Related Experiment Video
Updated: Nov 13, 2025
05:37
An R-Based Landscape Validation of a Competing Risk Model
Published on: September 16, 2022
2.3K
Improved generalized raking estimators to address dependent covariate and failure-time outcome error
Eric J Oh1, Bryan E Shepherd2, Thomas Lumley3
1Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, PA, USA.
Biometrical Journal. Biometrische Zeitschrift
|March 12, 2021
Summary
This study introduces improved statistical methods for electronic health records (EHR) data analysis, enhancing efficiency in failure-time outcome studies with measurement error. The new techniques, using multiple imputation, reduce bias and improve reliability for clinical research.
Area of Science:
- Biostatistics
- Epidemiology
- Health Informatics
Background:
- Biomedical studies using electronic health records (EHR) data are prone to bias from complex measurement errors in covariates and outcomes.
- Generalized raking methods offer consistent estimates without modeling error structures but can be inefficient in failure-time settings with misclassified outcomes.
Purpose of the Study:
- To develop more efficient raking estimators for EHR data analysis in failure-time outcome settings.
- To address the inefficiency of existing raking estimators when dealing with misclassified event indicators.
- To investigate the impact of outcome-dependent sampling on estimator efficiency.
Main Methods:
- Proposed novel raking estimators incorporating multiple imputation for target or auxiliary variables to enhance efficiency.
- Analyzed the influence of outcome-dependent sampling designs on the efficiency of raking estimators, with and without multiple imputation.
- Conducted extensive numerical studies to evaluate estimator performance across diverse measurement error scenarios.
Main Results:
- The proposed multiple imputation-based raking estimators demonstrate improved efficiency in failure-time outcome analyses with EHR data.
- Outcome-dependent sampling designs were shown to impact the efficiency of raking estimators, with multiple imputation offering benefits.
- Numerical studies confirmed the robust performance of the proposed methods across various measurement error complexities.
Conclusions:
- Multiple imputation-based raking estimators provide a more efficient and robust approach for analyzing EHR data, particularly in failure-time outcome studies with measurement error.
- The findings offer valuable methodological advancements for observational cohort studies, such as the analysis of HIV outcomes using EHR data.
- These enhanced methods contribute to more reliable inference from complex, real-world clinical data.
Related Concept Videos
01:20Comparing the Survival Analysis of Two or More Groups
396
Survival analysis is a cornerstone of medical research, used to evaluate the time until an event of interest occurs, such as death, disease recurrence, or recovery. Unlike standard statistical methods, survival analysis is particularly adept at handling censored data—instances where the event has not occurred for some participants by the end of the study or remains unobserved. To address these unique challenges, specialized techniques like the Kaplan-Meier estimator, log-rank test, and...
396
01:24Kaplan-Meier Approach
370
The Kaplan-Meier estimator is a non-parametric method used to estimate the survival function from time-to-event data. In medical research, it is frequently employed to measure the proportion of patients surviving for a certain period after treatment. This estimator is fundamental in analyzing time-to-event data, making it indispensable in clinical trials, epidemiological studies, and reliability engineering. By estimating survival probabilities, researchers can evaluate treatment effectiveness,...
370
01:14Parametric Survival Analysis: Weibull and Exponential Methods
810
Parametric survival analysis models survival data by assuming a specific probability distribution for the time until an event occurs. The Weibull and exponential distributions are two of the most commonly used methods in this context, due to their versatility and relatively straightforward application.
Weibull Distribution
The Weibull distribution is a flexible model used in parametric survival analysis. It can handle both increasing and decreasing hazard rates, depending on its shape parameter...
Weibull Distribution
The Weibull distribution is a flexible model used in parametric survival analysis. It can handle both increasing and decreasing hazard rates, depending on its shape parameter...
810
01:15Assumptions of Survival Analysis
245
Survival models analyze the time until one or more events occur, such as death in biological organisms or failure in mechanical systems. These models are widely used across fields like medicine, biology, engineering, and public health to study time-to-event phenomena. To ensure accurate results, survival analysis relies on key assumptions and careful study design.
245
01:09Censoring Survival Data
355
Survival analysis is a statistical method used to analyze time-to-event data, often employed in fields such as medicine, engineering, and social sciences. One of the key challenges in survival analysis is dealing with incomplete data, a phenomenon known as "censoring." Censoring occurs when the event of interest (such as death, relapse, or system failure) has not occurred for some individuals by the end of the study period or is otherwise unobservable, and it might have many different...
355
01:09Truncation in Survival Analysis
396
Truncation in survival analysis refers to the exclusion of individuals or events from the dataset based on specific criteria related to the time of the event. This exclusion can happen in two primary forms: left truncation and right truncation.
Left truncation occurs when individuals who experienced the event of interest before a certain time are not included in the study. This is often due to a "delayed entry" into the study where only those who survive until a certain entry point are...
Left truncation occurs when individuals who experienced the event of interest before a certain time are not included in the study. This is often due to a "delayed entry" into the study where only those who survive until a certain entry point are...
396