Search Results

You are looking at 1 - 4 of 4 items for

  • Author: Michael R. Elliott x
Clear All Modify Search
Open access

Xi Xia and Michael R. Elliott

Abstract

When analyzing data sampled with unequal inclusion probabilities, correlations between the probability of selection and the sampled data can induce bias if the inclusion probabilities are ignored in the analysis. Weights equal to the inverse of the probability of inclusion are commonly used to correct possible bias. When weights are uncorrelated with the descriptive or model estimators of interest, highly disproportional sample designs resulting in large weights can introduce unnecessary variability, leading to an overall larger mean square error compared to unweighted methods.

We describe an approach we term ‘weight smoothing’ that models the interactions between the weights and the estimators as random effects, reducing the root mean square error (RMSE) by shrinking interactions toward zero when such shrinkage is allowed by the data. This article adapts a flexible Laplace prior distribution for the hierarchical Bayesian model to gain a more robust bias-variance tradeoff than previous approaches using normal priors. Simulation and application suggest that under a linear model setting, weight-smoothing models with Laplace priors yield robust results when weighting is necessary, and provide considerable reduction in RMSE otherwise. In logistic regression models, estimates using weight-smoothing models with Laplace priors are robust, but with less gain in efficiency than in linear regression settings.

Open access

Nanhua Zhang, Henian Chen and Michael R. Elliott

Abstract

Nonresponse is very common in epidemiologic surveys and clinical trials. Common methods for dealing with missing data (e.g., complete-case analysis, ignorable-likelihood methods, and nonignorable modeling methods) rely on untestable assumptions. Nonresponse two-phase sampling (NTS), which takes a random sample of initial nonrespondents for follow-up data collection, provides a means to reduce nonresponse bias. However, traditional weighting methods to analyze data from NTS do not make full use of auxiliary variables. This article proposes a method called nonrespondent subsample multiple imputation (NSMI), where multiple imputation (Rubin 1987) is performed within the subsample of nonrespondents in Phase I using additional data collected in Phase II. The properties of the proposed methods by simulation are illustrated and the methods applied to a quality of life study. The simulation study shows that the gains from using the NTS scheme can be substantial, even if NTS sampling only collects data from a small proportion of the initial nonrespondents.

Open access

Hanzhi Zhou, Michael R. Elliott and Trivellore E. Raghunathan

Abstract

Multiple imputation (MI) is commonly used when item-level missing data are present. However, MI requires that survey design information be built into the imputation models. For multistage stratified clustered designs, this requires dummy variables to represent strata as well as primary sampling units (PSUs) nested within each stratum in the imputation model. Such a modeling strategy is not only operationally burdensome but also inferentially inefficient when there are many strata in the sample design. Complexity only increases when sampling weights need to be modeled. This article develops a generalpurpose analytic strategy for population inference from complex sample designs with item-level missingness. In a simulation study, the proposed procedures demonstrate efficient estimation and good coverage properties. We also consider an application to accommodate missing body mass index (BMI) data in the analysis of BMI percentiles using National Health and Nutrition Examination Survey (NHANES) III data. We argue that the proposed methods offer an easy-to-implement solution to problems that are not well-handled by current MI techniques. Note that, while the proposed method borrows from the MI framework to develop its inferential methods, it is not designed as an alternative strategy to release multiply imputed datasets for complex sample design data, but rather as an analytic strategy in and of itself.

Open access

Zeina M. Mneimneh, Roger Tourangeau, Beth-Ellen Pennell, Steven G. Heeringa and Michael R. Elliott

Abstract

Privacy is an important feature of the interview interaction mainly due to its potential effect on reporting information, especially sensitive information. Here we examine the effect of third-party presence on reporting both sensitive and relatively neutral outcomes. We investigate whether the effect of third-party presence on reporting sensitive information is moderated by the respondent’s need for social conformity and the respondent’s country of residence. Three types of outcomes are investigated: behavioral, attitudinal, and relatively neutral health events. Using data from 22,070 interviews and nine countries in the cross-national World Mental Health Survey Initiative, we fit multilevel logistic regression to study reporting effects on questions about suicidal behavior and marital ratings, and contrast these with questions about having high blood pressure, asthma, or arthritis. We find that there is an effect of third-party presence on reporting sensitive information and no effect on reporting of neutral information. Further, the effect of the interview privacy setting on reporting sensitive information is moderated by the need for social conformity and the cultural setting.