A Comparative Study of Generalized Maximum Entropy Estimator for the Two-way Error Component Regression Model

전수영,진서훈 한국자료분석학회 2009 Journal of the Korean Data Analysis Society Vol.11 No.2

Recently the study of the panel data has received attention in the literature of the regression model. The model has been usually dealing with the complete data. However, in a practical manner it is rare for data to be complete. For ill-posed problems, Song and Cheon(2006) proposed a robust generalized maximum entropy estimator less sensitive to the assumption and limited situation in a panel regression model with the only individual effect. However, the time effect needs to be considered in panel data. This paper considers a two-way error component model with both individual and time effects in ill-posed problems and proposes the generalized maximum entropy(GME) estimator for the unknown parameters. This estimator is compared with a variety of existing estimators on the simulated dataset. The numerical results are in favor of the new estimator in terms of its quality when the data are ill-posed. Recently the study of the panel data has received attention in the literature of the regression model. The model has been usually dealing with the complete data. However, in a practical manner it is rare for data to be complete. For ill-posed problems, Song and Cheon(2006) proposed a robust generalized maximum entropy estimator less sensitive to the assumption and limited situation in a panel regression model with the only individual effect. However, the time effect needs to be considered in panel data. This paper considers a two-way error component model with both individual and time effects in ill-posed problems and proposes the generalized maximum entropy(GME) estimator for the unknown parameters. This estimator is compared with a variety of existing estimators on the simulated dataset. The numerical results are in favor of the new estimator in terms of its quality when the data are ill-posed.

Bayesian Inference in Phylogeny via Sequential Stochastic Approximation Monte Carlo

전수영,김효성 한국자료분석학회 2009 Journal of the Korean Data Analysis Society Vol.11 No.3

The Sequential Stochastic approximation Monte Carlo(SSAMC) algorithm has recently been proposed by Cheon and Liang(2008) as a new phylogenetic tree construction method. SSAMC is an efficient algorithm to alleviate local trap problems and the curse of dimensionality in simulations simultaneously by making use of the sequential structure of phylogenetic trees in conjunction with stochastic approximation Monte Carlo(SAMC) simulations. In this paper, we discuss the application of SSAMC to the Bayesian inference in phylogeny. Two real datasets are used for SSAMC to show the capability of a phylogeny tree reconstruction and existing Bayesian methods, BAMBE and MrBayes, are applied for comparison. Numerical results indicate that SSAMC is a useful algorithm for phylogeny inference in terms of quality of the resulting phylogenetic trees.

오차항이 SAR(1)을 따르는 공간선형회귀모형에서 일반화 최대엔트로피 추정량에 관한 연구

전수영,임성섭,Cheon, Soo-Young,Lim, Seong-Seop 한국통계학회 2009 Communications for statistical applications and me Vol.16 No.2

지역적 공간의 특성을 고려한 공간선형회귀모형을 다루는 대부분의 연구들에서 사용되고 있는 자료는 완전한 상태임을 고려하고 있다. 하지만 공간선형회귀모형을 정확히 추론함에 있어서 완전한 자료가 사용 가능한 경우는 그다지 많지가 않은 것이 현실이다. 만약 이러한 상황을 고려하지 않고 통계적 추론을 할 경우 잘못된 결론이 도출될 수 있다. 본 연구에서는 오차항이 일차 공간자기상관을 따르는 공간선형회귀모형에서 자료가 불완전한 상태 일 경우 일반화 최대엔트로피 형식을 이용하여 미지의 모수를 추정하는 방법을 제안하였고 몬테카를로 모의실험을 통하여 여러 전통적인 추정량들과 효율성을 비교하였다. 그 결과, 자료가 불완전한 상태에서 일반화 최대엔트로피 추정량이 다른 추정방법들에 비해 효율적인 추정치를 제공하였다. This paper considers a linear regression model with a spatial autoregressive disturbance with ill-posed data and proposes the generalized maximum entropy(GME) estimator of regression coefficients. The performance of this estimator is investigated via Monte Carlo experiments. The results show that the GME estimator provides efficient and robust estimate for the unknown parameter.

Evolutionary Monte Carlo EM for Change Point Analysis

전수영 한국자료분석학회 2019 Journal of the Korean Data Analysis Society Vol.21 No.2

In the change point inference of incomplete data, the expectation-maximization (EM) algorithm is often difficult to handle, and thus the Markov chain Monte Carlo (MCMC) method has been used in this area for a long time. However, the traditional MCMC algorithm tends to be trapped to local minima when generating samples from the posterior distribution of change points. To overcome this problem, various advanced Monte Carlo methods have been proposed, but still somewhat difficult to use. This paper proposes an evolutionary Monte Carlo EM (EMCEM) algorithm that combines the evolutionary Monte Carlo algorithm (EMC) with EM using the maximum likelihood method for efficient and user-friendly sampling. EMC has incorporated several attractive features of genetic algorithms and simulated annealing into the framework of MCMC. EMCEM is compared with reversible jump MCMC version of EM (RJMCMCEM), the stochastic approximation version of EM (SAEM) and the stochastic approximation Monte Carlo version of EM (SAMCEM) on simulated and real datasets. The numerical results indicate that EMCEM can outperform RJMCMCEM and SAEM by producing much more accurate parameter estimates, and EMCEM is comparable to SAMCEM.

