A probabilistic approach to the construction of competing-risk life tables

"This paper aims to identify net and partial-crude probabilities in the competing-risk life table context, by using probabilistic approaches. Five types of lifelength random variables are defined to formulate these nonidentifiable probabilities. General expressions for net and partial-crude probabilities are first derived under independent risks assumptions. Two sets of explicit formulas for estimating the net and partial-crude probabilities are then derived in terms of the identifiable overall and crude probabilities by making the additional assumption of piecewise uniform distribution of the lifelength random variables. A study of the degree to which nonidentifiability can affect the net and partial-crude probabilities in a variety of situations is developed. An example from cross-sectional studies is employed to illustrate the methodology developed."     

Power frequency magnetic field exposures among nurses in a neonatal intensive care unit and a normal newborn nursery

Given the current interest in potential carcinogenic and developmental effects of exposure to extremely-low-frequency electromagnetic fields, there is a need to identify cohorts of exposed female workers for future epidemiologic investigations. This study was designed to test the hypothesis that nurses working in neonatal intensive care units (NICU) may be significantly exposed to power-frequency magnetic fields. An electromagnetic field monitor was used to measure magnetic fields at distances of 5, 15, 30, and 60 cm from the surfaces of each device used in the NICU. Six female nurses assigned to the NICU (the “exposed” group) and six female nurses working in the normal newborn nursery (the “referent” group) wore EMDEX dosimeters for the entire duration of their 12 h shifts. An investigator kept a detailed log of each NICU subject's whereabouts for the first one-third of her shift. Magnetic fields at 5 cm from the front (defined by the nurses' usual work area) of the NICU devices ranged from less than 0.1 to 114 μT and in all cases decreased considerably with increasing distance. The geometric mean of the shift-time-weighted average exposure of the NICU nurses was 0.17 μT compared with 0.11 μT for the normal newborn nurses. The percentage of time when subjects were exposed to magnetic fields of 0.4 μT or greater ranged from 5.8% to 15.6% for the NICU nurses, 0.4% to 2.9% for five of the comparison group nurses, and was 9.4% for one of the normal newborn nurses with unidentified aberrantly high exposures. Log data revealed that the vast majority of observed peaks among NICU nurses occurred while subjects were in close proximity to infant bed units. We conclude that NICU nurses represent one female-intensive job sector with intermittent high exposures to ELF magnetic fields and encourage larger exposure studies of nurses in a variety of medical settings. © 1994 Wiley-Liss, Inc.     

Marginal proportional hazards models for clustered interval-censored data with time-dependent covariates

The Botswana Combination Prevention Project was a cluster-randomized HIV prevention trial whose follow-up period coincided with Botswana's national adoption of a universal test and treat strategy for HIV management. Of interest is whether, and to what extent, this change in policy modified the preventative effects of the study intervention. To address such questions, we adopt a stratified proportional hazards model for clustered interval-censored data with time-dependent covariates and develop a composite expectation maximization algorithm that facilitates estimation of model parameters without placing parametric assumptions on either the baseline hazard functions or the within-cluster dependence structure. We show that the resulting estimators for the regression parameters are consistent and asymptotically normal. We also propose and provide theoretical justification for the use of the profile composite likelihood function to construct a robust sandwich estimator for the variance. We characterize the finite-sample performance and robustness of these estimators through extensive simulation studies. Finally, we conclude by applying this stratified proportional hazards model to a re-analysis of the Botswana Combination Prevention Project, with the national adoption of a universal test and treat strategy now modeled as a time-dependent covariate.     

Bias-reduced estimators of conditional odds ratios in matched case-control studies with unmatched confounding

We study bias-reduced estimators of exponentially transformed parameters in general linear models (GLMs) and show how they can be used to obtain bias-reduced conditional (or unconditional) odds ratios in matched case-control studies. Two options are considered and compared: the explicit approach and the implicit approach. The implicit approach is based on the modified score function where bias-reduced estimates are obtained by using iterative procedures to solve the modified score equations. The explicit approach is shown to be a one-step approximation of this iterative procedure. To apply these approaches for the conditional analysis of matched case-control studies, with potentially unmatched confounding and with several exposures, we utilize the relation between the conditional likelihood and the likelihood of the unconditional logit binomial GLM for matched pairs and Cox partial likelihood for matched sets with appropriately setup data. The properties of the estimators are evaluated by using a large Monte Carlo simulation study and an illustration of a real dataset is shown. Researchers reporting the results on the exponentiated scale should use bias-reduced estimators since otherwise the effects can be under or overestimated, where the magnitude of the bias is especially large in studies with smaller sample sizes.