아마추어 골프 선수를 위한 코치-선수 관계 척도의 타당화: Rasch 평정척도 모형 적용

김세형,최재일,이준우,Kim, Sae Hyung,Choi, Jae Il,Lee, Jun Woo 한국데이터정보과학회 2013 한국데이터정보과학회지 Vol.24 No.6

이 연구는 Rasch 모형을 적용하여 아마추어 골프 선수들에게 적합한 코치-선수와의 관계 척도를 개발하고 타당화시키는데 목적이 있다. 코치-선수 관계 척도는 Kim과 Park (2008)이 개발한 한국판 척도를 검사내용에 기초한 증거를 토대로 수정 (11문항, 7척도)하여 아마추어 골프 선수 217명 (중학교, 고등학교, 대학교)에게 조사하였다. 그리고 WINSTEPS 프로그램을 이용하여 Rasch 모형의 기본가정인 일차원성을 검증 (주성분 분석)하였으며, 응답범주에 적절성은 단계조정값 (step calibration)을 통해 규명하였다. 이때 적합도 지수 (infit, outfit)를 통해 문항별 적합도를 검증하였으며, 골프경력 (10년미만, 10년이상)에 따라 차별기능문항을 추정하였다. 문항별로 추정되는 적합지수가 1.30 이상을 부적합하게 판단하였고, 분석에 모든 유의수준을.05로 설정하였다. 분석결과, Rasch 측정모형에 의해 설명되는 관찰분산이 20% 이상 (33.7%)으로 나타나 11문항의 일차원성 가정은 만족하였다. 그리고 응답범주 (7척도)를 단계조정값으로 분석한 결과에서 부적합하게 나타나 5점 척도로 재점수화하여 재분석한 결과에서 적합하게 나타났다. 특히 체계화된 응답범주 (5척도)를 이용하여 문항의 적합도를 추정한 결과, 상보성 요인에서 문항 10 (나는 최선을 다할 준비가 되어 있다)과 문항 11 (나는 호의적인 자세를 취한다)이 부적합 문항으로 나타났고 골프경력에 따라 차별기능문항 추정결과에서는 상보성 요인인 문항 11이 경력에 따라 비균일적으로 차별화되는 것으로 나타났다. 따라서 부적합하고 차별되는 두 문항을 제거하여 아마추어 골프 선수에게 적합한 코치-선수 관계 척도는 9문항에 5점 척도가 타당한 것으로 규명되었다. The purpose of this research was to develop and validate the coach-athlete relationship scale suitable to amateur golf players by applying the Rasch rating scale model. As the coach-athlete relationship scale, the Korean form of scale developed by Kim and Park (2008), which was revised based on the evidence on the basis of inspection contents, was used to conduct a survey on 217 amateur golf athletes. And the unidimensionality, which is the basic assumption of the Rasch model, was verified using the WINSTEPS program, and the appropriateness of the item category was established through the step calibration. The goodness of fit of each question was tested through the goodness-of-fit index and the differential item functioning (DIF) was estimated according to the golf career. When the goodness-of-fit index estimated for each question was 1.30 or more it was judged unfit and the significance level in the analysis was all set as.05. The results of the analysis showed that the measures variance explained by the Rasch measurement model was more (33.7%) than 20%, so the unidimensionality assumptions of the 11 questions (..hospitable posture when my coach is teaching) were satisfied. The result of analyzing the item category (7 scale) with step calibration was found to be unfit, but in the result of reanalyzing by rescoring into a 5-point scale, it was found to be fit. Particularly, in the result of estimating the goodness-of-fit using the systematized item category (5 scale), Question 10 (...my best when my coach is teaching) and Question 11 were found to be unfit, and as a result of estimating the differential functioning item according to golf career, Question 11 was found to be unevenly differentiated according to golf career. So the 5-point scale of Question 9 after eliminating the two questions which were unfit and differentiated was validated to be the coach-athlete relationship scale suitable to amateur golf athletes.

