• Journal of the Korean Data and Information Science Society
• /
• v.16 no.3
• /
• pp.591-601
• /
• 2005

In this paper we consider detection of a discontinuity point in the variance function. When the mean function is discontinuous at a point, the variance function is usually discontinuous at the point. In this case, we had better estimate the location of the discontinuity point with the mean function rather than the variance function. On the other hand, the variance function only has a discontinuity point. The target function in order to estimate the location can be used the second moment function since the variance function and the second moment function have the same location and jump size of the discontinuity point. We propose a nonparametric detection method of the discontinuity point with the second moment function. We give the asymptotic results of these estimators. Computer simulation demonstrates the improved performance of the method over the existing ones.

• Journal of the Korea Society for Simulation
• /
• v.8 no.2
• /
• pp.1-11
• /
• 1999

Advanced information communication processing system mainly consists of network access subsystems and a switching system. This paper provides performance analysis of a typical network access subsystem. The network access subsystem is modeled as a queueing network including a server providing polling services. The arrival process of messages to an input buffer is regarded as a Poisson process. Performance measures such as mean input buffer length and mean waiting time of meassages are obtained through simulation, for it is impossible to calculate the performance measures using an analytical method. Hybrid simulation is used to reduce the variance of estimators. The variance reduction effect on the mean waiting time is reported.

• Journal of Applied Reliability
• /
• v.11 no.3
• /
• pp.213-224
• /
• 2011

In this paper, we analyze statistically the data set of first leak time of water pipeline. We classify first the leak time data by pipe type, location, diameter of pipe and, length of pipe. We perform the analysis of variance to indicate that there are significant difference of mean of the time between levels of the factor and also compare the distribution of levels using the multiple box-plot. When there are the difference of the mean, we perform the least significant test to find out what levels of the facor has a different mean.

• Journal of the Korean Statistical Society
• /
• v.28 no.4
• /
• pp.435-441
• /
• 1999

A 'convergence in probability' rate of the empirical distributions and quantiles of linear processes is obtained. As an application of the limit theorems, a trimmed mean for the location of the linear process is considered. It is shown that the trimmed mean is asymptotically normal. A consistent estimator for the asymptotic variance of the trimmed mean is provided.

• Communications for Statistical Applications and Methods
• /
• v.20 no.4
• /
• pp.247-257
• /
• 2013

A variety of practical problems can be addressed in the framework of rotation (successive) sampling. The present work presents a sample rotation pattern where sampling units are drawn on two successive occasions. The problem of estimation of population variance on current (second) occasion in two - occasion successive (rotation) sampling has been considered. A class of estimators has been proposed for population variance that includes many estimators as a particular case. Asymptotic properties of the proposed class of estimators are discussed. The proposed class of estimators is compared with the sample variance estimator when there is no matching from the previous occasion. Optimum replacement policy is discussed. Results are supported with the empirical means of comparison.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.1
• /
• pp.11-24
• /
• 2009

The process controller in the adjustment procedure is often used effectively to control the process level close to target when noise is present and unremovable. Examples of the robust controller are single EWMA controller and double EWMA controller. Double EWMA controller is designed to reduce the offset of the process deviation, which single EWMA can not eliminate. In this paper, the two controllers are modified by taking EWMA of the original controller to reduce the adjustment variance, which may become excessively large when the two given controllers are implemented. It is shown that the EWMA modification of the given controllers is successful in reducing the adjustment variance, while the mean squared deviation increases slightly.

• The Korean Journal of Applied Statistics
• /
• v.21 no.1
• /
• pp.177-182
• /
• 2008

There are times when we need more sample to achieve a more accurate estimator. Since these two sets of sample have the information about the same population, it is necessary to treat both as a single combined data. In this paper we present the unpooled sample variance for the combined data when we just know a sample mean and variance for the each data set without the raw data. It is shown that the pooled variance $s^2_p$ is always greater than the exact variance $s^2_t$ when ${\bar{x}}_n\;=\;{\bar{y}}_m$. And the difference of means for two data, ${\bar{x}}_n-{\bar{y}}_m}$, is larger, the difference of $s^2_p$ and $s^2_t$ is larger.

