• Journal of the Korean Data and Information Science Society
• /
• v.19 no.4
• /
• pp.1059-1071
• /
• 2008

In a balanced factorial design with a nested factor where crossed factors as well as a nested factor exist simultaneously, powers of the rank transformed FR statistic for testing the main, nested and interaction effects are superior to those of the parametric F statistic. In heavy tailed distributions such as exponential and double exponential distributions, powers of the FR statistic show much higher level than those of the F statistic. Further powers of the F and FR statistic for testing the main effect show the highest level in an absolute size as compared with powers of the F and FR statistic for testing the nested and interaction effects. However powers of the FR statistic for testing the nested and interaction effects rather than the main effect are greater in a relative size than powers of F statistic for the all population distributions.

• Journal of the Korean Statistical Society
• /
• v.30 no.4
• /
• pp.679-691
• /
• 2001

Two truncated sequential tests are developed for the two-sample scale problem based on the usual Wilcoxon rank-sum statistic for two different dispersion indices - absolute median deviations, when the medians of the two populations X and Y are equal or known and sums of squared mean deviations, when the medians are either unknown or unequal. The first test is briefly called SWAMD test and the second SWSMD test. For the SWAMD test, the percentile points for both the one-sided and two-sided alternatives, (equation omitted) have been found by Wiener approximation and their values computed for a range of values of a and N; analytical expression for the power function has been derived through Wiener process and its performance studied for various sequential designs for exponential distribution. This test has been illustrated by a numerical example. All the results of the SWAMD test, being directly applicable to the SWSMD test, are not dealt with separately Both the tests are compared and their suitable applications indicated.

• Communications for Statistical Applications and Methods
• /
• v.5 no.1
• /
• pp.133-144
• /
• 1998

In this paper, we propose the two-sample test statistic using Wilcoxon signed rank test on ranked-set sampling(RSS) and obtain the asymptotic relative efficiencies(ARE) of the proposed test statistic with respect to Mann-Whitney-Wilcoxon statistic on simple random sampling(SRS), the Mann-Whitney-Wilcoxon statistic on RSS, sign statistic on RSS and Wilcoxon signed rank test on SRS. From the simulation works, we compare the powers of the proposed test statistic, Mann-Whitney-Wilcoxon statistic on RSS, the usual two-sample t statistic, sign statistic on RSS, where the underlying distributions are uniform, normal, double exponential, logistic and Cauchy distributions.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.7
• /
• pp.1309-1314
• /
• 2007

The assignment of cells to reporting or non-reporting cells is an NP-hard problem having an exponential complexity in the Reporting Cell Location Management (RCLM) system. Frequent location update may result in degradation of quality of service due to interference. Miss on the location of a mobile terminal will necessitate a search operation on the network when a call comes in. The number of reporting cells and which cell must be reporting cell should be determined to balance the registration (location update) and search (paging) operations to minimize the cost of RCLM system. T1is paper compares Max-Min ant system (MMAS), rank-based ant system (RAS) and hybrid method of MMAS and RAS that generally used to solve combinatorial optimization problems. Experimental results demonstrate that hybrid method of MMAS and RAS is an effective and competitive approach in fairly satisfactory results with respect to solution quality and execution time for the optimal design of location management system.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.8
• /
• pp.735-743
• /
• 2002

In this paper, we propose three new text-independent speaker identification methods. At first, to exclude the frames not having enough features of speaker's vocal from calculation of the maximum likelihood, we propose the FS(Frame Selection) method. This approach selects the important frames by evaluating the difference between the biggest likelihood and the second in each frame, and uses only the frames in calculating the score of likelihood. Our secondly proposed, called the Hybrid, is a combined version of the FS and WMR(Weighting Model Rank). This method determines the claimed speaker using exponential function weights, instead of likelihood itself, only on the selected frames obtained from the FS method. The last proposed, called MWMR (Modified WMR), considers both original likelihood itself and its relative position, when the claimed speaker is determined. It is different from the WMR that take into account only the relative position of likelihood. Through the experiments of the speaker identification, we show that the all the proposed have higher identification rates than the ML. In addition, the Hybrid and MWMR have higher identification rate about 2% and about 3% than WMR, respectively.