위계적 선형, 비선형 모형을 적용한 청소년기 주관적 건강평가 변화에 대한 체육시간활동에 종단적 영향 분석

김세형,Kim, Sae Hyung 한국데이터정보과학회 2016 한국데이터정보과학회지 Vol.27 No.4

이 연구는 청소년 남녀학생의 주관적 건강평가가 시간에 따라 어떠한 변화를 보이는지, 또한 그러한 변화에 대해 남녀학생의 체육시간활동이 어떠한 영향을 미치는지 검증하는데 목적이 있다. 한국아동 청소년패널조사 (KCYPS)에서 공개되는 중학교 1학년 5차년도 (2010년부터 2014년) 종단자료를 수집하여 위계적 선형, 비선형 모형 (HLM)을 적용하였다. HLM 6.08 프로그램을 사용하였으며, 유의수준은 5%로 설정하였다. 연구 결과는 다음과 같다. 첫째, 위계적 선형모형으로 추정한 결과를 보면, 남학생은 2010년부터 2014년까지 주관적 건강평가지수가 증가하였고, 여학생은 감소하였다. 둘째, 위계적 비선형 모형으로 추정한 결과를 보면, 남학생의 경우는 주관적 건강평가 지수가 증가하다가 고등학교 1학년이 되면서 감소하는 변화 형태를 보였다. 셋째, 여학생의 경우는 주관적 건강평가지수가 증가하다가 중학교 3학년이 되면서 감소하는 변화 형태를 보였다. 넷째, 남학생의 경우는 고등학교 1학년 시기에 적극적인 체육시간 활동은 주관적 건강평가에 정적 (positive)으로 유의한 영향을 준다. 다섯째, 여학생의 경우는 중학교 1학년 시기에 적극적인 체육시간활동은 주관적 건강평가에 부적 (negative)으로 유의한 영향을 준다. 이 연구를 토대로 위계적 선형, 비선형모형을 적용하여 청소년 건강과 체육에 관련된 연구가 지속되길 기대한다. The purpose of this study was to analyze longitudinal effect of physical education activity (PEA) score on self-rated health evaluation change (SHEC). This study used hierarchical linear and nonlinear models to investigate of the SHEC during the transition into adolescence (from middle school 1st to high school 2nd grade). Using the Korea children and youth panel survey (KCYPA), data were collected over the course of five years (from 2010 and 2014). HLM 6.8 computer program was used to analyze the data. The result were as follows. First, boys' SHEC increased across the five years, and girls' SHEC decreased across the five years. Second, boys' the self-rated health was increased across the three years and decreased across the two years. Third, girls' the self-rated health was increased across the two years and decreased across the three years. Fourth, the PEA score of 1st grade of high school showed a significant positive association with the boys' SHEC. Fifth, the PEA score of 1st grade of middle school showed a significant negative association with the girls' SHEC.

일반선형모형을 적용한 한국남자프로농구 경기기록분석 : 2014-2015 정규리그

김세형,Kim, Sae Hyung 한국데이터정보과학회 2015 한국데이터정보과학회지 Vol.26 No.4

이 연구는 일반선형모형에 이원변량분석과 위계적회귀분석을 적용하여 한국남자프로농구 경기기록 (2014-2015 정규리그 270경기)을 분석하였다. 이원변량분석 결과, 3점슛시도에서 승패와 홈원정 집단간에 상호작용효과가 통계적으로 유의하게 나타났다. 이 외에 변인들 (2점슛시도, 어시스트, 속공, 선수교체)은 모두 승패 집단간에는 통계적으로 유의한 차이가 나타났고, 홈원정경기 간에는 유의한 차이가 없게 나타났다. 위계적회귀분석 결과, 어시스트는 3점슛시도가 총득점에 미치는 영향에 대해 통계적으로 유의한 조절변수로 나타났으며, 속공은 어시스트가 2점슛성공에 미치는 영향에 대해 유의한 조절변수로 나타났다. 반면 어시스트는 2점슛시도가 총득점에 미치는 영향에, 그리고 속공은 어시스트가 3점슛성공에 미치는 영향에 유의한 조절효과가 없는 것으로 나타났다. 마지막으로 선수교체는 2점슛시도, 3점슛시도 그리고 어시스트가 총득점에 미치는 영향에 통계적으로 유의한 조절효과가 없는 것으로 나타났다. The purpose of this study was to analyze records of Korean pro-basketball using general linear model (two-way ANOVA and hierarchical multiple regression analysis). Korea Basketball League (KBL) informed the records (2014-2015 season) of this study. The eight variables (TA, 2PA, 3PA, 2P, 3P, Ast, TFB, CH) were selected in content validity. SPSS program was used to analyze general linear model. All alpha level was set at 0.05. Major results were as follow. 3PA had significant interaction effect between victory & defeat variable and home & away variable. Victory teams showed that 3PA was higher in home games than away games, and defeat teams was the other. 2PA, AS, TFB, and CH were selected significant variables affecting victory and defeat. In result of hierarchical regression, Ast had significant moderation effect between 3PA and TS. TFB also had significant moderation effect between AS between 2P. The other construct (Ast between 2PA and TS; TFB between AS between 3P) had no significant moderation effect. In the effect of 2PA, 3PA and Ast to TS, CH also had no significant moderation effect.