평내동 위원회, 2015년 청소년문화축제 평가

전수영 한국자치학회 2016 월간 주민자치 Vol.51 No.-

The Mediating Effect of Social Capital on the Relationship Between Public Health Managers’ Transformational Leadership and Public Health Nurses’ Organizational Empowerment in Korea Public Health

전수영 한국간호과학회 2017 Asian Nursing Research Vol.11 No.4

Purpose: This study was to verify the effect of public health nurse's (PHN's) social capital on the relationship between public health manager's (PHM's) transformational leadership and PHN's organizational empowerment in Korea public health. Methods: This was a cross-sectional descriptive study involving 303 PHNs from public health centers in Daegu and Gyeongsangbuk-do cities in South Korea. Data were collected from February 29, 2016 to April 8, 2016, using structured questionnaires which included general characteristics, transformational leadership, organizational empowerment, and social capital. Data were analyzed using descriptive statistics, correlations, and structural equation model. Results: PHM's transformational leadership has a positive effect on PHN's social capital and PHN's organizational empowerment. Social capital had a mediating effect between transformational leadership and organizational empowerment in PHNs. Conclusion: This study suggests that PHM's transformational leadership is a contributing factor to improve PHN's organizational empowerment, and transformational leadership can lead to improve PHN's organizational empowerment through PHN's social capital. So, an intervention program to promote organizational empowerment should include strategies to enhance PHM's transformational leadership as well as to improve PHN's social capital.

Mediating Effect of Social Capital between Transformational Leadership Behavior and Organizational Citizenship Behavior in Hospital Nurses

전수영 간호행정학회 2017 간호행정학회지 Vol.23 No.5

Purpose: This study was conducted to examine the current status of transformational leadership behavior (TLB) and organizational citizenship behavior (OCB), and to investigate the mediating effect of social capital on the relationship between TLB and OCB in hospital nurses. Methods: A cross-sectional descriptive study design was adopted with a convenience sample of 219 nurses from two university-affiliated teaching hospitals in South Korea. Results: The survey instruments measured TLB, OCB, and social capital. Data were analyzed through t-tests, ANOVA, Scheffé’s test, Baron and Kenny’s regression method. The average level of TLB was 3.13 points, 3.64 points in OCB, and 3.24 points in social capital. Positive correlations were found between TLB, OCB, and social capital. Hospital nurses’ social capital showed a significant mediating effect on the relationship between TLB and OCB. Conclusion: TLB is a contributing factor to better OCB, and TLB can lead to improve OCB through social capital. Intervention to improve social capital of nurses in health-care organizations has important implications for OCB improvement.

오차항이 AR(1)을 따르는 Box-Cox 변환 회귀모형에서 모형 식별을 위한 검정

전수영,윤석진,황선영,송석헌,Cheon, Soo-Young,Yoon, Seok-Jin,Hwang, Sun-Young,Song, Seuck-Heun 한국통계학회 2008 응용통계연구 Vol.21 No.2

본 연구에서는 오차항이 AR(1)을 따르는 회귀모형에서 올바른 추론을 도출하고자 모형식별의 문제를 다루었다. 이를 위해 Box-Cox 변환된 회귀모형을 고려하여 (i) Box-Cox 변환모형과 AR(1) 오차에 대한 동시 검정, (ii) AR(1) 오차가 존재하는 모형에서의 Box-Cox 변환모형에 대한 검정 그리고 (iii) 모형이 Box-Cox 변환되어 있을 때 오차가 AR(1) 과정을 따르는지에 대한 LM 검정통계량을 유도하였다. 특히 LM 검정방법에서 여러개의 모수가 비선형관계를 형성하고있어 정보행렬의 추정은 계산상 매우 어렵다. 따라서 정보행렬의 원소에 대한 기대값을 구함에 있어 Taylor전개를 이용하여 정보행렬을 구하고 이에 기반을 둔 LM 검정통계량($LM_E$)를 제안하고 모의실험결과 $LM_E$가 기존의 헤시안행렬에 기반을 둔 LM 검정통계량($LM_H$)에 비하여 유의수준을 잘 유지하고 있는 것으로 나타났다. This paper derives joint and conditional Lagrange multiplier tests based on information matrix for testing functional form and/or the presence of autocorrelation in a regression model. Small sample properties of these tests are assessed by Monte Carlo study and comparisons are made with LM tests based on Hessian matrix. The results show that the proposed $LM_E$ tests have the most appropriate finite sample performance.

국내 상위 인터넷 패션 전문 몰의 메인 페이지 상세페이지 시각적 이미지 기법에 관한 분석연구

전수영,문희강 한국의류학회 2008 한국의류학회 학술대회논문집 Vol.2008 No.1

건강검진 검사운영 프로세스 재설계를 통한 검사 운영 능력 향상

전수영 한국의료QA학회 2008 가을학술대회 Vol.2008 No.2