• Journal of applied mathematics & informatics
• /
• 제40권1_2호
• /
• pp.1-13
• /
• 2022

This article introduces a new distribution called length-biased powered inverse Rayleigh distribution. Some of its statistical properties are derived. Maximum likelihood procedure is applied to report the point and interval estimations of all model parameters. The proposed distribution is also applied to two real data sets for illustrative purposes.

• Korea-Australia Rheology Journal
• /
• 제18권2호
• /
• pp.99-102
• /
• 2006

Primitive chain network model for block copolymers is used here to simulate molecular dynamics in the entangled state with acceptable computational cost. It was found that i) the hooking procedure rearranging the topology of the entangled network is critical for the equilibrium structure of the system, and ii) simulations accounting for the different chemistry, i.e., with a biased hooking probability based on interaction parameter ${\chi}$ for selection of the hooked partner, generates a reasonable phase diagram.

• 한국대기환경학회지
• /
• 제26권4호
• /
• pp.449-452
• /
• 2010

In this article, the performance of the THC analyzer was inspected using two different span gases of methane ($CH_4$) and propane ($C_3H_8$). To explore the effect of standard gas selection, MicroFID system was tested by the following procedures. Initially, the system is spanned by propane gas of 60 ppm (or 180 ppmC). The system is then run against methane standards prepared at 5 different concentrations of 200, 250, 300, 400, and 500 ppm. According to the suggestion of the KMOE's test procedure to use multiplying a factor of 3 (for propane), the resulting THC values derived by methane standards were systematically biased with ~500% error relative to true value. This paper discusses the interpretation procedures to obtain the least biased THC values for a given span set-up.

• Communications for Statistical Applications and Methods
• /
• 제30권2호
• /
• pp.149-162
• /
• 2023

The ℓ₁-trend filtering method is one of the most widely used methods for extracting underlying trends from noisy observations. Contrary to the Hodrick-Prescott filtering, the ℓ₁-trend filtering gives piecewise linear trends. One of the advantages of the ℓ₁-trend filtering is that it can be used for identifying change points in piecewise linear trends. However, since the ℓ₁-trend filtering employs total variation as a penalty term, estimated piecewise linear trends tend to be biased. In this study, we demonstrate the biasedness of the ℓ₁-trend filtering in trend level estimation and propose a two-stage bias-reduction procedure. The newly suggested estimator is based on the estimated change points of the ℓ₁-trend filtering. Numerical examples illustrate that the proposed method yields less biased estimates for piecewise linear trends.

• 논리연구
• /
• 제19권3호
• /
• pp.369-400
• /
• 2016

'한 어머니 상금 씨가 낳은 두 아이 가운데 적어도 하나는 딸이다'라는 정보를 입수했을 때 '상금 씨의 두 아이가 모두 딸이다'를 우리는 얼마큼 믿을 수 있는가? 이 확률이 1/3이라는 것은 거의 분명해 보인다. 그런데 상금 씨가 '보미는 내 딸이다'라는 정보를 새로 더 알려줄 경우 많은 학자들은 우리의 확률이 1/3에서 1/2로 바뀌어야 한다고 말한다. 하지만 나는 그 확률이 여전히 1/3에 머물러야 한다고 주장한다. 증거와 가설의 지지 관계나 정보 유입과 확률 변화를 가늠하기 위해 조건화 규칙을 사용할 때 우리가 주의해야 할 점이 있다. 관련 정보 또는 증거가 어떤 절차를 거쳐 우리에게 주어졌는지를 따져보아야 한다. 해당 증거가 마구잡이로 주어졌다고 여길 수 없을 때는 조건화 규칙을 조심해서 사용해야 한다. 다시 말해 특정 관찰, 증언, 증거가 주어지도록 정보를 갖고 있는 누군가가 그 증거를 각별히 선택하지는 않았는지 잘 따져야 한다. 관련 정보 또는 증거가 우연히 주어지지 않고 그 정보를 이미 알고 있는 사람이 그 정보를 각별히 골라 우리에게 제공한 것이라면, 그 정보는 때때로 우리의 믿음직함을 바꿀 만한 정보가 되지 못한다.

• Journal of the Korean Data and Information Science Society
• /
• 제20권5호
• /
• pp.895-903
• /
• 2009

The penalized partial likelihood based on restricted maximum likelihood method has been widely used for the inference of frailty models. However, the standard-error estimate for frailty parameter estimator can be downwardly biased. In this paper we show that such underestimation can be corrected by using hierarchical likelihood. In particular, the hierarchical likelihood gives a statistically efficient procedure for various random-effect models including frailty models. The proposed method is illustrated via a numerical example and simulation study. The simulation results demonstrate that the corrected standard-error estimate largely improves such bias.

• 품질경영학회지
• /
• 제19권2호
• /
• pp.40-51
• /
• 1991

The $C_B$ statistic, a generalization of Mallows's $C_L$ statistic, is developed to determine the shrinkage parameter. Since not all cases in a data set play an equal role in forming $C_B$, a subdivision of $C_B$ into individual components for each case is developed. This subdivision is useful both as an aid in understanding $C_B$ and as a diagnostic procedure.

• Journal of the Korean Statistical Society
• /
• 제14권1호
• /
• pp.48-55
• /
• 1985

In clinical trials subjects are avalible sequentially and must be assigned to treatments immediately. Completely randomized procedure for the allocation of treatments to each subject may result in severe imbalance among the number of subjects in treatment groups, especially for small experiments or interim analyses of large experiments. In this study, restricted randomization methods such as biased coin designs (Efron, 1971), permuted block design, and truncated binomial design are compared to teh completely randomized design in the presence of selection and/or accidential bias by Monte Carlo simulations.

• Communications for Statistical Applications and Methods
• /
• 제22권2호
• /
• pp.173-180
• /
• 2015

We propose a selection procedure of principal components in principal component regression. Our method selects principal components using variable selection procedures instead of a small subset of major principal components in principal component regression. Our procedure consists of two steps to improve estimation and prediction. First, we reduce the number of principal components using the conventional principal component regression to yield the set of candidate principal components and then select principal components among the candidate set using sparse regression techniques. The performance of our proposals is demonstrated numerically and compared with the typical dimension reduction approaches (including principal component regression and partial least square regression) using synthetic and real datasets.

• Communications for Statistical Applications and Methods
• /
• 제29권2호
• /
• pp.251-261
• /
• 2022

As AI has a wide range of influence on human social life, issues of transparency and ethics of AI are emerging. In particular, it is widely known that due to the existence of historical bias in data against ethics or regulatory frameworks for fairness, trained AI models based on such biased data could also impose bias or unfairness against a certain sensitive group (e.g., non-white, women). Demographic disparities due to AI, which refer to socially unacceptable bias that an AI model favors certain groups (e.g., white, men) over other groups (e.g., black, women), have been observed frequently in many applications of AI and many studies have been done recently to develop AI algorithms which remove or alleviate such demographic disparities in trained AI models. In this paper, we consider a problem of using the information in the sensitive variable for fair prediction when using the sensitive variable as a part of input variables is prohibitive by laws or regulations to avoid unfairness. As a way of reflecting the information in the sensitive variable to prediction, we consider a two-stage procedure. First, the sensitive variable is fully included in the learning phase to have a prediction model depending on the sensitive variable, and then an imputed sensitive variable is used in the prediction phase. The aim of this paper is to evaluate this procedure by analyzing several benchmark datasets. We illustrate that using an imputed sensitive variable is helpful to improve prediction accuracies without hampering the degree of fairness much.