프로골프 경기기록을 활용한 다중집단분석 : 경로분석 적용

김세형,조정환,Kim, Sae Hyung,Cho, Jung Hwan 한국데이터정보과학회 2013 한국데이터정보과학회지 Vol.24 No.3

이 연구는 프로골프대회에서 기록되는 중요변인들 (드라이브거리, 페어웨이안착율, 그린적중율, 센드세이브율, 리커버리율, 평균퍼팅수)이 평균타수에 미치는 영향력에 대해 집단 간 차이를 분석하였다. 구체적으로 미국남자프로골프협회 (PGA), 미국여자프로골프협회 (LPGA), 한국남자프로골프투어 (KGT), 그리고 한국여자프로골프투어 (KLPGT)에서 측정, 공개하는 자료를 통해 PGA, LPGA, KPGA, KLPGA 집단 간에 중요변인들이 평균타수에 미치는 경로에 유의한 차이가 있는지를 검증하였다. 그 결과 PGA와 LPGA 모형 간에 드라이브거리와 그린적중율이 평균타수에 미치는 경로가 p <.05 수준에서 통계적으로 유의한 차이가 있는 것으로 나타났으며, KPGA와 KLPGA 모형 간에는 드라이브거리, 리커버리율, 그리고 평균퍼팅이 평균타수에 미치는 경로가 유의한 차이가 있는 것으로 나타났다. 또한 PGA와 KPGA 모형 간에 드라이브거리, 리커버리율, 그리고 평균퍼팅이 평균타수에 미치는 경로가p <.05 수준에서 통계적으로 유의한 차이가 있는 것으로 나타났으며, LPGA와 KLPGA 모형 간에는 모든 경로에서 p >.05 수준에서 통계적으로 유의한 차이가 없는 것으로 나타났다. 이 연구 결과는 남녀 국내 투어와 미국 투어의 골프 경기력의 구조 특성을 이해하는데 필요한 기초자료로 활용 할 수 있을 것이며 향후 투어 진출을 위한 유의한 정보가 될 수 있을 것이다. This study is to analyze effectiveness of golf skills (driving distance, rating of fairway, green in regulation, sand save ratio, recovery ratio, putting average) to average score using records of PGA, LPGA, KPGA, KLPGA. Independent variables were driving distance, rating of fairway, green in regulation, sand save ratio or recovery ratio, putting average. Dependent variable was the scoring average in this study. To analyze these variables, multi-group (PGA vs LPGA, KPGA vs KLPGA, PGA vs KPGA, LPGA vs KLPGA) path analysis was used through AMOS 18.0 program and significance level was set at 0.05. As the result, the variables that show significant differences of path coefficient between PGA model and LPGA model were driving distance and green in regulation to average score. The variables that show significant differences of path coefficient between KPGA model and KLPGA model were driving distance, recovery ratio, and putting average to average score. The variables that show significant differences of path coefficient between PGA model and KPGA model were driving distance, recovery ratio, and putting average to average score. There was not significant difference of path coefficient between LPGA model and KLPGA model.

한국남자프로농구 경기기록 분석을 통한 승패결정요인 추정: 2010-2011시즌, 2011-2012시즌 정규리그 기록 적용

김세형,이준우,이미숙,Kim, Sae-Hyung,Lee, Jun-Woo,Lee, Mi-Sook 한국데이터정보과학회 2012 한국데이터정보과학회지 Vol.23 No.5

