• Journal of Korean Society for Quality Management
• /
• v.22 no.1
• /
• pp.169-178
• /
• 1994

Nonparametric tests for comparing two treatments when data are subject to unequal patterns of censorship are discussed. Best precedence test proposed by Slud can be viewed as a nice alternative test comparing with weighted log-rank tests, not to mention the advantage of short experimental period. This research revises some missing parts of Slud's test and examines the asymptotic power of it under the nonproportional hazard alternatives through the simulation. The simulation studies show best precedence test has reasonable power in the sense of robustness under nonproportional hazard alternatives and could be recommended at such situation.

• Communications for Statistical Applications and Methods
• /
• v.7 no.2
• /
• pp.563-573
• /
• 2000

In this thesis, we propose the test statistic for ordered alternatives on c-sample ranked set samples(RSS). The proposed test statistic JRSS is Jonckheere type statistic using the median of the i-th samples in each cycle. We obtained the asymptotic property of the proposed test statistic and the asymptotic relative efficiencies of the proposed test statistic with respect to J SRS which Jonckheere type statistic on simple random samples(SRS). From the simulation works, J RSS is superior to J SRS. We compared the empirical powers of J RSS with respect to U RSS on ranked set sample and U SRS on simple random sample using all samples, which are proposed by Kim, Kim and Lee(1999). The powers of J RSS are nearly the same values when entire sample size is large. J RSS is superior to U RSS. J RSS is simpler than U RSSon calculating process.

• Communications for Statistical Applications and Methods
• /
• v.8 no.2
• /
• pp.395-406
• /
• 2001

In this paper, we propose the test statistic for the umbrella alternatives on c-samples ranked set samples(RSS), where the peak of the umbrella is known. We obtain the asymptotic property of the proposed test statistic and the asymptotic relative efficiencies of the proposed test statistic with respect to U-statistic based on simple random samples(SRS). From the simulation work, we compare the empirical powers of the proposed test statistic with U-statistic based on SRS.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.10a
• /
• pp.233-238
• /
• 2003

Goodness of fit test statistics based on the information discrepancy have been shown to perform very well (Vasicek 1976, Dudewicz and van der Meulen 1981, Chandra et al 1982, Gohkale 1983, Arizona and Ohta 1989, Ebrahimi et al 1992, etc). Although the test is well defined for the non-censored case, censored case has not been discussed in the literature. Therefore we consider a goodness of fit test based on the partial Kullback-Leibler(KL) information with the type II censored data. We derive the partial KL information of the null distribution function and a nonparametric distribution function, and establish a goodness of fit test statistic. We consider the exponential and normal distributions and made Monte Calro simulations to compare the test statistics with some existing tests.

• Communications for Statistical Applications and Methods
• /
• v.2 no.1
• /
• pp.122-136
• /
• 1995

The objective of this research is to investigate the problem of goodness-of-fit testing based on nonparametric density estimation with a data-driven smoothing parameter. The small and large sample properties of a new test statistic $\hat{\lambda_a}$ is investigated. The test statistic $\hat{\lambda_a}$ is itself a smoothing parameter which is selected to minimize an estimated MISE for a truncated series estimator of the comparison density function. Therefore, this test statistic leads immediately to a point estimate of the density function th the event that $H_0$ is rejected. The limiting distribution of $\hat{\lambda_a}$ is obtained under the null hypothesis. It is also shown that this test is consistent against fixed alternatives.

• International Journal of Reliability and Applications
• /
• v.8 no.1
• /
• pp.27-39
• /
• 2007

Based on goodness of fit new testing procedures are derived for testing exponentiality against harmonic new renewal better than used in expectation (HNRBUE). For this aging properties, a nonparametric procedure (U-statistic) is proposed. The percentiles of this test statistic are tabulated for sample sizes n=5(1)30(10)50. The Pitman asymptotic efficiency (PAE) of the test is calculated and compared with, the (PAE) of the test for new renewal better than used (NRBU) class of life distribution [see Mahmoud et al (2003)]. The power of this test is also calculated for some commonly used life distributions in reliability. The right censored data case is also studied. Finally, real examples are given to elucidate the use of the proposed test statistic in the reliability analysis.

