• Bulletin of the Korean Mathematical Society
• /
• v.53 no.2
• /
• pp.351-363
• /
• 2016

In this paper, we consider the entropy-based goodness of fit test (Vasicek's test) for a composite hypothesis. The test measures the discrepancy between the nonparametric entropy estimate and the parametric entropy estimate obtained from an assumed parametric family of distributions. It is shown that the proposed test is asymptotically normal under regularity conditions, but is affected by parameter estimates. As a remedy, a bootstrap version of Vasicek's test is proposed. Simulation results are provided for illustration.

• The Journal of Fisheries Business Administration
• /
• v.47 no.1
• /
• pp.63-86
• /
• 2016

The purpose of this study is to investigate production efficiency of Oceans and Fisheries Human Resources Development Programs Efficiency using Bootstrap-DEA. The study extracts 33 officials curriculum, 11 fisheries managers curriculum for its analytical. First, the study estimates technical, pure technical, and scale efficiency of each curriculums based on traditional DEA under the assumption of CRS and VRS. 8(official 7, managers 1) curriculums are identified as efficient DMUs under the CCR-model, and 13(official 10, managers 3) under the BCC-model. We provide inputs that allow inefficient curriculum to be efficient DMUs on a production frontier, and a reference set for their bench-marking. Second, rank test, Wilcoxon-Mann-Whitney test to find a statistical significance of heterogeneity existing in efficiences between Bootstrap-DEA tenical vs Bootstrap-DEA pure technical was no significant difference. We have identified that G10, 11, 12 13, 25, 31, 33, 39 curriculums are the most efficiently produced in the technical and pure technical efficiency. Also we managed to measure the inefficiency which exists in efficiently produced curriculums when estimating the bias corrected efficiency scores. In Technical efficiency, Operation and facility was significant at the 10%. In Pure technical efficiency, facility was significant at the 10%.

• Communications for Statistical Applications and Methods
• /
• v.11 no.3
• /
• pp.643-655
• /
• 2004

L$_1$-estimator in the linear regression model is widely recognized to have superior robustness in the presence of vertical outliers. While the L$_1$-estimation procedures and algorithms have been developed quite well, less progress has been made with the hypothesis test in the multiple L$_1$-regression. This article suggests computer-intensive resampling approaches, jackknife and bootstrap methods, to estimating the variance of L$_1$-estimator and the scale parameter that are required to compute the test statistics. Monte Carlo simulation studies are performed to measure the power of tests in small samples. The simulation results indicate that bootstrap estimation method is the most powerful one when it is employed to the likelihood ratio test.

• Journal of the Korean Data and Information Science Society
• /
• v.13 no.1
• /
• pp.129-137
• /
• 2002

Two-sample problem is frequently discussed problem in statistics. In this paper we consider the hypothese methods for the general two-sample problem and suggest the bootstrap methods. And we show that the modified Kolmogorov-Smirnov test is more efficient than the Kolmogorov-Smirnov test.

• The Korean Journal of Applied Statistics
• /
• v.29 no.1
• /
• pp.61-73
• /
• 2016

We consider the wild bootstrap Ljung-Box (LB) test for autocorrelation in residuals of fitted multivariate time series models. The asymptotic chi-square distribution under the IID assumption is traditionally used for the LB test; however, size distortion tends to occur in the usage of the LB test, due to the conditional heteroskedasticity of financial time series. In order to overcome such defects, we propose the wild bootstrap LB test for autocorrelation in residuals of fitted vector autoregressive and error correction models. The simulation study and real data analysis are conducted for finite sample performance.

• Journal of Korean Society for Quality Management
• /
• v.24 no.2
• /
• pp.77-86
• /
• 1996

In this paper, we consider the problem of testing independence in the absolutely continuous bivariate exponential distribution of Block and Basu(1974). We construct a bootstrap procedure for testing zero and non-zero values of the parameter ${\lambda}_3$ which measures the degree of dependence and compare the power of the bootstrap test with likelihood ratio test(LRT) by Gupta et al.(1984) and the test based on maximum likelihood estimator(MLE) $\hat{{\lambda}}_3$ by Hanagal and Kale(1991) for small and moderate sample sizes.

• Journal of Korea Water Resources Association
• /
• v.42 no.10
• /
• pp.795-807
• /
• 2009

In this study, homogeneity analysis was performed between rainfall observation data set of Chukwooki (CWK) and rainfall observation data set of modern rain gage (MRG) using Bootstrap method. Since traditional statistical homogeneity test method are validated only when distribution of their population is known, meteorological data which their statistical distributions of population are complicated were difficult to verify the homogeneity and there were plenty of room for doubt for their statistical significance using historical method. In this reason, in this study homogeneity test was evaluated between two data sets using bootstrap method which is not necessary to infer distribution of population. The test results show that there was an statistical homogeneity between CWK and MRG except for slight impact of climatical trend.

• Journal of the Korean Statistical Society
• /
• v.27 no.4
• /
• pp.495-506
• /
• 1998

The proposed class of generalized logistic models, indexed by an extra parameter, can be used to model or to examine symmetric or asymmetric discrepancies from the logistic model. When there are a finite number of different design points, we are mainly concerned with maximum likelihood estimation of parameters and in deriving their large sample behavior A score test and a bootstrap hypothesis test are also considered to check if the standard logistic model is appropriate to fit the data or if a generalization is needed .

• Journal of the Korean Statistical Society
• /
• v.30 no.4
• /
• pp.645-660
• /
• 2001

In this paper we propose a goodness-of-fit test statistic for testing the (null) parametric model versus the (alternative) nonparametric model. Most of existing nonparametric test statistics are based on the residuals which are obtained by regressing the data to a parametric model. Our test is based on the bootstrap estimator of the probability that the smoothing parameter estimator is infinite when fitting residuals to cubic smoothing spline. Power performance of this test is investigated and is compared with many other tests. Illustrative examples based on real data sets are given.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.25 no.4
• /
• pp.1-7
• /
• 2002

Statistical process control is used widely as an effective tool to solve the quality problems in practice fields. All the control charts used in statistical process control are parametric methods, suppose that the process distributes normal and observations are independent. But these assumptions, practically, are often violated if the test of normality of the observations is rejected and/or the serial correlation is existed within observed data. Thus, in this study, to screening process, the Combined Shewhart - CUSUM quality control chart is described and evaluated that used bootstrap method. In this scheme the CUSUM chart will quickly detect small shifts form the goal while the addition of Shewhart limits increases the speed of detecting large shifts. Therefor, the CSC control chart is detected both small and large shifts in process, and the simulation results for its performance are exhibited. The bootstrap CSC control chart proposed in this paper is superior to the standard method for both normal and skewed distribution, and brings in terms of ARL to the same result.