• Journal of the Korean Data and Information Science Society
• /
• v.15 no.1
• /
• pp.273-284
• /
• 2004

Bayes estimation of parameters is considered for two independent exponential distributions with ordered means. Order restricted Bayes estimators for means are obtained with respect to inverted gamma, noninformative prior and uniform prior distributions, and their asymptotic properties are established. It is shown that the maximum likelihood estimator, restricted maximum likelihood estimator, unrestricted Bayes estimator, and restricted Bayes estimator of the mean are all consistent and have the same limiting distribution. These estimators are compared with the corresponding unrestricted Bayes estimators by Monte Carlo simulation.

• International Journal of Reliability and Applications
• /
• v.7 no.2
• /
• pp.127-140
• /
• 2006

AIn this paper we introduce and study a multivariate notions of mean inactivity time (MIT) functions. Basic properties of these functions are derived and their relationship to the multivariate conditional reversed hazard rate functions is studied. A partial ordering, called MIT ordering, of non-negative random vectors is introduced and its basic properties are presented. Its relationship to reversed hazard rate ordering is pointed out. Finally, using the MIT ordering, a bivariate and multivariate notions of IMIT (increasing mean inactivity time) class is introduced and studied.

• Research in Mathematical Education
• /
• v.10 no.3 s.27
• /
• pp.229-238
• /
• 2006

During World War II there was a statistical analysis conducted by the Allied analysts to estimate the German war productions, including their tank productions. This article revisits the analysis of the tank productions as a classroom activity format. Various reformed ideas are proposed in order to enhance students' perspectives of the point estimation. Comprehensive simulation works and actual classroom discussions will be provided along with the theoretical investigations.

• Communications for Statistical Applications and Methods
• /
• v.1 no.1
• /
• pp.52-56
• /
• 1994

When we have an i.i.d. sample of size n from a continuous distribution, the distribution truncated on the left at the rth order statistic plays an important role in the theoretical analysis of the Type 2 censored data. The charaterization of distributions by the average of the conditional expectation and the average of the conditional information concerning the truncated distribution is studied here.

• Journal of the Korean Data and Information Science Society
• /
• v.6 no.1
• /
• pp.53-61
• /
• 1995

This paper deals with problems of predicting, based on the random censored sampling, a future observation and the p-th order statistic of n' future observations for the Rayleigh model. We consider the prediction intervals for the Rayleigh model with respect to an inverse gamma prior distribution. In additions, numerical examples are given in order to illustrate the proposed predictive procedure.

• Bulletin of the Korean Mathematical Society
• /
• v.33 no.1
• /
• pp.135-170
• /
• 1996

Recently many people have studied the Sobolev orthogonal polynomials, that is, polynomials which are orthogonal relative to a symmetric bilinear form $\phi(\cdot,\cdot)$ defined by $$ (1.1) $\phi(p,q) := (p,q)_N = \sum_{k=0}^{N} \int_{R}p^(k) (x)q^(k) (x) d\mu_k, $$ where each $d\mu_k$ is a signed Borel measure on the real line $R$ with finite moments of all orders. For the brief history on this subject, we refer to the survey article Ronveaux [13] and Marcellan and et al [10].

• The Korean Journal of Applied Statistics
• /
• v.23 no.6
• /
• pp.1067-1080
• /
• 2010

A number of methods have been developed to determine sample sizes in clinical trial, and most clinical trial organizations determine sample sizes based on the methods. In contrast, determining sufficient sample sizes needed for experiments using microarray chips is unsatisfactory and not widely in use. In this paper, our objective is to provide a guideline in determining sample sizes, utilizing reproducibility of real microarray data. In the reproducibility comparison, five methods for discovering differential expression are used: Fold change, Two-sample t-test, Wilcoxon rank-sum test, SAM, and LPE. In order to standardize gene expression values, both MAS5 and RMA methods are considered. According to the number of repetitions, the upper 20 and 100 gene accordances are also compared. In determining sample sizes, more realistic information can be added to the existing method because of our proposed approach.

• The Korean Journal of Applied Statistics
• /
• v.26 no.6
• /
• pp.1033-1041
• /
• 2013

In this paper, we investigate several variance estimators for pps systematic sampling. Unfortunately, there is no unbiased variance estimators for a systematic sample because systematic sampling can be regarded as a random selection of one cluster. This study provides guidance on which variance estimator may be more appropriate than others in several circumstances. We judge the efficiency of variance estimators for systematic sampling based on of their relative biases and relative mean square error. Also, we investigate variance estimation problems for two-stage systematic sampling applied for the Food Raw Material Consumption Survey and the Establishment Labor Force Survey simulation study, in order to consider the popular two-stage pps systematic sample design for establishment and household survey in Korea.

• Survey Research
• /
• v.8 no.2
• /
• pp.91-115
• /
• 2007

OES survey as the national official statistics aims to provide the basic data for the national labor market policy and research such as the basic statistics for human resource supply policy, the prediction of employment by occupations, the decision of occupation, the occupational training and the finding jobs et al., at the levels of industrial and occupational classifications(3-digit). In order to achieve this objective, we analyze the OES data in 2005 and 2006 and propose the new sampling design using the long form data in Korea (10% sample data of census 2005). In this paper, we provide the criterion of sample allocation and derive the formular for estimator and error of it including the weighting procedure. From the proposed sampling design, we would expect that it contributes to the supply policy of human resource and the research for labor market.

• The Korean Journal of Applied Statistics
• /
• v.37 no.2
• /
• pp.239-253
• /
• 2024

This research applies both point-wise and pair-wise learning strategies within the learning-to-rank (LTR) framework to predict horse race rankings in Seoul. Specifically, for point-wise learning, we employ a linear model and random forest. In contrast, for pair-wise learning, we utilize tools such as RankNet, and LambdaMART (XGBoost Ranker, LightGBM Ranker, and CatBoost Ranker). Furthermore, to enhance predictions, race records are standardized based on race distance, and we integrate various datasets, including race information, jockey information, horse training records, and trainer information. Our results empirically demonstrate that pair-wise learning approaches that can reflect the order information between items generally outperform point-wise learning approaches. Notably, CatBoost Ranker is the top performer. Through Shapley value analysis, we identified that the important variables for CatBoost Ranker include the performance of a horse, its previous race records, the count of its starting trainings, the total number of starting trainings, and the instances of disease diagnoses for the horse.