• Journal of the Korea Society of Computer and Information
• /
• v.8 no.1
• /
• pp.20-29
• /
• 2003

According as quantity of information is augmented rapidly in World Wide Web, users are investing more times finding correct information to on. Search function that a search agent is personalized according to user's preference degree or search objective to solve these problem should be offered. Therefore, a search agent accumulates experienced knowledge connected with user's past search in this research. When new query was given, search agent offered learning function of intelligence that decides category group through estimation method of similarity using this knowledge. So this paper showed that case based search can bring superior result in the correctness rate than other search method.

• Proceedings of the Korean Association for Survey Research Conference
• /
• 2000.06a
• /
• pp.137-159
• /
• 2000

In this paper, the following facts have been reviewed: First, statistics should have the characteristics of descriptive, inferential, and applicative statistics in "information-Knowledge Society." Second, the computer has been employed in the process data collection and data analysis for producing the statistics with timeliness and efficiency. Third, we have to develop a statistical development plan which lays emphasis on the production of applicative statistics in the coming "Internet Cyber Society." In addition, we investigaated statistical survey methods. The prospects of internet surveys were also investigated here. On the basis of the above review and investigation. we suggested "an integrated system of computer-assisted statistical surveys" that can be applied to all kinds of surveys and statistics.nds of surveys and statistics.

• Survey Research
• /
• v.1 no.2
• /
• pp.137-159
• /
• 2000

In this paper, the following facts have been reviewed: First, statistics should have the characteristics of descriptive, inferential, and applicative statistics in "information-Knowledge Society." Second, the computer has been employed in the process of data collection and data analysis for producing the statistics with timeliness and efficiency. Third. we have to develop a statistical development plan which lays emphasis on the production of applicative statistics in the coming "Internet Cyber Society" In addition, we investigated overall status of computer utilization, and the process of the development of computer-assisted statistical survey methods. The prospects of internet surveys were also investigated here. On the basis of the above review and investigation, we suggested "an integrated system of computer-assisted statistical surveys" that can be applied to all kinds of surveys and statistics.

• The Korean Journal of Applied Statistics
• /
• v.1 no.2
• /
• pp.61-65
• /
• 1987

Randomization is one of the principles that should be adopted in comparative experiments. Randomization is well known as a useful tool for averaging out the effects of external factors. It also validates statistical inference based on mathematical model. This teaching meterial is designed for the purpose of illustrating the role of randomization.

• The Korean Journal of Applied Statistics
• /
• v.4 no.2
• /
• pp.179-193
• /
• 1991

In this paper, we introduce various methods of PR techniques initiated by S. Warner in 1960's and examine the maximum likelihood estimator for them. One of the main subjects of this paper is to represent Warner model, Unrelated Question Model, and Multi-Proportion Model in linear model. The other subject is to study the inference of PR model by using the Bayesian Approach.

• The Korean Journal of Applied Statistics
• /
• v.12 no.2
• /
• pp.553-561
• /
• 1999

이변량 정규분포의 상관계수 $\rho$에 대한 검정 및 신뢰구간을 구하는 모수적 방법으로서 Fisher의 z 변환과 해당하는 점근적 분포가 널리 쓰이고 있다. 본 연구에서는 이에 대한 대안으로서 직교변환과 F 분포를 활용하는 방법을 제시한다. 후자의 방법이 전자와 비교하여 사실상 대등하면서도 설명은 오히려 쉬우므로 통계학 교육에 더 적합하다고 생각한다. 또한, 시험적으로, $H_0$:$\rho$=$\rho_0$에 대한 모수적 임의화 검정법을 제안한다.

• The Korean Journal of Applied Statistics
• /
• v.12 no.2
• /
• pp.479-490
• /
• 1999

선형시계열모형인 AR(1)모형과 비선형시계열모형인 RCA(1), ARCH(1)모형에서 이상치(Outlier)가 존재할 경우 최소제곱추정량과 M추정량간의 점근상대효율(Asymptotic Relative Efficiency: ARE)을 구하여 두 추정량의 로버스트 성질을 비교·분석하였다. 또한 여러 유계함수(Huber, Tukey, Andrews, Hampel)들을 M추정함수에 적용하여 각각의 유계함수들을 비교·분석하였다.

• Proceedings of the Korean Statistical Society Conference
• /
• 2000.11a
• /
• pp.39-43
• /
• 2000

분산 추정 및 신뢰구간 추정의 한 방법으로 널리 쓰이고 있는 붓스트랩 방법을 복합표본에 적용하는 방법에 대해 알아보았다. 복합 표본은 유한 모집단에서 추출되고 추출확률이 다르기 때문에 i.i.d. 표본에 기초하여 개발된 전통적인 붓스트랩 방법을 직접 적용하면 추론의 오류가 발생할 수 있다. 본 연구에서는 복원 확률비례표본과 랜덤그룹표본에 붓스트랩을 적용하는 방법을 알아보았다.

• Proceedings of the Korean Statistical Society Conference
• /
• 2005.05a
• /
• pp.1-6
• /
• 2005

SAS의 PROC MIXED는 ANOVA 추정량보다 더 다양한 잔차최대우도추정법 또는 최대우도추정법으로 모수들을 추론할 수 있다. 혼합모형에 속하는 불균형중첩오차구조를 갖는 선형회귀모형에서 랜덤효과에 해당되는 그룹간의 분산과 고정효과에 해당되는 회귀계수들에 대한 신뢰구간을 구하기 위하여 대표본인 경우와 소표본인 경우에 대하여 PROC MIXED를 사용한다. 시뮬레이션을 실행한 결과, 대표본인 경우에는 모수들의 신뢰구간을 구하기 위하여 PROC MIXED를 활용할 수 있지만, 소표본인 경우에는 PROC MIXED를 사용할 경우, 그룹간 분산과 회귀계수 가운데 하나인 절편항에 대한 신뢰구간은 시뮬레이터된 신뢰계수가 명시한 신뢰계수를 지키지 못하는 것을 보인다.

• The Korean Journal of Applied Statistics
• /
• v.7 no.2
• /
• pp.263-268
• /
• 1994

Thomas Bayes assumed uniform prior for the location $\theta$ of a billiard ball W in his historic 1764 paper. In this study, following mathematical derivation of the uniform distribution from several assumptions that are plausible on te billiard table, it is argued that the probabilistic meaning of Bayes' uniform prior (especially in Billiard Problem) is not just sujective but logical.