한국남자프로농구 경기기록을 이용하여 승패결정요인을 분석하였다. 2010년 10월부터 2011년 3월까지, 2011년 10월부터 2012년 3월까지 치러진 정규리그 (540경기)의 기록을 분석하여 승패결정요인을 추정하였다. 한국농구연맹은 7개 공격변인과 7개 수비변인에 대한 자료를 제공하고 있다. 이들 자료 중에 공헌도와 공격력에 적용되는 6개 공격변인 (2점슛 성공률, 3점슛 성공률, 자유투 성공률, 공격리바운드, 어시스트, 턴오버)과 4개 수비변인 (수비리바운드, 스틸, 굿디펜스, 블록슛)이 승패에 미치는 영향을 통계적으로 분석하기 위해 로지스틱회귀분석과 의사결정나무분석을 적용하였다. 두 분석은 PASW와 Answer Tree 통계프로그램을 사용하였으며 모든 유의수준은 .05로 설정하였다. 로지스틱회귀분석 결과, 6개 공격변인 중 2점슛 성공률, 3점슛 성공률, 턴오버가 통계적으로 승패에 유의미한 영향을 미치고 4개 수비변인 중 굿디펜스를 제외한 수비리바운드, 스틸, 블록슛이 통계적으로 승패에 유의미한 영향을 미치는 것으로 나타났다. 그리고 공격변인 의사결정나무분석 결과에서는 2점슛 성공률이 51%-58%이며, 3P%가 31%를 초과하고 TO가 11개 이하일때 승리할 수 있는 확률이 80.85%로 가장 높게 나타났다. 이에 반해 수비변인 의사결정나무분석 결과, 수비리바운드가 24개를 초과하고 스틸이 6개를 초과하며, 블록슛이 2개를 초과할 때 승리할 수 있는 확률이 94.12%로 가장 높게 나타났다. The purpose of this study was to estimate the determinants of victory and defeat through analyzing records of Korean men pro-basketball. Statistical models of victory and defeat were established by collecting present basketball records (2010-2011, 2011-2012 season). Korea Basketball League (KBL) informs records of every pro-basketball game data. The six offence variables (2P%, 3P%, FT%, OR, AS, TO), and the four defense variables (DR, ST, GD, BS) were used in this study. PASW program was used for logistic regression and Answer Tree program was used for the decision tree. All significance levels were set at .05. Major results were as follows. In the logistic regression, 2P%, 3P%, and TO were three offense variables significantly affecting victory and defeat, and DR, ST, and BS were three significant defense variables. Offensive variables 2P%, 3P%, TO, and AS are used in constructing the decision tree. The highest percentage of victory was 80.85% when 2P% was in 51%-58%, 3P% was more than 31 percent, and TO was less than 11 times. In the decision tree of the defence variables, the highest percentage of victory was 94.12% when DR was more than 24, ST was more than six, and BS was more than two times.

한국남자프로농구 경기기록 분석을 통한 승패결정요인 추정: 2010-2011시즌, 2011-2012시즌 정규리그 기록 적용

김세형,Kim, Sae Hyung 한국데이터정보과학회 2012 한국데이터정보과학회지 Vol.23 No.6

Rasch RSM과 PCM을 적용한 청소년 자아인식 측정척도 재구성 : 체육수업 운동 참여유무 집단 간 차이에 따른 타당화

김세형(Kim, Sae-Hyung) 한국체육과학회 2019 한국체육과학회지 Vol.28 No.3

The purpose of this study was to reconstruct of the youth self-awareness measurement scale(SAMS) utilizing Rasch rating scale model(RSM) and partial credit model(PCM), and verified known group difference validity by physical education class participation. The subjects were 3rd year high school students 1492(746 male and 746 female students), which were investigated by the Korea child and youth panel study(KCYPS). 40-item(10-item: self-esteem, 14-item: ego-resiliency, 8-item: ego-identity, 8-item: career-identity) and 4-point scale were generated. The Rasch measurement computer program, JMetrik 4.1.1 was used to analyze the data. Model fit was decided by infit and outfit index (≤1.20). The results were as follow. First Rasch RSM and PCM showed that 4-point scale was appropriated scale that was verified by the step calibration and outfit index. Second, the eight items were over the standard setting (1.20) of the infit or outfit in Rasch RSM and PCM. Third, one item as the DIF(differential item functioning) between gender in Rasch RSM and PCM. Fourth, Rasch RSM and PCM showed the item-ability map that was verified difference of the two model. Finally, this study reconstructed as 32-item and 4-point scale for youth SAMS. In addition, there was a statistically significant mean difference in the SAMS score between categorized the physical education class participation group, [F (1, 1490)=345.64, p<.001, n<SUP>2</SUP>p =.19]. This result supported the known group difference validity evidence of the SAMS that reconstructed in this study.

