Combining information from multiple surveys for assessing health disparities

Despite advances in public health practice and medical technology, the disparities in health among the various racial/ethnic and socioeconomic groups remain a concern which has prompted the Department of Human and Health Services to designate the elimination of disparities in health as an overarching goal of Healthy People 2010. To assess the progress towards this goal, suitable measures are needed at the population level that can be tracked over time; Statistical inferential procedures have to be developed for these population level measures; and the data sources have to be identified to allow for such inferences to be conducted. Popular data sources for health disparities research are large surveys such the National Health and Interview Survey (NHIS) or the Behavior Risk Factor Surveillance System (BRFSS). The self-report disease status collected in these surveys may be inaccurate and the errors may be correlated with variables used in defining the groups. This article uses the National Health and Nutritional Examination Survey (NHANES) 99-00 to assess the extent of error in the self-report disease status; uses a Bayesian framework develop corrections for the self-report disease status in the National Health Interview Survey (NHIS) 99-00; and compares inferences about various measures of health disparities, with and without correcting for measurement error. The methodology is illustrated using the disease outcome hypertension, a common risk factor for cardiovascular disease. JEL classification C1 (C11, C13, C15), C4 (C42) and I3 (I31, I38)     

Combining information from multiple surveys through the empirical likelihood method

It is often desirable to combine information collected in compatible multiple surveys in order to improve estimation and meet consistency requirements. Zieschang (1990) and Renssen & Nieuwenbroek (1997) suggested to this end the use of the generalized regression estimator with enlarged number of auxiliary variables. Unfortunately, adjusted weights associated with their approach can be negative. The author uses the notion of pseudo empirical likelihood to construct new estimators that are consistent, efficient and possess other attractive properties. The proposed approach is asymptotically equivalent to the earlier one, but it has clear maximum likelihood interpretations and its adjusted weights are always positive. The author also provides efficient algorithms for computing his estimators.     

Combining information from multiple surveys by using regression for efficient small domain estimation

Summary.  In sample surveys of finite populations, subpopulations for which the sample size is too small for estimation of adequate precision are referred to as small domains. Demand for small domain estimates has been growing in recent years among users of survey data. We explore the possibility of enhancing the precision of domain estimators by combining comparable information collected in multiple surveys of the same population. For this, we propose a regression method of estimation that is essentially an extended calibration procedure whereby comparable domain estimates from the various surveys are calibrated to each other. We show through analytic results and an empirical study that this method may greatly improve the precision of domain estimators for the variables that are common to these surveys, as these estimators make effective use of increased sample size for the common survey items. The design-based direct estimators proposed involve only domain-specific data on the variables of interest. This is in contrast with small domain (mostly small area) indirect estimators, based on a single survey, which incorporate through modelling data that are external to the targeted small domains. The approach proposed is also highly effective in handling the closely related problem of estimation for rare population characteristics.     

Combining information from related meta-analyses of genetic association studies

Summary.  When synthesizing data from genetic association studies researchers frequently perform several related meta-analyses, perhaps on different polymorphisms of the same gene, or on different outcomes, or they might define subgroups of studies by factors such as ethnicity, gender or study design. Current practice is to perform a totally separate meta-analysis of each set of studies; however, when the meta-analyses investigate related questions, it is possible that the estimates in one meta-analysis could be improved by using information from another. The meta-analytic model for a genetic association study can be parameterized in terms of four meaningful parameters: the size of the genetic effect, the genetic model, the allele frequency in controls and the degree of departure from Hardy–Weinberg equilibrium in controls. Even when the size of the genetic effect differs across meta-analyses, it may be possible to assume that some of the other parameters are common. The models are applied to a meta-analysis of the same gene–disease relationship in three different ethnic groups.     

Alternative estimators for the population totals in multiple characteristic surveys

The problem of estimating the population totals of multiple characteristics using without replacement sampling design is addressed. The alternative estimators for the study characteristics which are unrelated or have the low correlations with the characteristic used in sample selection are suggested. The efficiency of the estimators under two super population models, approximating the situations in which both the characteristics are unrelated and also when they are related, is studed. A numerical investigation is also carried out to get insight into the performance of the estimators in real applications.     

