• Communications for Statistical Applications and Methods
• /
• v.10 no.3
• /
• pp.647-654
• /
• 2003

Bayesian probability models for finite populations are considered assuming so-called the super-population. We find the posterior distribution of population mean by a new approach, using the concept of pivotal quantity for the small sample case. A large sample theory is also treated throught the concept of asymptotically pivotal quantity.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.54 no.1
• /
• pp.38-42
• /
• 2005

Restructuring of the electric power industry has brought the issue of market competitiveness to surface. Recent years have witnessed the appearance of a particular seller or group of sellers exercising market power in electricity supply. In fact, much scholarly work has been done on how to identify and mitigate such abuse by market management rules. In this paper we assess the possible market power on the basis of pivotal supplier test and propose the method to determine the reasonable quantity of long-term contracts which can play a crucial role in mitigating the market power for a pivotal player. Furthermore the market efficiency is guaranteed by making long term contracts with a pivotal player up to the quantity to ensure that the pivotal player has no incentive to abuse the pivotal quantity in the electricity market.

• Communications for Statistical Applications and Methods
• /
• v.9 no.1
• /
• pp.221-227
• /
• 2002

The concept of pivot has been widely used in various classical inferences. In this paper, it is proved by use of pivotal quantities that the Bayesian inferences can be arrived at the same results of classical inferences for the location-scale parameters models under the assumption of non-informative prior distributions. Some theorems are proposed in which the posterior distribution and the sampling distribution of a pivotal quantity coincide. The theorems are applied illustratively to some statistical models.

• Communications for Statistical Applications and Methods
• /
• v.17 no.2
• /
• pp.275-292
• /
• 2010

Receiver operating characteristic(ROC) curves can be used to assess the accuracy of tests measured on ordinal or continuous scales. The most commonly used measure for the overall diagnostic accuracy of diagnostic tests is the area under the ROC curve(AUC). When two ROC curves are constructed based on two tests performed on the same individuals, statistical analysis on differences between AUCs must take into account the correlated nature of the data. This article focuses on confidence interval estimation of the difference between paired AUCs. We compare nonparametric, maximum likelihood, bootstrap and generalized pivotal quantity methods, and conduct a monte carlo simulation to investigate the probability coverage and expected length of the four methods.

• Journal of Korean Society for Quality Management
• /
• v.25 no.3
• /
• pp.1-10
• /
• 1997

In the context of accelerated life tests, procedures are given for estimating the parameters in the modified Arrhenius model and for estimating mean life at a given future stress level. The conditional confidence intervals are obtained by conditioning on ancillary statistics and pivotal quantity. Using the data of Tobias and Trindada(1986), we illustrate conditional confidence interval for parameters under use condition in the modified Arrhenius model.

• Journal of the Korean Statistical Society
• /
• v.29 no.4
• /
• pp.489-499
• /
• 2000

We propose a new instrumental variable estimator of the complex parameter of a class of univariate complex-valued diffusion processes defined by the possibly non-stationary and/or nonlinear stochastic differential equations. On the basis of the exact finite sample distribution of the pivotal quantity, we construct the exact confidence intervals and the exact tests for the parameter. Monte-Carlo simulation suggests that the new estimator seems to provide a viable alternative to the maximum likelihood estimator (MLE) for nonlinear and/or non-stationary processes.

• The Journal of the Korea Contents Association
• /
• v.21 no.7
• /
• pp.386-403
• /
• 2021

Preannouncing a new product to its target audiences has been more and more prevalent in a wealth of industries, particularly industries that attach great importance to the speed of entry. Grounded in market signaling theory, the current research advances a theoretical model that takes full cognizance of the relation between preannounced information about an upcoming product and individual customers' behavioral intentions as well as significant moderating effects of prior product knowledge and new product innovativeness. In response, a web-based survey is conducted for data collection and the structural equation model is utilized for data analysis. Results of this study demonstrate that preannounced new product information attributes (i.e., quantity, clarity) may positively influence consumers' attitudes, in turn, lead to a favorable purchase intention. Moreover, the moderating effects of product knowledge and product innovativeness are also confirmed. Specifically, product knowledge moderates the quantity-attitude relation positively and moderates the clarity-attitude relation negatively, whereas product innovativeness does opposite. Both implications and limitations are also described.

• Proceedings of the Korean Statistical Society Conference
• /
• 2004.11a
• /
• pp.265-270
• /
• 2004

불균형중첩오차구조를 갖는 단순선형회귀모형에서 나타나는 두 분산의 합에 대한 신뢰구간을 구하기 위하여 Ting et al.(1990) 방법과 Graybill and Wang(1980) 방법과 Tsui and Weerahandi(1989)가 제안한 일반화 축량(generalized pivotal quantity)방법을 이용한 두 가지 방법 등 모두 네 가지 신뢰구간을 제안한다. 신뢰구간의 적절성을 판단하기 위하여 여러 가지 불균형 설계에 대하여 SAS/IML로 시뮬레이션을 실행하고 신뢰계수와 신뢰구간의 평균 길이를 비교한다. 불균형중첩오차구조를 갖는 단순선형회귀모형의 두 분산의 합에 대한 네 가지 신뢰구간들이 주샘플링 단위의 변화에 따라 어느 방법이 적절한 신뢰구간을 구축하는지 추천하고, 실제 예제를 적용하여 시뮬레이션의 결과와 일관성이 있는지를 확인한다.

• Communications for Statistical Applications and Methods
• /
• v.12 no.1
• /
• pp.87-100
• /
• 2005

In order to construct confidence intervals on the sum of variance components in a simple regression model with unbalanced nested error structure, alternative confidence intervals using Graybill and Wang(1980) and generalized inference concept introduced by Tsui and Weerahandi(1989) are proposed. Computer simulation programmed by SAS/IML is performed to compare the simulated confidence coefficients and average interval lengths of the proposed confidence intervals. A numerical example is provided to demonstrate the confidence intervals and to show consistency between the example and simulation results.

• Journal of the Korean Statistical Society
• /
• v.26 no.4
• /
• pp.543-554
• /
• 1997

A family of some capability indices { $C_{p}$(.alpha.,.beta.); .alpha..geq.0, .beta..geq.0}, containing the indices $C_{p}$, $C_{{pk}}$, $C_{{pm}}$, and $C_{{pmk}}$, has been defined by Vannman(1993) for the case of two-sided specification interval. By varying the parameters of the family various capability indices with suitable properties are obtained. We derive tha asymptotic distribution of the family { $C_{p}$(.alpha.,.beta.); .alpha..geq.0,.beta..geq.0} under general proper conditions. It is also shown that the bootstrap approximation to the distribution of the estimator $C_{p}$(.alpha., .beta.) is vaild for almost all sample sequences. These asymptotic distributions would be used in constructing some bootstrap confidence intervals.tervals.