골프선수를 위한 부모교육관여 척도의 적합도 검증

김세형(Kim, Sae-Hyung),최봉암(Choi, Bong-Am),이준우(Lee, Jun-Woo) 한국체육과학회 2018 한국체육과학회지 Vol.27 No.5

The purpose of this study was to validate of the parent education participation measurement scale(PEPMS) for golf player using Rasch partial credit model. Establishing content and face validity, 30-item(24-item: autonomy encourage factor, 6-item: exercise information supply factor) and 5-point scale were generated. The scale was administered to 213 golf player. The Rasch measurement computer program, WINSTEPS 4.2.0 was used to analyze the data. Model fit was decided by Infit and Outfit index (≥.60 and ≤1.40). The results are as follow. First 4-point scale was more appropriated than the 5-point scale that was showed the step calibration index increased step by step in each item. Second, the two factors were satisfied by the global fit statistics index as RMSR (Root mean square residual). Third, 2-item in the autonomy encourage factor was selected as the DIF(differential item functioning) between gender, and nothing item in the exercise information supply factor as the DIF between gender. Fourth, one item in the autonomy encourage factor was over the standard item fit (infit=1.40, outfit=1.55). The results indicated that 21 items in the autonomy encourage factor and 6 items in exercise information supply factor were finally selected. This study verified and showed the PEPMS that constructed 27-item and 4-point scale for golf player. In addition, the newly constructed this scale for golf players should be validated to increase external validity.

한국남자프로농구 경기기록 분석을 통한 승패결정요인 추정방법 비교

김세형(Kim, Sae-Hyung) 한국체육과학회 2012 한국체육과학회지 Vol.21 No.3

The purpose of this study was to compare estimating method of victory and defeat through analyzing records of Korean men pro-basketball. Korea Basketball League(KBL) informs the records that are seven offence variables(2P%, 3P%, FT%, OR, AS, TO, DK), and seven defense variables(DR, ST, GD, BS, WFT, WOFT, TF). This study used 12 variables(2P%, 3P%, FT%, OR, AS, TO, DR, ST, GD, BS, WFT, WOFT) that excepted the DK and TF. To analyze the factor of the victory and defeat, the statistics’ design was that the 12 variables were independent variables and the victory and defeat was dependent variable. Discriminant analysis, logistic regression, decision tree analysis and artificial neural network analysis were used to compare result. PASW program was used and all alpha level was set at .05. Major results were as follow. The result of discriminant analysis and logistic regression was that DR, 3P%, 2P%, ST, TO were the significantly high rank variables. The decision tree analysis was that DR, 2P%, 3P%, ST, TO, and artificial neural network analysis was DR, 2P%, 3P%, TO, ST were the significantly high rank variables. All estimating methods in this study showed the defence rebound was the most important effect to victory.

다층성장모형을 적용한 청소년기 체육시간 활동변화에 대한 자아개념과 또래애착에 종단적 영향 분석

김세형(Kim, Sae-Hyung) 한국체육과학회 2016 한국체육과학회지 Vol.25 No.3

The purpose of this study was to analyze longitudinal effect of the factor, self-concept and peer-attachment on physical education activity change(PEAC). This study used multilevel growth model to investigate of the PEAC during the transition into adolescence (from the middle school 1st to the high school 2nd grade). Using the Korea children and youth panel survey(KCYPA), data were collected over the course of five years(from 2010 and 2014). For this study, self-concept factors(self-esteem, selfresilience) and peer-attachment factors(peer-trust, peer-estrangement) were considered time-invariant predictors of the PEAC. HLM 6.8 computer program was used to analyze the data. Alpha level was set at .05. The result were as follows. First both boys and girls’ PEAC showed lower level of across the five years, and random effect were significant variance component that means each student had different of the PEAC. Second, boys had precisely nonlinear change that was higher level of across the two years and lower level of across the three years. Third, girls had minutely nonlinear change that was lower level of across the two years and also lower level of the other years. Fourth, the self-concept factors showed no significant effect. Fifth, the peer-attachment factor showed significant nonlinear positive effect to the boys’ PEAC. Sixth, the peer-trust variable showed significant linear positive effect to girls’ PEAC.