Accounting for animal density gradients using independent information in distance sampling surveys

Distance sampling is extensively used for estimating animal density or abundance. Conventional methods assume that location of line or point transects is random with respect to the animal population, yet transects are often placed along linear features such as roads, rivers or shorelines that do not randomly sample the study region, resulting in biased estimates of abundance. If it is possible to collect additional data that allow an animal density gradient with respect to the transects to be modelled, we show how to extend the conventional distance sampling likelihood to give asymptotically unbiased estimates of density for the covered area. We illustrate the proposed methods using data for a kangaroo population surveyed by line transects laid along tracks, for which the true density is known from an independent source, and the density gradient with respect to the tracks is estimated from a sample of GPS collared animals. For this example, density of animals increases with distance from the tracks, so that detection probability is overestimated and density underestimated if the non-random location of transects is ignored. When we account for the density gradient, there is no evidence of bias in the abundance estimate. We end with a list of practical recommendations to investigators conducting distance sampling surveys where density gradients could be an issue.     

A Markov chain Monte Carlo algorithm for multiple imputation in large surveys

Important empirical information on household behavior and finances is obtained from surveys, and these data are used heavily by researchers, central banks, and for policy consulting. However, various interdependent factors that can be controlled only to a limited extent lead to unit and item nonresponse, and missing data on certain items is a frequent source of difficulties in statistical practice. More than ever, it is important to explore techniques for the imputation of large survey data. This paper presents the theoretical underpinnings of a Markov chain Monte Carlo multiple imputation procedure and outlines important technical aspects of the application of MCMC-type algorithms to large socio-economic data sets. In an illustrative application it is found that MCMC algorithms have good convergence properties even on large data sets with complex patterns of missingness, and that the use of a rich set of covariates in the imputation models has a substantial effect on the distributions of key financial variables.     

A class of estimators using auxiliary information in sample surveys

A large class of estimators is considered for the mean of a finite population using information on an auxiliary variable. It is shown that members of this class of estimators are asymptotically no more efficient than the linear regression estimator.     

Improvement over variance estimation using auxiliary information in sample surveys

This paper addresses the problem of estimating the population variance S²_y of the study variable y using auxiliary information in sample surveys. We have suggested a class of estimators of the population variance S²_y of the study variable y when the population variance S²_x of the auxiliary variable x is known. Asymptotic expressions of bias and mean squared error (MSE) of the proposed class of estimators have been obtained. Asymptotic optimum estimators in the proposed class of estimators have also been identified along with its MSE formula. A comparison has been provided. We have further provided the double sampling version of the proposed class of estimators. The properties of the double sampling version have been provided under large sample approximation. In addition, we support the present study with aid of a numerical illustration.     

Finite mixture models with concomitant information: assessing diagnostic criteria for diabetes

The World Health Organization (WHO) diagnostic criteria for diabetes mellitus were determined in part by evidence that in some populations the plasma glucose level 2 h after an oral glucose load is a mixture of two distinct distributions. We present a finite mixture model that allows the two component densities to be generalized linear models and the mixture probability to be a logistic regression model. The model allows us to estimate the prevalence of diabetes and sensitivity and specificity of the diagnostic criteria as a function of covariates and to estimate them in the absence of an external standard. Sensitivity is the probability that a test indicates disease conditionally on disease being present. Specificity is the probability that a test indicates no disease conditionally on no disease being present. We obtained maximum likelihood estimates via the EM algorithm and derived the standard errors from the information matrix and by the bootstrap. In the application to data from the diabetes in Egypt project a two-component mixture model fits well and the two components are interpreted as normal and diabetes. The means and variances are similar to results found in other populations. The minimum misclassification cutpoints decrease with age, are lower in urban areas and are higher in rural areas than the 200 mg dl^-1 cutpoint recommended by the WHO. These differences are modest and our results generally support the WHO criterion. Our methods allow the direct inclusion of concomitant data whereas past analyses were based on partitioning the data.     

Bayesian weighted inference from surveys

Data from large surveys are often supplemented with sampling weights that are designed to reflect unequal probabilities of response and selection inherent in complex survey sampling methods. We propose two methods for Bayesian estimation of parametric models in a setting where the survey data and the weights are available, but where information on how the weights were constructed is unavailable. The first approach is to simply replace the likelihood with the pseudo likelihood in the formulation of Bayes theorem. This is proven to lead to a consistent estimator but also leads to credible intervals that suffer from systematic undercoverage. Our second approach involves using the weights to generate a representative sample which is integrated into a Markov chain Monte Carlo (MCMC) or other simulation algorithms designed to estimate the parameters of the model. In the extensive simulation studies, the latter methodology is shown to achieve performance comparable to the standard frequentist solution of pseudo maximum likelihood, with the added advantage of being applicable to models that require inference via MCMC. The methodology is demonstrated further by fitting a mixture of gamma densities to a sample of Australian household income.     

