• The Korean Journal of Applied Statistics
• /
• v.28 no.2
• /
• pp.189-200
• /
• 2015

Stationary bootstrapping is applied to a Lagrangian multiplier (LM) test to test market microstructure noise (MMN) in financial asset prices. A Monte-Carlo experiment shows that the bootstrapping method improves the size of the original LM test which has some size distortion for conditional heteroscedastic models. The proposed test is illustrated for real data sets like KOSPI index and Won-Dollar exchange rate.

• The Korean Journal of Applied Statistics
• /
• v.27 no.7
• /
• pp.1163-1170
• /
• 2014

The concepts and structure of intermittent panel time series data are introduced. We suggest a Wald test statistic for the test of homogeneity for intermittent panel first order autoregressive model and its limit distribution is derived. We consider the fitting the model with pooling data using sample mean at the time point if homogeneity for intermittent panel AR(1) is satisfied. We performed simulations to examine the limit distribution of the homogeneity test statistic for intermittent panel AR(1). In application, we fit the intermittent panel AR(1) for panel Mumps data and investigate the test of homogeneity.

• The Korean Journal of Applied Statistics
• /
• v.15 no.2
• /
• pp.415-421
• /
• 2002

Because most common assumption is normality in statistical analysis, testing normality is very important. We propose a new plot and test statistic to test for normality based on the modified Lorenz curve that is proved to be a powerful tool to measure the income inequality within a population of income receivers. We also compare the proposed test statistics with the W test (Shapiro and Wilk (1965)), TL test (Kang and Cho (1999)) in terms of the power of test through by Monte Carlo method. The proposed test is more usually powerful than the other tests except some case.

• Communications for Statistical Applications and Methods
• /
• v.10 no.1
• /
• pp.211-224
• /
• 2003

Good's lambda test, a permutation test used to detect the changes of microorganism composition under two pathological conditions, has been quite popular for studying the micro-flora responsible for periodontal disease. A vast number of different micro-flora in the mouth renders the traditional chi-square test inapplicable. The main purpose of this paper is to evaluate the power of this test so that the sample size can be determined at the design stage. The robustness of this test and its comparison to two other intuitive tests are also presented. It is found that a permutation test based on likelihood ratio is more powerful than the lambda test in our simulated cases.

• Communications for Statistical Applications and Methods
• /
• v.22 no.4
• /
• pp.377-387
• /
• 2015

The area under the ROC curve can be represented by both Mann-Whitney and Wilcoxon rank sum statistics. Consider an ROC surface and manifold equal to three dimensions or more. This paper finds that the volume under the ROC surface (VUS) and the hypervolume under the ROC manifold (HUM) could be derived as functions of both conditional Mann-Whitney statistics and conditional Wilcoxon rank sum statistics. The nullhypothesis equal to three distribution functions or more are identical can be tested using VUS and HUM statistics based on the asymptotic large sample theory of Wilcoxon rank sum statistics. Illustrative examples with three and four random samples show that two approaches give the same VUS and $HUM^4$. The equivalence of several distribution functions is also tested with VUS and $HUM^4$ in terms of conditional Wilcoxon rank sum statistics.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.2
• /
• pp.559-564
• /
• 2016

The Durbin-Watson (DW) test in regression model and the Ljung-Box (LB) test in ARMA (autoregressive moving average) model are typical examples of correlated error tests. The DW test is used for detecting autocorrelation of errors using the residuals from a regression analysis. The LB test is used for specifying the correct ARMA model using the first some sample autocorrelations based on the residuals of a tted ARMA model. In this article, simulations with four data generating processes have been carried out to evaluate their performances as correlated error tests. Our simulations show that the DW test is severely dependent on the assumed AR(1) model but isn't sensitive enough to reject the misspecified model and that the LB test reports lackluster performance in general.

• Communications for Statistical Applications and Methods
• /
• v.8 no.1
• /
• pp.137-145
• /
• 2001

There are many situations in which the well-known tests such as log-rank test and Gehan-Wilcoxon test fail to detect the survival differences. Assuming large samples, these tests are developed asymptotically normal properties. Thus, they shall be called asymptotic tests in this paper, Several asymptotic tests sensitive to some specific types of survival differences have been recently proposed. This paper compares by simulations the test levels and the powers of the conventional asymptotic tests and their random permutation versions. Simulation studies show that the random permutation tests possess competitive powers compared to the corresponding asymptotic tests, keeping exact test levels even in the small sample case. It also provides the guidelines for choosing the valid and most powerful test under the given situation.

• Journal of the Korean Statistical Society
• /
• v.25 no.3
• /
• pp.347-358
• /
• 1996

A new test for goodness-of-fit is presented. It is a modification of a test of LaRiccia (1991). These tests are applicable to continuous lo-cation/scale models. The new test statistic is based on a few selected order statistics taken from the sample, while the LaRiccia test is based directly on the full sample. Each test embeds the hypothesized model in a larger linear model and proceeds to test the goodness-of-fit hy-pothesis by testing the coefficients of this linear model appropriately. The general theory is presented. The tests are compared via computer simulation to a related test of Ali and Umbach (1989) for distributions that could be used as lifetime models. An important aspect of all these tests is that only standard $X_2$ tables are used. Selection of the spacings of the order statistics is discussed.

• Communications for Statistical Applications and Methods
• /
• v.23 no.2
• /
• pp.163-177
• /
• 2016

We consider a jump diffusion process for high-frequency financial asset data. We apply the stationary bootstrapping to construct a bootstrap test for jumps. First-order asymptotic validity is established for the stationary bootstrapping of the jump ratio test under the null hypothesis of no jump. Consistency of the stationary bootstrap test is proved under the alternative of jumps. A Monte-Carlo experiment shows the advantage of a stationary bootstrapping test over the test based on the normal asymptotic theory. The proposed bootstrap test is applied to construct continuous-jump decomposition of the daily realized variance of the KOSPI for the year 2008 of the world-wide financial crisis.

• Communications for Statistical Applications and Methods
• /
• v.30 no.3
• /
• pp.227-244
• /
• 2023

In this paper, a depth-based nonparametric test for a multivariate two-sample scale problem is proposed. The proposed test statistic is based on the depth-induced ranks and is thus distribution-free. In this article, the depth values of data points of one sample are calculated with respect to the other sample or distribution and vice versa. A comprehensive simulation study is used to examine the performance of the proposed test for symmetric as well as skewed distributions. Comparison of the proposed test with the existing depth-based nonparametric tests is accomplished through empirical powers over different depth functions. The simulation study admits that the proposed test outperforms existing nonparametric depth-based tests for symmetric and skewed distributions. Finally, an actual life data set is used to demonstrate the applicability of the proposed test.