A functional marked point process model for lupus data

Modelling for marked point processes is an important problem, but has received remarkably little attention in the statistical literature. The authors developed a marked point process model that incorporates the use of functional data analysis in a joint estimation of the frequency function of the point process and the intensity of the mark, with application to data from 22 lupus patients consisting of times of flares in symptom severity combined with a quantitative assessment of the severity. The data indicate that a rapid decrease in drug dose is significantly associated with a decrease in flare frequency. Experiments with simulated data designed to model the actual data further support this conclusion. The Canadian Journal of Statistics 40: 517–529; 2012 © 2012 Statistical Society of Canada     

A variant of the Geo/G/1 queues with disasters and general repair times

Abstract

This paper deals with Geo/G/1 queues with a repairable server. The server is subject to failure due to a disaster arrival, which can occur while the server is turned on and not only when it is busy. At a failure instant, the server is turned off and its repair process begins. During the repair process, two models are considered. For both models, we present the PGF and the expected number of clients in the system in the steady state.     

COMBINING INDIVIDUAL PARTICIPANT DATA AND SUMMARY STATISTICS FROM BOTH CONTINUOUSLY VALUED AND BINARY VARIABLES TO ESTIMATE REGRESSION PARAMETERS

Recent research has extended standard methods for meta‐analysis to more general forms of evidence synthesis, where the aim is to combine different data types or data summaries that contain information about functions of multiple parameters to make inferences about the parameters of interest. We consider one such scenario in which the goal is to make inferences about the association between a primary binary exposure and continuously valued outcome in the context of several confounding exposures, and where the data are available in various different forms: individual participant data (IPD) with repeated measures, sample means that have been aggregated over strata, and binary data generated by thresholding the underlying continuously valued outcome measure. We show that an estimator of the population mean of a continuously valued outcome can be constructed using binary threshold data provided that a separate estimate of the outcome standard deviation is available. The results of a simulation study show that this estimator has negligible bias but is less efficient than the sample mean – the minimum variance ratio is based on a Taylor series expansion. Combining this estimator with sample means and IPD from different sources (such as a series of published studies) using both linear and probit regression does, however, improve the precision of estimation considerably by incorporating data that would otherwise have been excluded for being in the wrong format. We apply these methods to investigate the association between the G277S mutation in the transferrin gene and serum ferritin (iron) levels separately in pre‐ and post‐menopausal women based on data from three published studies.     

DUAL‐OBJECTIVE OPTIMAL MIXTURE DESIGNS

Mixture experiments are widely used in many industries and particularly in the manufacture of consumer products. Almost all work to date assumes a single study objective, which is unrealistic. Researchers may want to estimate model parameters and make predictions or extrapolations at the same time. We discuss design issues for determining the optimal proportions of the mixture components when there are two or more objectives in the study and there is a large sample size. We present a general methodology for constructing two types of dual‐objective optimal design for mixture experiments and discuss the general applicability of the design strategy to more complicated types of mixture design problems, including mixture experiments.     

Macroeconomic and financing determinants of out of pocket payments in health care: Evidence from selected OECD countries

In this paper, we examine the impact of macroeconomic, as well public and private health insurance financing (PHI) factors on out of pocket (OOP) healthcare expenditures, by using fixed/random effects and dynamic panel data methodology to a dataset of 26 EU and OECD countries for a period lasting from 1995 to 2013. The existing empirical literature has focused on testing the hypothesis that several macroeconomic and health financing determinants have an effect on OOP healthcare expenditures. Nevertheless, the related articles have not well tested the hypothesis concerning the potential impact of PHI financing on OOP spending. We find that public and PHI financing have a significant countervailing effect on OOP spending. Moreover, we show that unemployment rate has a significant positive impact on OOP expenditures. Sensitivity tests with variation of specifications and samples show that our findings are robust. We argue that policy-makers should give serious consideration to PHI institution; our results indicate that there is an inverse effect on OOP spending. We suggest that our examined countries have to provide financial risk protection to their citizens against OOP payments, rather than only attending health budgetary retrenchments in order to adjust public finances.     

Corporate ownership,efficiency and performance under state capitalism: Evidence from China

This paper studied the relationship between business performance and the ownership structure of firms focusing on Chinese state owned enterprises (SOEs) using a firm level panel data set of China from 1999 to 2011. By classifying all firms into different types based on their ultimate controlling shareholders, we found that SOEs in general underperform in the marketplace than private enterprises. However, among the SOEs in our sample, the SOEs controlled by central government outperformed all types of firms because they offered the highest asset turnover ratio and lowest business administration ratio by receiving favourable government treatment. We conclude that firm ownership type and work efficiency are the main factors that influence the differences in firm performance. In particular, the performance of SOEs controlled by central government is greatly determined by the degree of government intervention, which is referred to as State Capitalism.     

Limit behaviors of the estimator of nonparametric regression model based on martingale difference errors

In the paper, we shall establish some limit theorems for the nonparametric estimator of the regression model, which include $L^p$-convergence, complete convergence, and strong convergence of the estimator. These results supplement and improve some known works.     

Robust adaptive model selection and estimation for partial linear varying coefficient models in rank regression

Partial linear varying coefficient models are often used in real data analysis for a good balance between flexibility and parsimony. In this paper, we propose a robust adaptive model selection method based on the rank regression, which can do simultaneous coefficient estimation and three types of selections, i.e., varying and constant effects selection, relevant variable selection. The new method has superiority in robustness and efficiency by inheriting the advantage of the rank regression approach. Furthermore, consistency in the three types of selections and oracle property in estimation are established as well. Simulation studies also confirm our method.