• Journal of Korean Society on Water Environment
• /
• v.33 no.1
• /
• pp.40-50
• /
• 2017

We were interested in the long-term temporal and spatial variability trends of water quality. Trend tests such as the Seasonal and Regional Kendall tests and LOWESS (LOcally WEighted Scatter plot Smoother) have been recommended as outstanding tools for trend detection. In this study, we conducted four types of nonparametric trend tests (Seasonal and Regional Kendall tests, LOWESS, and flow-adjusted Seasonal Kendall). We aimed to identify water quality trends using the monthly data for five variables (BOD, COD, TN, TP, and flow) collected from 24 sites in the Nakdong River from August 2004 to December 2013. According to the Regional Kendall test, BOD, COD, and TN increased but TP decreased trend. The Seasonal Kendall test showed that BOD, TN, and TP remained constant at 62.5-83.3% of the sites. COD remained constant at 58.3% of the sites. LOWESS showed that TP gradually increased between 2007 and 2008, then decreased slowly at the Gumi, Geumhogang6, Daeam-1 and Milyanggang3 sites. BOD increased slightly between 2008 and 2009, and then decreased slowly at the Namgang4-1 site. Lastly, a flow-adjusted Seasonal Kendall test was conducted. There were different results between Seasonal Kendall and flow-adjusted Seasonal Kendall tests at 11 of the 24 sites. According to the results from six of the eleven sites, BOD increased at one site, showed no trends at three sited, and decreased at two sites. Each of COD, TN increased at two, one site. but TP decreased at two sites.

• Journal of Forest and Environmental Science
• /
• v.38 no.2
• /
• pp.102-109
• /
• 2022

This study was conducted to test the significant difference of fertility variation among families and to select superior families for acorn production in the breeding seedling seed orchards (BSSOs) of Quercus acuta and Quercus glauca. The seed orchards were located in Jeju island and established by seedlings raised from selected parents for genetic testing in 2006. In the spring of 2021, the numbers of female and male flower were counted from 5 to 10 individuals per family in the BSSOs. To test statistical significance of which parameter is not satisfied through the normality test, we used a nonparametric analysis. Correlation analysis was performed to quantify the association between female and male flower production. As the results, the significant difference of flower production among families was found in both seed orchards. The averages of female flower production were 65.3 and 181.9 in Q. acuta and Q. glauca. The positive Spearman's rank correlation was existed between male and female flower production. Broad-sense heritability on female and male flower production were 0.191 and 0.147 in Q. acuta, and 0.285 and 0.068 in Q. glauca, respectively. Sexual asymmetry (e.g., maleness index) between female and male, and contribution variation among families (e.g., parental balance) were analyzed to find reasonable alternatives in the management of seed orchards. Effective population size of seed crops was predicted as a concept of status number. Loss of gene diversity (accumulation of group coancestry) would not be alarming in the BSSOs. Our results would be helpful to select breeding materials for establishing new seed orchards and to supply genetically improved seeds of evergreen oaks, which is one of the backbones of the strategy of carbon sink in the 2050 Carbon Neutrality of Korea Forest Service.

• Smart Structures and Systems
• /
• v.15 no.2
• /
• pp.409-424
• /
• 2015

Structural nonlinearity is a common phenomenon encountered in engineering structures under severe dynamic loading. It is necessary to localize and identify structural nonlinearities using structural dynamic measurements for damage detection and performance evaluation of structures. However, identification of nonlinear structural systems is a difficult task, especially when proper mathematical models for structural nonlinear behaviors are not available. In prior studies on nonparametric identification of nonlinear structures, the locations of structural nonlinearities are usually assumed known and all structural responses are measured. In this paper, an identification algorithm is proposed for locating and identifying model-free structural nonlinearities and systems using incomplete measurements of structural responses. First, equivalent linear structural systems are established and identified by the extended Kalman filter (EKF). The locations of structural nonlinearities are identified. Then, the model-free structural nonlinear restoring forces are approximated by power series polynomial models. The unscented Kalman filter (UKF) is utilized to identify structural nonlinear restoring forces and structural systems. Both numerical simulation examples and experimental test of a multi-story shear building with a MR damper are used to validate the proposed algorithm.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.2
• /
• pp.261-272
• /
• 2009

Kolmogorov-Smirnov (K-S) statistic has been widely used for testing homogeneity of two distributions in the credit rating models. Joseph (2005) used K-S statistic to obtain validation criteria which is most well-known. There are other homogeneity test statistics such as the Cramer-von Mises, Anderson-Darling, and Watson statistics. In this paper, these statistics are introduced and applied to obtain criterion of these statistics by extending Joseph (2005)'s work. Another set of alternative criterion is suggested according to various sample sizes, type a error rates, and the ratios of bads and goods by using the simulated data under the similar situation as real credit rating data. We compare and explore among Joseph's criteria and two sets of the proposed criterion and discuss their applications.