• Journal of Integrative Natural Science
• /
• v.15 no.1
• /
• pp.9-18
• /
• 2022

This research examines the power of bootstrap two-sample test, and compares it with the powers of two-sample t-test and Wilcoxon rank sum test, through simulation. For simulation work, a positively skewed and heavy tailed distribution was selected as a population distribution, the chi-square distributions with three degrees of freedom, χ²₃. For two independent samples, the fist sample was selected from χ²₃. The second sample was selected independently from the same χ²₃ as the first sample, and calculated d+ax for each sampled value x, a randomly selected value from χ²₃. The d in d+ax has from 0 to 5 by 0.5 interval, and the a has from 1.0 to 1.5 by 0.1 interval. The powers of three methods were evaluated for the sample sizes 10,20,30,40,50. The null hypothesis was the two population medians being equal for Bootstrap two-sample test and Wilcoxon rank sum test, and the two population means being equal for the two-sample t-test. The powers were obtained using r program language; wilcox.test() in r base package for Wilcoxon rank sum test, t.test() in r base package for the two-sample t-test, boot.two.bca() in r wBoot pacakge for the bootstrap two-sample test. Simulation results show that the power of Wilcoxon rank sum test is the best for all 330 (n,a,d) combinations and the power of two-sample t-test comes next, and the power of bootstrap two-sample comes last. As the results, it can be recommended to use the classic inference methods if there are widely accepted and used methods, in terms of time, costs, sometimes power.

• 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.

• Journal of the Korean Data and Information Science Society
• /
• v.13 no.2
• /
• pp.355-363
• /
• 2002

Using the Buckley-James method, we construct bootstrap confidence intervals for the regression coefficients under the censored data. And we compare these confidence intervals in terms of the coverage probabilities and the expected confidence interval lengths through Monte Carlo simulation.

• Journal of the Korean Statistical Society
• /
• v.15 no.1
• /
• pp.1-8
• /
• 1986

The k-medians clustering method is considered to partition observations into k clusters. Consistency and advantage of bootstrap confidence sets of k optimal cluster centers are discussed. The k-medians and k-means clustering methods are compared by using actual data sets.

• Journal of the Korean Statistical Society
• /
• v.28 no.2
• /
• pp.253-264
• /
• 1999

Conditinal weakly convergence of the blockwise bootstrapped empirical process for stationary sequences to the appropriate Gaussian process is reestablished particularly for severely dependent $\alpha$-mixing sequences. Issue of block size is discussed from the point of validity of bootstrap method.

• Communications for Statistical Applications and Methods
• /
• v.4 no.3
• /
• pp.827-832
• /
• 1997

Statistical relations between a system and empirical distribution are studied in terms of the concept of Akaike's Information Criterion. From this consideration we derive a bootstrap criterion for determining the optimal number of hidden units in nerual networks.

• Journal of Wetlands Research
• /
• v.21 no.2
• /
• pp.114-124
• /
• 2019

The objective of this study is to reduce the uncertainty of the river discharge estimation method using the stage-discharge relation curve. It is necessary to consider the quantitative and accurate estimation method because the river discharge data is essential data for hydrological interpretation and water resource management. For this purpose, the parameters estimated by Bayesian and Bootstrap methods are compared with the ones obtained by stage-discharge relation curve. In addition, the Bayesian and Bootstrap methods are applied to assess uncertainty and then those are compared with the confidence intervals of the results from standard error method which has t-distribution. From the results of this study, The estimated value of the regression analysis developed through this study is less than 1 ~ 5%. Also It is confirmed that there are some areas where the applicability is better than the existing one according to the water level at each point. Therefore, if we use more suitable method according to the river characteristics, we could obtain more reliable discharge with less uncertainty.

• Journal of Korean Society of Forest Science
• /
• v.100 no.4
• /
• pp.535-539
• /
• 2011

This study was conducted to examine the bootstrap evaluation of the stem density and biomass expansion factor for Pinus rigida plantations in Korea. The stem density ($g/cm^3$) in less than 20 tree years were 0.460 while more than 21 tree years were 0.456 respectively. Biomass expansion factor of less than 20 years and more than 21 years were 2.013, 1.171, respectively. The results of 100 and 500 bootstrap iterations, stem density ($g/cm^3$) in less than 20 years were 0.456~0.462 while more than 21 years were 0.457~0.456 respectively. Biomass expansion factor of less than 20 years and more than 21 years were 1.990~2.039, 1.173~1.170, respectively. The mean differences between observed biomass factor and average parameter estimates showed within 5 percent differences. The split datasets of younger stands and old stands were compared to the results of bootstrap simulations. The stem density in less than 20 years of mean difference were 0.441~1.049% while more than 21years were 0.123~0.206% respectively. Biomass expansion factor in less than 20 years and more than 21 years were -1.102~1.340%, -0.024~0.215% respectively. Younger stand had relatively higher errors compared to the old stand. The results of stem density and biomass expansion factor using the bootstrap simulation method indicated approximately 1.1% and 1.4%, respectively.

• Proceedings of the Korean Society for Quality Management Conference
• /
• 1998.11a
• /
• pp.309-315
• /
• 1998

Process Capability can be expressed with a process index which indicates the incapability of a process to meet its specifications. This index is regarded as a process capability index(PCI) or more precisely as a process incapability index(PII). It is obtained from a simple transformation of a PCI. Greenwich and Jahr-Schaffrath(1995) considered the PII $C_{pp}$ which could be obtained from the transformation to the PCI, $C_{pm}$, and they provided the asymptotic distribution for $C_{pp}$ which was useful unless the process characteristic was normally distributed. However, some statistical inferences based on the asymptotic distribution need a large sample size. There are some processes which process engineers could not help obtaining sufficiently a large sample size. Thus, we have derived its corresponding bootstrap asymptotic distribution since bootstrapping would be a helpful technique for the PII, $C_{pp}$ which was nonparametric or free from assumptions of the distribution of the characteristic X. Moreover, we have constructed six bootstrap confidence intervals used in reducing bias of estimations based on the bootstrap asymptotic distribution and simulated their performances for $C_{pp}$,

• The Korean Journal of Applied Statistics
• /
• v.19 no.3
• /
• pp.535-544
• /
• 2006

We consider use of Bootstrap calibration in the problem of setting a confidence interval for a linear combination of variance components. Based on the the modified large sample(MLS) method by Graybill and Wang(1980), Bootstrap Calibration is applied to improve the coverage probability of the MLS confidence bound when the experiment is balanced and coefficients of a linear combination are positive. Performance of the proposed confidence bound in small sample is investigated by simulation studies.