Dataset Information

Improving upon the efficiency of complete case analysis when covariates are MNAR.

ABSTRACT: Missing values in covariates of regression models are a pervasive problem in empirical research. Popular approaches for analyzing partially observed datasets include complete case analysis (CCA), multiple imputation (MI), and inverse probability weighting (IPW). In the case of missing covariate values, these methods (as typically implemented) are valid under different missingness assumptions. In particular, CCA is valid under missing not at random (MNAR) mechanisms in which missingness in a covariate depends on the value of that covariate, but is conditionally independent of outcome. In this paper, we argue that in some settings such an assumption is more plausible than the missing at random assumption underpinning most implementations of MI and IPW. When the former assumption holds, although CCA gives consistent estimates, it does not make use of all observed information. We therefore propose an augmented CCA approach which makes the same conditional independence assumption for missingness as CCA, but which improves efficiency through specification of an additional model for the probability of missingness, given the fully observed variables. The new method is evaluated using simulations and illustrated through application to data on reported alcohol consumption and blood pressure from the US National Health and Nutrition Examination Survey, in which data are likely MNAR independent of outcome.

SUBMITTER: Bartlett JW

PROVIDER: S-EPMC4173105 | biostudies-other | 2014 Oct

REPOSITORIES: biostudies-other

ACCESS DATA

Publications

Improving upon the efficiency of complete case analysis when covariates are MNAR.

Bartlett Jonathan W JW Carpenter James R JR Tilling Kate K Vansteelandt Stijn S

Biostatistics (Oxford, England) 20140606 4

Missing values in covariates of regression models are a pervasive problem in empirical research. Popular approaches for analyzing partially observed datasets include complete case analysis (CCA), multiple imputation (MI), and inverse probability weighting (IPW). In the case of missing covariate values, these methods (as typically implemented) are valid under different missingness assumptions. In particular, CCA is valid under missing not at random (MNAR) mechanisms in which missingness in a cova ...[more]

PMID: 24907708

Similar Datasets

Project description:BACKGROUND:Accurate estimation of operative case-time duration is critical for optimizing operating room use. Current estimates are inaccurate and earlier models include data not available at the time of scheduling. Our objective was to develop statistical models in a large retrospective data set to improve estimation of case-time duration relative to current standards. STUDY DESIGN:We developed models to predict case-time duration using linear regression and supervised machine learning. For each of these models, we generated an all-inclusive model, service-specific models, and surgeon-specific models. In the latter 2 approaches, individual models were created for each surgical service and surgeon, respectively. Our data set included 46,986 scheduled operations performed at a large academic medical center from January 2014 to December 2017, with 80% used for training and 20% for model testing/validation. Predictions derived from each model were compared with our institutional standard of using average historic procedure times and surgeon estimates. Models were evaluated based on accuracy, overage (case duration > predicted + 10%), underage (case duration < predicted - 10%), and the predictive capability of being within a 10% tolerance threshold. RESULTS:The machine learning algorithm resulted in the highest predictive capability. The surgeon-specific model was superior to the service-specific model, with higher accuracy, lower percentage of overage and underage, and higher percentage of cases within the 10% threshold. The ability to predict cases within 10% improved from 32% using our institutional standard to 39% with the machine learning surgeon-specific model. CONCLUSIONS:Our study is a notable advancement toward statistical modeling of case-time duration across all surgical departments in a large tertiary medical center. Machine learning approaches can improve case duration estimations, enabling improved operating room scheduling, efficiency, and reduced costs.

Project description:BackgroundReactive case detection (RCD) seeks to enhance malaria surveillance and control by identifying and treating parasitaemic individuals residing near index cases. In Zambia, this strategy starts with passive detection of symptomatic incident malaria cases at local health facilities or by community health workers, with subsequent home visits to screen-and-treat residents in the index case and neighbouring (secondary) households within a 140-m radius using rapid diagnostic tests (RDTs). However, a small circular radius may not be the most efficient strategy to identify parasitaemic individuals in low-endemic areas with hotspots of malaria transmission. To evaluate if RCD efficiency could be improved by increasing the probability of identifying parasitaemic residents, environmental risk factors and a larger screening radius (250 m) were assessed in a region of low malaria endemicity.MethodsBetween January 12, 2015 and July 26, 2017, 4170 individuals residing in 158 index and 531 secondary households were enrolled and completed a baseline questionnaire in the catchment area of Macha Hospital in Choma District, Southern Province, Zambia. Plasmodium falciparum prevalence was measured using PfHRP2 RDTs and quantitative PCR (qPCR). A Quickbird™ high-resolution satellite image of the catchment area was used to create environmental risk factors in ArcGIS, and generalized estimating equations were used to evaluate associations between risk factors and secondary households with parasitaemic individuals.ResultsThe parasite prevalence in secondary (non-index case) households was 0.7% by RDT and 1.8% by qPCR. Overall, 8.5% (n?=?45) of secondary households had at least one resident with parasitaemia by qPCR or RDT. The risk of a secondary household having a parasitaemic resident was significantly increased in proximity to higher order streams and marginally with increasing distance from index households. The adjusted OR for proximity to third- and fifth-order streams were 2.97 (95% CI 1.04-8.42) and 2.30 (95% CI 1.04-5.09), respectively, and that for distance to index households for each 50 m was 1.24 (95% CI 0.98-1.58).ConclusionApplying proximity to streams as a screening tool, 16% (n?=?3) more malaria-positive secondary households were identified compared to using a 140-m circular screening radius. This analysis highlights the potential use of environmental risk factors as a screening strategy to increase RCD efficiency.

Dataset Information

Improving upon the efficiency of complete case analysis when covariates are MNAR.

Publications

Improving upon the efficiency of complete case analysis when covariates are MNAR.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets