• Communications for Statistical Applications and Methods
• /
• v.3 no.2
• /
• pp.175-185
• /
• 1996

For the Change-point problem in a sequence of binomial variables we consider the maximum likelihood estimator (MLE) of unknown change-point. Its asymptotic distribution is quite limited in the case of binomial variables with different numver of trials at each time point. Hinkley and Hinkley (1970) gives an asymptotic distribution of the MLE for a sequence of Bernoulli random variables. To find the asymptotic distribution a numerical method such as bootstrap can be used. Another concern of our interest in the inference on the change-point and we derive confidence sets based on the liklihood ratio test(LRT). We find approximate confidence sets from the bootstrap distribution and compare the two results through an example.

• Communications for Statistical Applications and Methods
• /
• v.28 no.6
• /
• pp.627-641
• /
• 2021

An asymmetric least squares estimation method has been employed to estimate linear models for percentile regression. An asymmetric maximum likelihood estimation (AMLE) has been developed for the estimation of Poisson percentile linear models. In this study, we propose generalized nonlinear percentile regression using the AMLE, and the use of the parametric bootstrap method to obtain confidence intervals for the estimates of parameters of interest and smoothing functions of estimates. We consider three conditional distributions of response variables given covariates such as normal, exponential, and Poisson for three mean functions with one linear and two nonlinear models in the simulation studies. The proposed method provides reasonable estimates and confidence interval estimates of parameters, and comparable Monte Carlo asymptotic performance along with the sample size and quantiles. We illustrate applications of the proposed method using real-life data from chemical and radiation epidemiological studies.

• Communications for Statistical Applications and Methods
• /
• v.29 no.3
• /
• pp.301-317
• /
• 2022

In this paper, we propose a change point detection procedure based on the modified information criterion in a generalized lambda distribution (GLD) model. Simulations are conducted to obtain empirical critical values of the proposed test statistic. We have also conducted simulations to evaluate the performance of the proposed methods comparing to the log-likelihood method in terms of power, coverage probability, and confidence sets. Our results indicate that, under various conditions, the proposed method modified information criterion (MIC) approach shows good finite sample properties. Furthermore, we propose a new goodness-of-fit testing procedure based on the energy distance to evaluate the asymptotic null distribution of our test statistic. Two real data applications are provided to illustrate the use of the proposed method.

• Journal of the Korean Data and Information Science Society
• /
• v.14 no.3
• /
• pp.571-578
• /
• 2003

In this paper, we consider two components system which have bivariate weibull model with bivariate type I censored data. We proposed maximum likelihood estimator and relative frequency estimator for the reliability of series system. Also, we construct approximate confidence intervals for the reliability based on the two proposed estimators. And we present a numerical study.

• Journal of Korean Society for Quality Management
• /
• v.22 no.3
• /
• pp.85-98
• /
• 1994

In current coordinate measuring machine practice, there are no commonly accepted sample sizes for estimating form errors which have a statistical confidence. Practically, sample size planning is important for the geometrical tolerance inspection using a coordinate measuring machine. We determine and validate appropriate sample sizes for form error estimation. Also, we develop form error estimation methods with certain confidence levels based on the obtained sample sizes in various form errors: straightness, flatness, circularity, and cylindericity.

• Journal of the Korean Statistical Society
• /
• v.35 no.2
• /
• pp.167-177
• /
• 2006

An important role of statistical analysis in science is interpreting observed data as evidence, that is 'what do the data say?'. Although standard statistical methods (hypothesis testing, estimation, confidence intervals) are routinely used for this purpose, the theory behind those methods contains no defined concept of evidence and no answer to the basic question 'when is it correct to say that a given body of data represent evidence supporting one statistical hypothesis against another?' (Royall, 1997). In this article, we use likelihood ratios to measure evidence provided by record values in favor of a hypothesis and against an alternative. This hypothesis is concerned on mean of an exponential model and prediction of future record values.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.5
• /
• pp.1921-1928
• /
• 2010

