Related Experiment Video
Updated: Mar 31, 2026
06:55
Inverse Probability of Treatment Weighting Propensity Score using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
15.5K
Evaluation of a weighting approach for performing sensitivity analysis after multiple imputation
Panteha Hayati Rezvan1, Ian R White2, Katherine J Lee3,4
1Centre for Epidemiology and Biostatistics, Melbourne School of Population and Global Health, The University of Melbourne, Parkville, Melbourne, VIC, Australia. phayati@student.unimelb.edu.au.
BMC Medical Research Methodology
|October 15, 2015
Summary
The weighting approach for missing data sensitivity analysis shows bias, even with many imputations. This method is not recommended for multiple imputation (MI) analyses, necessitating further research for better techniques.
Area of Science:
- Statistics
- Data Science
- Biostatistics
Background:
- Multiple imputation (MI) is standard for missing data but assumes data are Missing at Random (MAR).
- Departures from MAR, known as Missing Not At Random (MNAR), are common but difficult to detect.
- Sensitivity analyses are crucial to assess the impact of potential MNAR data on MI results.
Purpose of the Study:
- To evaluate a weighting approach for MNAR sensitivity analyses in MI.
- To assess the robustness of MI results when data are not MAR.
- To compare the performance of weighting-based MNAR estimates against MAR estimates.
Main Methods:
- Simulation studies were conducted to evaluate the weighting approach.
- Missingness in a single variable was simulated, focusing on marginal mean and association parameters.
- A graphical method was assessed for determining the magnitude of departure from MAR.
Main Results:
- The weighting approach showed improvement over the MAR approach but remained biased.
- Biased parameter estimates were observed with the weighting approach, irrespective of the number of imputations.
- The graphical method failed to accurately capture the true parameter value for MAR departure.
Conclusions:
- The weighting approach is not recommended for sensitivity analyses in MI.
- Further research is needed to develop more reliable methods for MNAR sensitivity analyses.
- Standard MI may yield unreliable results if data are MNAR and not properly assessed.
Related Concept Videos
00:57Weighted Mean
7.4K
While taking the arithmetic, geometric, or harmonic mean of a sample data set, equal importance is assigned to all the data points. However, all the values may not always be equally important in some data sets. An intrinsic bias might make it more important to give more weightage to specific values over others.
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...
For example, consider the number of goals scored in the matches of a tournament. While computing the average number of goals scored in the tournament, it may be more important to...
7.4K
01:25Strategies for Assessing and Addressing Confounding
545
Confounding is a critical issue in epidemiological studies, often leading to misleading conclusions about associations between exposures and outcomes. It occurs when the relationship between the exposure and the outcome is mixed with the effects of other factors that influence the outcome. Given that, addressing confounding is of high importance for drawing accurate inferences in research.
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
Confounding can be addressed at both the design phase of a study and through analytical methods after data...
545
01:14Parametric Survival Analysis: Weibull and Exponential Methods
1.3K
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...
1.3K
01:15Assumptions of Survival Analysis
488
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.
488
01:16Statistical Inference Techniques in Hypothesis Testing: Parametric Versus Nonparametric Data
586
Statistical inference techniques, paramount in hypothesis testing, differentiate into two broad categories: parametric and nonparametric statistics.
Parametric statistics, as the name suggests, assumes that data follow a specific distribution, often a normal distribution. This assumption enables robust hypothesis testing and estimation. Parametric methods, like the Student's t-test or Goodness-of-fit test, are frequently employed in biostatistics due to their robustness. For instance,...
Parametric statistics, as the name suggests, assumes that data follow a specific distribution, often a normal distribution. This assumption enables robust hypothesis testing and estimation. Parametric methods, like the Student's t-test or Goodness-of-fit test, are frequently employed in biostatistics due to their robustness. For instance,...
586
01:15One-Way ANOVA: Unequal Sample Sizes
7.0K
One-way ANOVA can be performed on three or more samples of unequal sizes. However, calculations get complicated when sample sizes are not always the same. So, while performing ANOVA with unequal samples size, the following equation is used:
7.0K