호흡곤란 환자에 대한 혈액검사 결과들의 수량화 연구

박철용,Park, Cheol-Yong 한국데이터정보과학회 2011 한국데이터정보과학회지 Vol.22 No.3

Park et. al (2010) proposed a statistical model for determining the admission or discharge of 668 patients with a chief complaint of dyspnea by the number of 11 blood tests belonging to the corresponding discharge intervals. Since this method does not take into consideration the importance of each blood test result, its performance might not be optimally good. In this study, we employ a quantification method to evaluate the importance of those blood test results, and then provide a new statistical mode that takes the importance into consideration. The results show that the performance of this new model is a little better than that of the model by Park et. al (2010).

선형회귀 모형에서 자기공분산 기반 추정

박철용,Park, Cheol-Yong 한국데이터정보과학회 2011 한국데이터정보과학회지 Vol.22 No.5

In this study, we derive an estimator based on autocovariance for the regression coefficients vector in the multiple linear regression model. This method is suggested by Park (2009), and although this method does not seem to be intuitively attractive, this estimator is unbiased for the regression coefficients vector. When the vectors of exploratory variables satisfy some regularity conditions, under mild conditions which are satisfied when errors are from autoregressive and moving average models, this estimator has asymptotically the same distribution as the least squares estimator and also converges in probability to the regression coefficients vector. Finally we provide a simulation study that the forementioned theoretical results hold for small sample cases.

척도화 향상도에 근거한 처방 선택

박철용,Park, Cheol-Yong 한국데이터정보과학회 2011 한국데이터정보과학회지 Vol.22 No.2

In this study, we propose order selection methods based on scaled lift. This study is proposed to overcome the problem that the lift used by Park and Kim (2010) takes unbounded values and thus it is hard to know how big (or small) lift value is big (or small). The first scaled lift just scales lift, so that it takes values between 0 and 1, and the second scaled lift scales lift-1, so that it takes values between -1 and 1. In other words, the first method scales lift only and the second methods ceters and scales lift. We apply order selection methods based on scaled lift to acute appendicitis patients in emergency room and compare them with the results based on lift.

면접점수 표준화 방법 모의실험 비교

박철용,Park, Cheol-Yong 한국데이터정보과학회 2011 한국데이터정보과학회지 Vol.22 No.2

In this study, we perform a simulation study to compare frequently used standardization methods for interview scores based on trimmed mean, rank mean, and z-score mean. In this simulation study we assume that interviewer's score is influenced by a weighted average of true interviewee's true score and independent noise whose weight is determined by the professionality of the interviewer. In other words, as interviewer's professionality increases, the observed score becomes closer to the true score and if interviewer's professionality decreases, the observed score becomes closer to the noise instead of the true score. By adding interviewer's tendency bias to the weighed average, final interviewee's score is assumed to be observed. In this simulation, the interviewers's cores for each method are computed and then the method is considered best whose rank correlation between the method's scores and the true scores is highest. Simulation results show that when the true score is from normal distributions, z-score mean is best in general and when the true score is from Laplace distributions, z-score mean is better than rank mean in full interview system, where all interviewers meet all interviewees, and rank mean is better than z-score mean in half split interview system, where the interviewers meet only half of the interviewees. Trimmed mean is worst in general.

감성의 시대

박철용,Park, Cheol-Yong 한국가톨릭의료협회 2008 Health & mission Vol.11 No.-

스포츠영재성 검사 항목과 코스타스 점수간의 연관성 분석

박철용,이미숙,Park, Cheol-Yong,Lee, Mi-Sook 한국데이터정보과학회 2011 한국데이터정보과학회지 Vol.22 No.1

The Korea Sport Talent Search System (KOSTASS) can easily assess potential of Korean youth in 23 sport events and to identify sports talents who have high potential in track-and-field, swimming and gymnastics. The purpose of present study was to analysis relationship between sports talent test scores and KOSTASS scores. Physique, physical fitness, motor ability and physiological tests including skeletal age were administrated. Data of 201 elementary students who aged 7 to 12 living in Seoul area were collected. For pure association analysis, Pearson correlation coefficient and partial correlation coefficient are used and stepwise regression analysis is used for selecting important sports talent test scores. The results show that skeletal age, weight, chest circumference, 50-meter run, and half-squat jump have relatively low impact on six KOSTASS scores. The KOSTASS program would contribute to identify talented youth in sports among Korean youth population and success for international sports competition.