This study was attempted in order to examine about influence of knowledge and attitude toward CPR(Cardiopulmonary Resuscitation) in elementary school students of some regions upon self-confidence. The aim is to be conducive to effective performance and self-confidence in CPR for cardiac arrest patients. We carried out targeting 381 elementary school students who attend 4 schools in J city and K city of J province from June 25 to July 15, 2009. The statistical processing was done by SPSS WIN 12.0 Version. The statistical significance was set to p<.05. As for correlation between variables of cardiopulmonary resuscitation characteristics with knowledge, attitude, and self-confidence, the appearance of acquiring information(r=.174, p<.01), the appearance of experiencing cardiopulmonary resuscitation(r=.143, p<.01), the appearance of educating cardiopulmonary resuscitation(r=.164, p<.01), necessity for education(r=.184, p<.01), knowledge(r=.342, p<.01), and attitude(r=.736, p<.01) showed correlation with self-confidence. As for influence of knowledge and attitude toward cardiopulmonary resuscitation upon self-confidence, the attitude($\beta=.703$, t=17.884, p<.01) had significant influence upon self-confidence. It is necessary to arrange educational program of cardiopulmonary resuscitation, to distribute effective manpower, and to provide elementary school students to cope with emergent situation.

• Journal of the Society of Naval Architects of Korea
• /
• v.51 no.4
• /
• pp.321-327
• /
• 2014

A wide scope of numerical simulations was performed to predict model-ship resistances by using STAR-CCM+ and OpenFOAM. The numerical results were compared with experimental measurements in towing tank to analyze statistical reliability of the present simulations. Based on the normal distribution of resistance errors in 113 cases of container carriers, tankers and very large crude-oil carriers, the confidence intervals of numerical error were estimated as [-2.64%,+2.32%] and [-1.82%, +1.87%] with 95% confidence in STAR-CCM+ and OpenFOAM, respectively. The resistance errors of liquefied natural gas carriers with single- and twin-skeg were confident in the ranges of [-2.51%,+2.64%] and [-2.29%, +1.46%], respectively. The grid uncertainty of resistance coefficients for KCS was also quantitatively analyzed by using a grid verification procedure. The grid uncertainty of OpenFOAM (5.1%) was larger than 4.4% uncertainty of STAR-CCM+ although OpenFOAM provided statistically more confident results than those of STAR-CCM+. It means that a grid system verified under a specific condition does not automatically lead to statistical reliability in general cases.

• The Korean Journal of Applied Statistics
• /
• v.23 no.2
• /
• pp.263-274
• /
• 2010

Business survey index(BSI) is an economic forecasting index made on the basis of the past achievement of the company and enterpriser's plan and decision for the future. Even the index is very popular in economic situations, only a little research result is known to the public. In the paper we investigate statistical properties of BSI. We define population BSI in the finite population and estimate it unbiasedly. Also we derive the variance of the estimated BSI and its unbiased estimator. In addition, confidence interval of the estimated BSI is proposed. We asserte that confidence interval of the estimated BSI is more reasonable than the relative standard error.

• Computers and Concrete
• /
• v.21 no.5
• /
• pp.485-493
• /
• 2018

Statistical analysis has found useful application in the design of experiments (DOE) especially optimization of concrete ingredients however, to be able to apply the concept properly using computer aided applications there has to be an upper and lower limits of responses fed to the system. In this study, the production of high-performance steel fiber concrete (HPSFC) at five different fiber addition levels by volume with two aspect ratios of 60 and 83 were studied under two curing methods completely dry cured (DC) and moist cured (MC) conditions. In other words, this study was carried out for those limits based on material properties available in North Cyprus. Specimens utilized were cubes 100 mm size casted and cured for 28 days and tested for compressive strength. Minitab 18 statistical software was utilized for the analysis of results at a 5 per cent level of significance. Experimentally, it was observed that, there was fluctuation in compressive strength results for the two aspect ratios and curing regimes. On the other hand P-value hypothesis evaluation of the response showed that at the stated level of significance, there was a statistically significant difference between dry and moist curing conditions. Upper and lower limit values were proposed for the response to be utilized in DOE for future studies based on these material properties. It was also suggested that for a narrow confidence interval and accuracy of the system, future study should increase the sample size.