본문 바로가기
KERD
논문

분할 선형 성장모형을 사용한 불연속 성장궤적의 분석에서 도약의 추정

Estimating jumps in disjointed trajectories using piecewise linear growth model

권도희|조승빈
한국심리학회 (The Korean Psychological Association)|2023.12|한국심리학회지:일반 (Korean Journal of Psychology: General)|제42권 제4호|pp. 333-357|DOI 10.22257/kjp.2023.12.42.4.333

0

조회

0

다운로드

0

인용

0

참고문헌

키워드

잠재성장모형latent growth model분할 선형 성장모형비선형 성장불연속 성장궤적종단모형piecewise linear growth modelnon-linear growthdisjointed trajectorieslongitudinal model
주제분류심리과학

초록

분할 선형 성장모형(piecewise linear growth model)은 비선형 성장궤적을 가지는 종단자료의 분석에 유용하다. 분할 선형 성장모형에서는 변곡점을 기준으로 측정기간을 복수의 구간으로 나누고 각 구간에 개별적인 선형모형을 적용함으로써 비선형 성장궤적을 모형화할 수 있을 뿐만 아니라 성장요인에 대해 직관적이고 이론적으로 의미 있는 해석이 용이하다. 이러한 장점에 더해서, 변곡점에서 발생하는 변화로 인해 성장궤적이 연결되지 않는 불연속 성장궤적(이하 ‘도약’) 또한 모형화가 가능하다. 그러나 이러한 장점은 분할성장모형의 적용에서 자주 간과된다. 본 연구에서는 도약을 포함한 분할 선형 성장모형의 모수화 방법을 개괄하고 분할 선형 성장모형의 적용에서 자료에 실재하는 도약을 생략할 때 발생할 수 있는 모수 추정의 편향과 적합도의 변화를 시뮬레이션을 통해 확인하였다. 다양한 크기의 도약이 존재하는 불연속 성장궤적을 기반으로 자료를 생성하고 이를 Harring 등(2006)이 제안한 분할 선형 성장모형으로 분석하였다. Harring 등(2006)의 모형은 이론에 기반 하여 선험적으로 변곡점을 설정하는 대신, 자료로부터 변곡점의 위치를 추정한다. 따라서 본 연구의 결과를 통해 도약의 생략으로 인해 발생할 수 있는 변곡점 추정의 편향 또한 확인하였다. 분석 결과, 도약의 크기가 커질수록 이를 포함하지 않는 분할 선형 성장모형의 결과에서 모수 추정의 편향이 대체로 커지고 모형의 적합도가 낮아졌다. 모수 추정의 편향은 성장요인의 종류에 따라 그 양상이 달랐다. 본 연구의 결과는 분할 선형 성장모형의 적용에서 도약을 추정하거나 실증적으로 검정하는 것이 대부분의 경우 더 적절함을 시사한다. 마지막으로 본 연구의 결과를 토대로 분할 선형 성장모형의 적용을 위한 전략을 제안하였다.

Abstract

Piecewise linear growth model(PLGM) is useful to model for non-linear trajectories. In PLGM, entire assessment period is split into multiple phases at points called “knots’, and separate linear growth model is applied to each phase. Because linear growth model is used at each phase, the interpretation of growth factors is more straightforward and theoretically meaningful compared to other methods for modeling non-linear growths. In addition, radical changes at the knot can lead to disjointed trajectories (referred to as ”jump“ in the follwing) at knots, and PLGM can model the jump. However, such advantage of PLGM　is often overlooked in applications of PLGM. In this study, we reviewed parameterizations of PLGM that allow the estimation of the jump in disjointed trajectories, and examined consequences, in terms of estimation bias and model fit, of model misspecification by omitting the jump. For this purpose, we generated datasets with trajectories with various degrees of jumps and analyzed the datasets using the PLGM proposed by Harring et al. (2006), which estimates the location of the knot, instead of setting it at an a priori point. Thus, we were also able to examine the estimation of the knot locations in the presence of the model misspecification. In our results, with increasing degrees of the jump, in general, the bias of parameter estimates increased and the model fit declined. The results showed that, in most situations, it is a good idea to include the jump in the applications of PLGM, unless there is a strong theoretical background to omit the jump. We also provided practical strategies in the applications of PLGM based on our results.

