기계학습을 통한 TIMSS 2011 중학생의 수학 성취도 관련 변수 탐색 = TIMSS 2011 Predictors Relating to Korean 8th Graders’ Mathematics Achievement, Explored Via Machine Learning

국문 초록 (Abstract)

본 연구는 기계학습적 접근법인 LASSO 기법을 우리나라 TIMSS 2011 중학교 2학년 자료에 적용하였다. TIMSS의 100개의 설명변수를 모형에 모두 투입하여 22개 변수를 선택하였을때, 이 모형의 예측정확도는 약 80%였다. 학생의 수학적 자기효능감, 수학에 대한 태도, 어머니의 교육 수준, 그리고 가정 보유 장서 수와 같은 가정의 교육자원 변수가 학생의 수학 성취수준에 영향을 미치는 것으로 나타났으며, 이는 기존 연구 결과와 일치하였다. 본 연구에서 학생의 수학 성취수준과 관련과 있다고 새롭게 탐색된 변수로 수학숙제 시간, 학생의 과학적 자기효능감, 과학숙제 부여 빈도 등이 있었다. 연구 함의 및 향후 연구 주제 또한 논의되었다.

다국어 초록 (Multilingual Abstract)

A substantial body of research has been conducted on factors relating to students’ math achievement with TIMSS. However, most studies have focused on selected a few factors instead of utilizing hundreds of variables TIMSS provides, and have employed conventional statistical methods. This study aimed to investigate possible sets of predictors from a totally different approach: LASSO, currently one of the most popular machine learning techniques. Korean 8th graders’ TIMSS 2011 were used as the sample, and the prediction accuracy of the LASSO model was about 80% with the selected 22 out of 100 predictors. As results, students’ math efficacy, attitudes toward math, mother’s education level, and home educational resources including amount of books at home were influential to their math achievement, which was consistent with previous studies. Additionally, math homework completion time, student’s science self-efficacy, and science homework frequency were newly found important predictors. Implications and future research topics are discussed.

참고문헌 (Reference)

1 김완섭, "로지스틱 회귀분석과 데이터마이닝 분석을 이용한 컴퓨터 교양교육 성과의 요인에 대한 연구" 한국교양교육학회 6 (6): 743-767, 2012

2 유진은, "데이터 마이닝 기법을 통한 교육 패널데이터 분석: 벌점회귀모형과 KYPS 자료" 교육연구소 17 (17): 1-19, 2016

3 김진, "데이터 마이닝 기법을 이용한 특성화고등학교 교육성과 분석" 한국컴퓨터교육학회 17 (17): 21-33, 2014

4 김완섭, "대학 컴퓨터 실습 교양과목에서의 학업성취 요인에 대한 연구" 한국정보교육학회 17 (17): 433-447, 2013

5 Winnaar, L. D., "Understanding school effects in South Africa using multilevel analysis : Finding from TIMSS 2011" 13 : 151-170, 2015

6 Dettmers, S., "The relationship between homework time and achievement is not universal : Evidence from multilevel analyses in 40countries" 20 : 375-405, 2009

7 Trautwein, U., "The homework-achievement relation reconsidered : Differentiating homework time, homework frequency, and homework effort" 17 : 372-388, 2007

8 Engel, L. C., "The harder side of globalisation : Violent conflict and academic achievement. Globalisation" 7 : 433-456, 2009

9 Hastie, T., "The elements of statistical learning: Data mining, inference, and prediction" Springer 2009

10 Mills, J. D., "The development of statistical literacy skills in the eighth grade : exploring the TIMSS data to evaluate student achievement and teacher characteristics in the United States" 19 : 323-345, 2013

11 Mikk, J., "Students’ homework and TIMSS 2003 mathematics results"

12 Azina, I. N., "Student factors and mathematics achievement : Evidence from TIMSS 2007. Eurasia Journal of Mathematics" 8 : 249-255, 2012

13 Ng, K. T., "Relationship between affect and achievement in science and mathematics in Malaysia and Singapore" 30 : 225-237, 2012

14 Tibshirani, R., "Regression shrinkage and selection via the LASSO" 58 : 267-288, 1996

15 Cheng, Q., "Quality mathematics instructional practices contributing to student achievements in five high-achieving Asian education systems : An analysis using TIMSS 2011 data" 9 : 493-518, 2014

16 Sulku, S. N., "Public and private school distinction, regional development differences, and other factors influencing the success of primary school students in Turkey" 15 : 419-431, 2015

17 Epstein, J. L., "More than minutes : Teachers’ roles in designing homework" 36 : 181-193, 2001

18 Lent, R. W., "Mathematics self-efficacy : Sources and relation to science-based career choice" 38 : 424-430, 1991

19 Silver, D., "Mastering the game of Go with deep neural networks and tree search" 529 : 484-489, 2016

20 Goeman, J, "L1 and L2 Penalized Regression Models"

21 Zhu, Y., "Homework and mathematics achievement in Hong Kong : Evidence from the TIMSS 2003" 10 : 907-925, 2012

22 Tsai, L. T., "Hierarchical effects of school classroom, and student-level factors on the science performance of eighth-grade Taiwanese students" 37 : 1166-1181, 2015

23 Matsuoka, R., "Disparities between schools in Japanese compulsory education : Analyses of a cohort using TIMSS 2007 and 2011" 8 : 77-92, 2014

24 Breiman, L., "Bagging predictors" 26 : 123-140, 1996

25 Kareshki, H., "A multilevel analysis of the role of school quality and family background on students’ mathematics achievement in the Middle East" 2 : 593-602, 2014