Shonosuke Sugasawa

Parametric transformed Fay-Herriot model for small area estimation

Motivated from analysis of positive data such as income, revenue, harvests and production, the paper suggests the parametric transformed Fay-Herriot model in small-area estimation. When the dual power transformation is used as the parametric transformation, we provide consistent estimators of the transformation parameter, the regression coefficients and the variance component. The empirical best linear unbiased predictors which plug in those consistent estimators are suggested, and their mean squared errors (MSE) are asymptotically evaluated. A second-order unbiased estimator of the MSE is also given through the parametric bootstrap. Finally, performances of the suggested procedures are investigated through simulation and empirical studies.

On conditional prediction errors in mixed models with application to small area estimation

The empirical Bayes estimators in mixed models are useful for small area estimation in the sense of increasing precision of prediction for small area means, and one wants to know the prediction errors of the empirical Bayes estimators based on the data. This paper is concerned with conditional prediction errors in the mixed models instead of conventional unconditional prediction errors. In the mixed models based on natural exponential families with quadratic variance functions, it is shown that the difference between the conditional and unconditional prediction errors is significant under distributions far from normality. Especially for the binomial-beta mixed and the Poisson-gamma mixed models, the leading terms in the conditional prediction errors are, respectively, a quadratic concave function and an increasing function of the direct estimate in the small area, while the corresponding leading terms in the unconditional prediction errors are constants. Second-order unbiased estimators of the conditional prediction errors are also derived and their performances are examined through simulation and empirical studies.

Bayesian estimators in uncertain nested error regression models

Nested error regression models are useful tools for the analysis of grouped data, especially in the context of small area estimation. This paper suggests a nested error regression model using uncertain random effects in which the random effect in each area is expressed as a mixture of a normal distribution and a positive mass at0. For the estimation of the model parameters and prediction of the random effects, an objective Bayesian inference is proposed by setting non-informative prior distributions on the model parameters. Under mild sufficient conditions, it is shown that the posterior distribution is proper and the posterior variances are finite, confirming the validity of posterior inference. To generate samples from the posterior distribution, a Gibbs sampling method is provided with familiar forms for all the full conditional distributions. This paper also addresses the problem of predicting finite population means, and a sampling-based method is suggested to tackle this issue. Finally, the proposed model is compared with the conventional nested error regression model through simulation and empirical studies.

Transforming response values in small area prediction

In real applications of small area estimation, one often encounters data with positive response values. The use of a parametric transformation for positive response values in the Fay-Herriot model is proposed for such a case. An asymptotically unbiased small area predictor is derived and a second-order unbiased estimator of the mean squared error is established using the parametric bootstrap. Through simulation studies, a finite sample performance of the proposed predictor and the MSE estimator is investigated. The methodology is also successfully applied to Japanese survey data.

Latent mixture modeling for clustered data

This article proposes a mixture modeling approach to estimating cluster-wise conditional distributions in clustered (grouped) data. We adapt the mixture-of-experts model to the latent distributions, and propose a model in which each cluster-wise density is represented as a mixture of latent experts with cluster-wise mixing proportions distributed as Dirichlet distribution. The model parameters are estimated by maximizing the marginal likelihood function using a newly developed Monte Carlo Expectation–Maximization algorithm. We also extend the model such that the distribution of cluster-wise mixing proportions depends on some cluster-level covariates. The finite sample performance of the proposed model is compared with some existing mixture modeling approaches as well as mixed effects models through the simulation studies. The proposed model is also illustrated with the posted land price data in Japan.

Exploring predictive biomarkers from clinical genome-wide association studies via multidimensional hierarchical mixture models

Although the detection of predictive biomarkers is of particular importance for the development of accurate molecular diagnostics, conventional statistical analyses based on gene-by-treatment interaction tests lack sufficient statistical power for this purpose, especially in large-scale clinical genome-wide studies that require an adjustment for multiplicity of a huge number of tests. Here we demonstrate an alternative efficient multi-subgroup screening method using multidimensional hierarchical mixture models developed to overcome this issue, with application to stroke and breast cancer randomized clinical trials with genomic data. We show that estimated effect size distributions of single nucleotide polymorphisms (SNPs) associated with outcomes, which could provide clues for exploring predictive biomarkers, optimizing individualized treatments, and understanding biological mechanisms of diseases. Furthermore, using this method we detected three new SNPs that are associated with blood homocysteine levels, which are strongly associated with the risk of stroke. We also detected six new SNPs that are associated with progression-free survival in breast cancer patients.

An efficient and flexible test for rare variant effects

Since it has been claimed that rare variants with extremely small allele frequency play a crucial role in complex traits, there is great demand for the development of a powerful test for detecting these variants. However, due to the extremely low frequencies of rare variants, common statistical testing methods do not work well, which has motivated recent extensive research on developing an efficient testing procedure for rare variant effects. Many studies have suggested effective testing procedures with reasonably high power under some presumed assumptions of parametric statistical models. However, if the parametric assumptions are violated, these tests are possibly under-powered. In this paper, we develop an optimal, powerful statistical test called the aggregated conditional score test (ACST) for simultaneously testing M rare variant effects without restrictive parametric assumptions. The proposed test uses a test statistic aggregating the conditional score statistics of effect sizes of M rare variants. In simulation studies, ACST generally performed well compared with the two most commonly used tests, the optimal sequence kernel association test (SKAT-O) and Kullback-Leibler distance test. Finally, we demonstrate the performance and practical utility of ACST using the Dallas Heart Study data.