단순 선형회귀 모형에서 자기공분산에 근거한 최적 추정 방법

박철용,Park, Cheol-Yong 한국데이터정보과학회 2009 한국데이터정보과학회지 Vol.20 No.2

이 논문에서는 단순 선형회귀 모형에서 회귀 계수의 최적 추정량을 구할 수 있는 자기공분산에 근거한 추정 방법을 제시하였다. 이 방법이 직관적으로 매혹적이지는 않지만 이 최적 추정량이 해당 회귀 계수의 불편추정량이 된다. 설명변수가 0과 1사이의 균등간격의 값을 가지면, 오차가 자기회귀 이동평균 모형을 따르면 성립하는 조건 하에서 이 최적 추정량이 최소제곱 추정량과 점근적으로 통일한 분포를 가진다는 것을 보였다. 추가적으로 똑같은 조건 하에서 이 최적 추정량이 해당 회귀 계수에 확률상 수렴한다는 것을 자체적으로 입증하였다.

최적 시계열 모형에 기초한 오존주의보 날짜 예측

박철용,김현일,Park, Cheol-Yong,Kim, Hyun-Il 한국데이터정보과학회 2009 한국데이터정보과학회지 Vol.20 No.2

이 논문에서는 대구 두 개 동의 시간별 오존농도를 예측하는 모형으로 회귀, 자기회귀누적이동평균, 자기회귀누적이동평균 오차를 가지는 회귀 같은 선형모형들을 고려하였다. 평균제곱오차제곱근에 근거하여 보았을 때 한 개 동에서는 자기회귀누적이동평균 모형이 최적의 모형으로 선택되었고, 다른 동에서는 자기회귀누적이동평균 오차를 가지는 회귀 모형이 최적 모형으로 선택되었다. 이 최적의 모형으로부터 나온 잔차들의 변동석 분석을 수행하였는데 이를 통해 120 ppb를 넘는 오존 주의보 날짜를 예측하였다. 2000년에서 2003년까지의 훈련용 자료에 근거하여 보았을 때 잔차값의 경계값으로 35 ppb를 잡았을 때 오존주의보 날짜를 예측하는데 좋은 결과를 보였다. 하나의 동에서는 2004년의 오존주의보가 발령된 이틀 중 하루와 나머지 주의보가 발령되지 않은 364일을 모두 정확히 예측하였다. 다른 동에서는 2004년의 오존주의보가 발령된 하루와 주의보가 발령되지 않은 365일을 모두 정확히 예측하였다.

맹장염 수술에서 임상경로 개발을 위한 처방 선택 방법

박철용,김태윤,Park, Cheol-Yong,Kim, Tae-Yoon 한국데이터정보과학회 2010 한국데이터정보과학회지 Vol.21 No.1

In this study, we propose a new order selection method for clinical pathway development in acute appendectomy. This method is based on the lift concept which is popular in association rule discovery and, starting from the orders with more frequencies, sequentially removes the negatively associated orders which have lift values somewhat less than one. The orders in acute appendectomy we consider in this study are test and medical treatment items respectively, and since there are different order patterns before, during, and after operation, three different order selections are made for each. The selection results are somewhat different from those selected only by the order of more frequencies. Specifically, the selection results of two methods are different in 1 or 2 orders for medical treatment items and in maximum 5 orders for test items, respectively.

사영에 근거한 면접 점수의 통계적 모형

박철용,김현욱,Park, Cheol-Yong,Kim, Hyun-Wook 한국데이터정보과학회 2012 한국데이터정보과학회지 Vol.23 No.3

In this study, we propose a statistical model based on projection that generates interview scores. In this model, each interviewee's true score and its related variable are viewed as X, Y values respectively in the two dimensional plane, and each interviewer's score is the projected score of true score X to the axis rotated by some angle, which reflects the interviewer's perspective. Each interviewer's observed interview score is obtained by adding personal bias and observed error to this projected score. We compared commonly used standardizing methods of interview scores such as trimmed mean method, rank method, and z-score method based on the proposed statistical model. In this simulation, two types of interview methods, two numbers of interviewers, two degrees of interviewers' expertise and two distributions and three correlations between actual score and its related variable are all considered.