• Communications for Statistical Applications and Methods
• /
• v.15 no.1
• /
• pp.27-41
• /
• 2008

A graphical method of checking the adequacy of a generalized linear model is proposed. The graph helps to assess the assumption that the link function of mean can be expressed as a linear combination of explanatory variables in the generalized linear model. For the graph the boosting technique is applied to estimate nonparametrically the relationship between the link function of the mean and the explanatory variables, though any other nonparametric regression methods can be applied. Through simulation studies with normal and binary data, the effectiveness of the graph is demonstrated. And we list some limitations and technical details of the graph.

• The Korean Journal of Applied Statistics
• /
• v.29 no.1
• /
• pp.171-180
• /
• 2016

Basel committee suggests using Value-at-Risk (VaR) and expected shortfall (ES) as a measurement for market risk. Various estimation methods of VaR and ES have been studied in the literature. This paper compares semi-parametric methods, such as conditional autoregressive value at risk (CAViaR) and conditional autoregressive expectile (CARE) methods, and a Gaussian quasi-maximum likelihood estimator (QMLE)-based method through back-testing methods. We use unconditional coverage (UC) and conditional coverage (CC) tests for VaR, and a bootstrap test for ES to check the adequacy. A real data analysis is conducted for S&P 500 index and Hyundai Motor Co. stock price index data sets.

• Communications for Statistical Applications and Methods
• /
• v.17 no.2
• /
• pp.275-292
• /
• 2010

Receiver operating characteristic(ROC) curves can be used to assess the accuracy of tests measured on ordinal or continuous scales. The most commonly used measure for the overall diagnostic accuracy of diagnostic tests is the area under the ROC curve(AUC). When two ROC curves are constructed based on two tests performed on the same individuals, statistical analysis on differences between AUCs must take into account the correlated nature of the data. This article focuses on confidence interval estimation of the difference between paired AUCs. We compare nonparametric, maximum likelihood, bootstrap and generalized pivotal quantity methods, and conduct a monte carlo simulation to investigate the probability coverage and expected length of the four methods.

• The Korean Journal of Applied Statistics
• /
• v.27 no.5
• /
• pp.755-771
• /
• 2014

Isotropy is one of the main assumptions for the ease of spatial prediction (named kriging) based on some covariance models. A lack of isotropy (or anisotropy) in a spatial process necessitates that some additional parameters (angle and ratio) for anisotropic covariance model be obtained in order to produce a more reliable prediction. In this paper, we propose a new class of geometrically extended anisotropic covariance models expressed as a weighted average of some geometrically anisotropic models. The maximum likelihood estimation method is taken into account to estimate the parameters of our interest. We evaluate the performances of our proposal and compare it with an isotropic covariance model and a geometrically anisotropic model in simulation studies. We also employ extended geometric anisotropy to the analysis of real data.

• The Korean Journal of Applied Statistics
• /
• v.19 no.1
• /
• pp.1-12
• /
• 2006

The aim of this study is to analyse a survey data on the number of charitable donations using a mixture of two Poisson regression models. The survey was conducted in 2002 by Volunteer 21, an nonprofit organization, based on Koreans, who were older than 20. The mixture of two Poisson distributions is used to model the number of donations based on the empirical distribution of the data. The mixture of two Poisson distributions implies the whole population is subdivided into two groups, one with lesser number of donations and the other with larger number of donations. We fit the mixture of Poisson regression models on the number of donations to identify significant covariates. The expectation-maximization algorithm is employed to estimate the parameters. We computed 95% bootstrap confidence interval based on bias-corrected and accelerated method and used then for selecting significant explanatory variables. As a result, the income variable with four categories and the volunteering variable (1: experience of volunteering, 0: otherwise) turned out to be significant with the positive regression coefficients both in the lesser and the larger donation groups. However, the regression coefficients in the lesser donation group were larger than those in larger donation group.