cancer Datamentioning

confidence: 99%

“…As suggested in Beesley et al . (), we impute missing values of each p th covariate X ( p ) using a standard regression model with X (− p ) , G ,

G \times {\overset{H}{true}}_{0} false(T false)

, and

G \times {\overset{H}{true}}_{0} false(T false) \times {bold-italicX}^{(- p)}

as predictors. Here,

{\overset{H}{true}}_{0} false(T false)

is an estimate of the cumulative baseline hazard of having an event in the non‐cured group.…”

Section: Application To Head and Neck Cancer Datamentioning

confidence: 99%

“…Beesley et al . ). In this paper, we explore a generalisation of this missingness mechanism that allows covariate/outcome missingness to depend on the latent variable, which is a missing not at random (MNAR) mechanism (Little & Rubin ).…”

Section: Introductionmentioning

confidence: 97%

“…Beesley et al . () explores SMC imputation for a particular modelling setting with latent variables, but we have not found any literature exploring chained equations or SMC imputation under latent ignorable missingness in general.…”

Section: Introductionmentioning

confidence: 99%

“…Schafer ; Schafer & Yucel ; Chung, Flaherty & Schafer ) or using less restrictive assumptions (Beesley et al . . While the proposed method can be applied under MAR or LMAR, the primary novelty consists of the application to the LMAR setting.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Sequential imputation for models with latent variables assuming latent ignorability

Beesley

Taylor

Little

2019

Aus NZ J of Statistics

Self Cite

View full text Add to dashboard Cite

Models that involve an outcome variable, covariates, and latent variables are frequently the target for estimation and inference. The presence of missing covariate or outcome data presents a challenge, particularly when missingness depends on the latent variables. This missingness mechanism is called latent ignorable or latent missing at random and is a generalisation of missing at random. Several authors have previously proposed approaches for handling latent ignorable missingness, but these methods rely on prior specification of the joint distribution for the complete data. In practice, specifying the joint distribution can be difficult and/or restrictive. We develop a novel sequential imputation procedure for imputing covariate and outcome data for models with latent variables under latent ignorable missingness. The proposed method does not require a joint model; rather, we use results under a joint model to inform imputation with less restrictive modelling assumptions. We discuss identifiability and convergence-related issues, and simulation results are presented in several modelling settings. The method is motivated and illustrated by a study of head and neck cancer recurrence. Imputing missing data for models with latent variables under latent-dependent missingness without specifying a full joint model.

show abstract

“…Beesley et al . () explores imputation‐based approaches for dealing with the missing covariate data for this study. The analysis in Beesley et al .…”

Section: Application To Head and Neck Cancer Datamentioning

confidence: 99%

“…As suggested in Beesley et al . (), we impute missing values of each p th covariate X ( p ) using a standard regression model with X (− p ) , G ,