A new approach to use multivariate auxiliary information in sample surveys

A new approach to form multivariate difference estimator is suggested which does not require the knowledge of unknown population parameters as such. It gives minimum variance among the class of multivariate difference estimators. The performance of this estimator with respect to Des Raj's (J. Amer. Statist. Assoc. 60 (1965), 270–277) multivariate difference estimator is illustrated. Using the information on two auxiliary variates, the robustness of Des Raj's estimator y_d is studied empirically. Two new estimators to estimate population mean/total are developed on the same lines as that of y_d. The performance of these estimators is studied for a wide variety of populations.     

Unbiased estimators of finite population variance using auxiliary information in sample surveys

We present some unbiased estimators of the population variance in a finite population sample survey using the knowledge of population variance of an auxiliary character.Exact variance expressions for the proposed estimators are obtained and compared with usual unbiased estimator and the ratio estimator envisaged by Isaki (1983). Generalization of the proposed estimator is also suggested.     

Post-randomization for controlling identification risk in releasing microdata from general surveys

Before releasing survey data, statistical agencies usually perturb the original data to keep each survey unit''s information confidential. One significant concern in releasing survey microdata is identity disclosure, which occurs when an intruder correctly identifies the records of a survey unit by matching the values of some key (or pseudo-identifying) variables. We examine a recently developed post-randomization method for a strict control of identification risks in releasing survey microdata. While that procedure well preserves the observed frequencies and hence statistical estimates in case of simple random sampling, we show that in general surveys, it may induce considerable bias in commonly used survey-weighted estimators. We propose a modified procedure that better preserves weighted estimates. The procedure is illustrated and empirically assessed with an application to a publicly available US Census Bureau data set.     

Bias-calibrated estimation from sample surveys containing outliers

We discuss the problem of estimating finite population parameters on the basis of a sample containing representative outliers. We clarify the motivation for Chambers's bias-calibrated estimator of the population total and show that bias calibration is a key idea in constructing estimators of finite population parameters. We then link the problem of estimating the population total to distribution function or quantile estimation and explore a methodology based on the use of Chambers's estimator. We also propose methodology based on the use of robust estimates and a bias-calibrated form of the Chambers and Dunstan estimator of the population distribution function. This proposal leads to a bias-calibrated estimator of the population total which is an alternative to that of Chambers. We present a small simulation study to illustrate the utility of these estimators.     

Estimation from incomplete data in longitudinal surveys

In longitudinal surveys where a number of observations have to be made on the same sampling unit at specified time intervals, it is not uncommon that observations for some of the time stages for some of the sampled units are found missing. In the present investigation an estimation procedure for estimating the population total based on such incomplete data from multiple observations is suggested which makes use of all the available information and is seen to be more efficient than the one based on only completely observed units. Estimators are also proposed for two other situations; firstly when data is collected only for a sample of time stages and secondly when data is observed for only one time stage per sampled unit.     

Admissible and optimal sampling strategy for estimating finite population mean in randomized response surveys with multiple responses

ABSTRACT

We consider the problem of estimation of a finite population mean (or proportion) related to a sensitive character under a randomized response model when independent responses are obtained from each sampled individual as many times as he/she is selected in the sample and prove the admissibility of a sampling strategy in a class of comparable linear unbiased strategies. We prove that the admissible strategy is also optimal in this class under a super-population model.     

Inferences on missing information under multiple imputation and two-stage multiple imputation

In the presence of missing values, researchers may be interested in the rates of missing information. The rates of missing information are (a) important for assessing how the missing information contributes to inferential uncertainty about, Q, the population quantity of interest, (b) are an important component in the decision of the number of imputations, and (c) can be used to test model uncertainty and model fitting. In this article I will derive the asymptotic distribution of the rates of missing information in two scenarios: the conventional multiple imputation (MI), and the two-stage MI. Numerically I will show that the proposed asymptotic distribution agrees with the simulated one. I will also suggest the number of imputations needed to obtain reliable missing information rate estimates for each method, based on the asymptotic distribution.     

A graphical summary of disparities in health care and related summary measures

In order to assess the effectiveness of government programs designed to reduce disparities in the health care minority groups receive relative to the majority white population, a proper statistical measure should be used. This article proposes a measure of and its accompanying graph, which is readily interpretable and is not affected by the number of minority subgroups examined.