• Journal of the Korean Data and Information Science Society
• /
• 제10권1호
• /
• pp.1-10
• /
• 1999

Table of the empirical quantiles for the well known Shapiro-Francia W' goodness of fit statistic is produced which is more accurate than the existing ones. Prediction equation for the quantiles of W' statistic for sample sizes 30 or more we developed. The process of computing the expected values for the standard normal variate is discussed. This work is intended to make the Shapiro-Francia W' statistic more accessible to the practitioner.

• Journal of the Korean Data and Information Science Society
• /
• 제11권2호
• /
• pp.139-155
• /
• 2000

An exclusive simulation study is conducted in computing means for order statistics in standard normal variate. Monte Carlo moments are used in Shapiro-Francia W' statistic computation. Finally, quantiles for Shapiro-Francia W' are generated. The study shows that in computing means for order statistics in standard normal variate, complicated distributions and intensive numerical integrations can be avoided by using Monte Carlo simulation. Lack of accuracy is minimal and computation simplicity is noteworthy.

• Journal of the Korean Data and Information Science Society
• /
• 제12권1호
• /
• pp.103-125
• /
• 2001

The Box-Cox transformation is a well known family of power transformation that brings a set of data into agreement with the normality assumption of the residuals and hence the response variable of a postulated model in regression analysis. This paper proposes a new method for estimating the Box-Cox transformation using maximization of the Sample Entropy statistic which forces the data to get closer to normal as much as possible. A comparative study of the proposed procedure with the maximum likelihood procedure, the procedure via artificial regression estimation, and the recently introduced maximization of the Shapiro-Francia W' statistic procedure is given. In addition, we generate a table for the optimal spacings parameter in computing the Sample Entropy statistic.

• Journal of the Korean Data and Information Science Society
• /
• 제15권1호
• /
• pp.211-218
• /
• 2004

The subject of assessing whether a data set is from a specific distribution has received a good deal of attention. This topic is critically important for uniform distributions. Several parametric tests are compared. These tests also can be used in testing randomness of a sample. Anderson-Darling $A^2$ statistic is found to be most powerful.

• Communications for Statistical Applications and Methods
• /
• 제8권2호
• /
• pp.473-481
• /
• 2001

Shapiro and Wilk (1972) developed a test for exponentiality with origin and scale unknown. The procedure consists of comparing the generalized least squares estimate of scale with the estimate of scale given by the sample variance. However the test statistic is inconsistent. Kim(2001) proposed a modified Shapiro-Wilk's test statistic based on the ratio of tow asymptotically efficient estimates of scale. In this paper, we study the asymptotic behavior of the statistic using the approximation of the quantile process by a sequence of Brownian bridges and represent the limit null distribution as an integral of a Brownian bridge.

• 응용통계연구
• /
• 제21권2호
• /
• pp.265-273
• /
• 2008

본 논문에서는 Kim (2001a)에서 제안한 지수분포에서의 수정된 Shapiro와 Wilk (1972) $W_E$-통계량을 중도절단자료에 적용하였다. 검정통계량은 Samanta와 Schwarz (1988)에서 $W_E$-통계량을 중도절단자료에 대해 수정한 것과 같은 방법으로 정규화 등간격(normalized spacings)을 이용하여 수정하였다. 그 결과 제안된 통계량은 귀무가설에서 중도절단이 없는 경 우와 같은 분포를 갖고 표본크기만 변하게 된다. 제안된 통계량의 검정력을 Samanta와 Schwarz (1988)의 통계량과 비교한 결과, 중도절단이 없는 경우와 마찬가지로 중도절단이 있는 경우에도 변동계수가 1보다 크거나 같은 대립가설에서 제안된 통계량은 더 좋은 검정력을 나타내었다.

• Journal of the Korean Statistical Society
• /
• 제27권4호
• /
• pp.435-449
• /
• 1998

In this paper, we consider the problem of constructing the lower cofidence intervals for the reliability P(X < Y z,w), where the stress X and the strength Y are the random variables with explanatory variables z and w, respectively. As an estimator of the reliability, a Mann-Whitney type statistic is considered. It is shown that under regularity conditions, the proposed estimator is asymptotically normal. Based on the result, the distribution free lower confidence intervals are constructed.

• Communications for Statistical Applications and Methods
• /
• 제6권3호
• /
• pp.901-908
• /
• 1999

Using the Transformed Lorenz curve which is introduced by Cho et al.(1999) we propose the test statistic for testing of normality that is very important test in statistical analysis and compare the proposed test statistic with the Shapiro and Wilk's W test statistic in terms of the power of test through by Monte Carlo method.

• Communications for Statistical Applications and Methods
• /
• 제21권4호
• /
• pp.309-316
• /
• 2014

Testing normality is very important because the most common assumption is normality in statistical analysis. We propose a new plot and test statistic to goodness-of-fit test for normality based on the generalized Lorenz curve. We compare the new plot with the Q-Q plot. We also compare the new test statistic with the Kolmogorov-Smirnov (KS), Cramer-von Mises (CVM), Anderson-Darling (AD), Shapiro-Francia (SF), and Shapiro-Wilks (W) test statistic in terms of the power of the test through by Monte Carlo method. As a result, new plot is clearly classified normality and non-normality than Q-Q plot; in addition, the new test statistic is more powerful than the other test statistics for asymmetrical distribution. We check the proposed test statistic and plot using Hodgkin's disease data.

• International Journal of Reliability and Applications
• /
• 제8권1호
• /
• 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.