• Communications for Statistical Applications and Methods
• /
• v.31 no.1
• /
• pp.1-35
• /
• 2024

The assumption of homoscedasticity is one of the most crucial assumptions for many parametric tests used in the biological sciences. The aim of this paper is to compare the empirical probability of type I error and the power of ten parametric and two non-parametric tests for homoscedasticity with simulations under different types of distributions, number of groups, number of samples per group, variance ratio and significance levels, as well as through empirical data from an agricultural experiment. According to the findings of the simulation study, when there is no violation of the assumption of normality and the groups have equal variances and equal number of samples, the Bhandary-Dai, Cochran's C, Hartley's Fmax, Levene (trimmed mean) and Bartlett tests are considered robust. The Levene (absolute and square deviations) tests show a high probability of type I error in a small number of samples, which increases as the number of groups rises. When data groups display a nonnormal distribution, researchers should utilize the Levene (trimmed mean), O'Brien and Brown-Forsythe tests. On the other hand, if the assumption of normality is not violated but diagnostic plots indicate unequal variances between groups, researchers are advised to use the Bartlett, Z-variance, Bhandary-Dai and Levene (trimmed mean) tests. Assessing the tests being considered, the test that stands out as the most well-rounded choice is the Levene's test (trimmed mean), which provides satisfactory type I error control and relatively high power. According to the findings of the study and for the scenarios considered, the two non-parametric tests are not recommended. In conclusion, it is suggested to initially check for normality and consider the number of samples per group before choosing the most appropriate test for homoscedasticity.

• The Korean Journal of Financial Management
• /
• v.26 no.1
• /
• pp.165-188
• /
• 2009

This paper has suggested the methodology for the frontier portfolios and the optimal portfolio under the mean-VaR framework, not assuming the normal distribution and considering the investor's preferences for the higher moments of return distributions. It suggested the grid and rank approach which did not need an assumption about return distributions to find the frontier portfolios. And the optimal portfolio was selected using the utility function that considered the 3rd and the 4th moments. For the application of the methodology, weekly returns of the developed countries index, the emerging market index and the KOSPI index were used. After the frontier portfolios of the mean-variance framework and the mean-VaR framework were selected, the optimal portfolios of each framework were compared. This application compared not only the difference of the standard deviation but also the difference of the utility level and the certainty equivalent expressed by weekly expected returns. In order to verify statistical significances about the differences between the mean-VaR and the mean-variance, this paper presented the statistics which were obtained by the historical simulation method using the bootstrapping. The results showed that an investor under the mean-VaR framework had a tendency to select the optimal portfolio which has bigger standard deviation, comparing to an investor under the mean-variance framework. In addition, the more risk averse an investor is, the bigger utility level and certainty equivalent he achieves under the mean-VaR framework. However, the difference between the two frameworks were not significant in statistical as well as economic criterion.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.3
• /
• pp.95-100
• /
• 2020

Machines and facilities are physically or chemically degenerated by continuous usage. One of the results of this degeneration is the process mean shift. The representative type of the degeneration is wear of tool or machine. According to the increasing wear level, non-conforming products cost and quality loss cost are increasing simultaneously. Therefore a periodic preventive resetting the process is necessary. The total cost consists of three items: adjustment cost (or replacement cost), non-conforming cost due to product out of upper or lower limit specification, and quality loss cost due to difference from the process target value and the product characteristic value among the conforming products. In this case, the problem of determining the adjustment period or wear limit that minimizes the total cost is called the 'process mean shift' problem. It is assumed that both specifications are set and the wear level can be observed directly. In this study, we propose a new model integrating the quality loss cost, process variance, and production volume, which has been conducted in different fields in previous studies. In particular, for the change in production volume according to the increasing in wear level, we propose a generalized production quantity function g(w). This function can be applied to most processes and we fitted the g(w) to the model. The objective equation of this model is the total cost per unit wear, and the determining variables are the wear limit and initial process setting position that minimize the objective equation.