• The Korean Journal of Applied Statistics
• /
• v.8 no.2
• /
• pp.87-97
• /
• 1995

When there is no main effcts or only one main effect in a $2 \times 2$ factorial design, Type I error rates and power for the rank transformed F test (FR test) for interaction are nearly equal to those of the classical F test. However the power of FR test is quite superior under the exponential distribution rather than the of FR test is quite superior under the exponential distribution rather than the normal distribution. Meanwhile when both main effects are in the model, Type I error rates of FR test, compared with those of F test, decrease as the effect size increases and are dependent on the fashion in which main effects are constructed. In addition, the power of FR test increases as the effect size and the sample size increase and is highly dependent on the manner in which main effects are constructed and the type of population distribution.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.6
• /
• pp.1225-1238
• /
• 2015

In this research, we fit various survival models and conduct tests and estimation for the hazard change-point with the rectal cancer data. By the log-rank tests, at significance level ${\alpha}=0.10$, survival functions are significantly different according to the uniporter of glucose (GLUT1), clinical stage (cstage) and pathologic stage (ypstage). From the Cox proportional hazard model, the most significant covariates are GLUT1 and ypstage. Assuming that the rectal cancer data follows the exponential distribution, we estimate one hazard change-point using Matthews and Farewell (1982), Henderson (1990) and Loader (1991) methods.

• Journal of the Korean Society of Safety
• /
• v.32 no.5
• /
• pp.115-121
• /
• 2017

This paper is to introduce the main modeling assumptions and data structures associated with right-censored data to describe the successful methodological ideas for analyzing such a field-failure-data when components operating in different environments. The Kaplan - Meier method is the most popular method used for survival analysis. Together with the log-rank test, it may provide us with an opportunity to estimate survival probabilities and to compare survival between groups. An important advantage of the Kaplan - Meier curve is that the method can take into account some types of censored data, particularly right-censoring. The above non-parametric method was used to verify the equality of parts life used in different environments. After that, we performed the life distribution analysis using the parametric method. We simulated data from three distributions: exponential, normal, and Weibull. This allowed us to compare the results of the estimates to the known true values and to quantify the reliability indices. Here we used the Akaike information criterion to find a suitable life time distribution. If the Akaike information criterion is the smallest, the best model of failure data is presented. In this paper, no-nparametrics and parametrics methods are analyzed using R program which is a popular statistical program.

• Communications for Statistical Applications and Methods
• /
• v.25 no.3
• /
• pp.283-296
• /
• 2018

Ranked set sampling, as introduced by McIntyre (Australian Journal of Agriculture Research, 3, 385-390, 1952), dealt with the estimation of the mean of one population. To deal with two or more variables, different forms of bivariate and multivariate ranked set sampling were suggested. For a technique to be useful, it should be easy to implement in practice. Bivariate ranked set sampling, as introduced by Al-Saleh and Zheng (Australian & New Zealand Journal of Statistics, 44, 221-232, 2002), is not easy to implement in practice, because it requires the judgment ranking of each of the combination of the order statistics of the two characteristics. This paper investigates two modifications that make the method easier to use. The first modification is based on ranking one variable and noting the rank of the other variable for one cycle, and do the reverse for another cycle. The second approach is based on ranking of one variable and giving the second variable the same rank (Concomitant Order Statistic) for one cycle and do the reverse for the other cycle. The two procedures are investigated for an estimation of the means of some well-known distributions. It is show that the suggested approaches can be used in practice and can be more efficient than using SRS. A real data set is used to illustrate the procedure.

• Journal of the Korean Data and Information Science Society
• /
• v.25 no.6
• /
• pp.1499-1506
• /
• 2014

Random walk is used for describing random phenomenon in various areas but tests for random walk developed so far are known to suffer from size distortion and low power. Kim et al. (2014) proposed a sign test for unit root (${\rho}=1$) hypothesis based on slopes. This article proposes a Wilcoxon signed rank test based on slopes for unit root hypothesis, and compares it with the augmented Dickey-Fuller test and the sign test by a simulation study. Our results confirm that the nonparametric tests are better than ADF test for small samples like n = 30. The results also show that the sign test is better than the Wilcoxon signed rank test and that for 0 < ${\rho}$ < 1 (-1 < ${\rho}$ < 0), the nonparametric tests suffer from power loss (improvement) as normal error changes to double exponential error.