참고문헌 (41)

  1. 안은미, "가정외보호 청소년의 또래관계가 학교적응 발달궤적에 미치는 영향", 청소년복지연구, 18(4), pp.191~218 (2016), 한국청소년복지학회[DOI]
  2. 조승빈, "알코올 사용 문제 발생 기제의 이해를 위한 성인진입기 종단자료의 중요성과 방법론적 고려점", 청소년학연구, 29(8), pp.75~107 (2022), 한국청소년학회[DOI]
  3. 황혜영, "분할함수 잠재성장모형을 활용한 청소년의 학업 자아개념, 사회 자아개념 및 학업 스트레스의 종단적 관계 분석", 중등교육연구, 69(4), pp.527~554 (2021), 사범대학부속중등교육연구소
  4. Jaejin Ahn, "Trajectory of problem behaviours of Korean adopted children: using piecewise hierarchical linear growth modelling", Child & Family Social Work, 22(1), pp.461~471 (2015), Wiley[DOI]
  5. P. M. Bentler, "Comparative fit indexes in structural models.", Psychological Bulletin, 107(2), pp.238~246 (1990), American Psychological Association (APA)[DOI]
  6. Andre Beauducel, "Simulation Study on Fit Indexes in CFA Based on Data With Slightly Distorted Simple Structure", Structural Equation Modeling: A Multidisciplinary Journal, 12(1), pp.41~75 (2005), Informa UK Limited[DOI]
  7. Bollen, K. A., "Latent curve models : A structural equation perspective" (2006), John Wiley & Sons
  8. Emil Coman, "Examining Differential Resilience Mechanisms by Comparing ‘Tipping Points’ of the Effects of Neighborhood Conditions on Anxiety by Race", Ethnicity, 2018, pp.6(1), 18~[DOI]
  9. Robert Cudeck, "Analysis of Nonlinear Patterns of Change with Random Coefficient Models", Annual Review of Psychology, 58(1), pp.615~637 (2007), Annual Reviews[DOI]
  10. Thierno M. O. Diallo, "Power of Latent Growth Curve Models to Detect Piecewise Linear Trajectories", Structural Equation Modeling: A Multidisciplinary Journal, 22(3), pp.449~460 (2014), Informa UK Limited[DOI]
  11. Danielle M. Dick, "Genetic influences on alcohol use across stages of development:<i>GABRA2<", i>and longitudinal trajectories of drunkenness from adolescence to young adulthood, 2013, pp.19(6), 1055~1064[DOI]
  12. Lei Duan, "Trajectories of Peer Social Influences as Long-term Predictors of Drug Use from Early Through Late Adolescence", Journal of Youth and Adolescence, 38(3), pp.454~465 (2008), Springer Science and Business Media LLC[DOI]
  13. Bruce J. Ellis, "Quality of early family relationships and the timing and tempo of puberty: Effects depend on biological sensitivity to context", Development and Psychopathology, 23(1), pp.85~99 (2011), Cambridge University Press (CUP)[DOI]
  14. David B. Flora, "Specifying Piecewise Latent Trajectory Models for Longitudinal Data", Structural Equation Modeling: A Multidisciplinary Journal, 15(3), pp.513~533 (2008), Informa UK Limited[DOI]
  15. Kevin J. Grimm, "Nonlinear Growth Curves in Developmental Research", Child Development, 82(5), pp.1357~1371 (2011), Wiley[DOI]
  16. Denis Gerstorf, "Late-life decline in well-being across adulthood in Germany, the United Kingdom, and the United States: Something is seriously wrong at the end of life.", Psychology and Aging, 25(2), pp.477~485 (2010), American Psychological Association (APA)[DOI]
  17. Jeffrey R. Harring, "Fitting Partially Nonlinear Random Coefficient Models as SEMs", Multivariate Behavioral Research, 41(4), pp.579~596 (2006), Informa UK Limited[DOI]
  18. Adele M. Hayes, "Change is not always linear: The study of nonlinear and discontinuous patterns of change in psychotherapy", Clinical Psychology Review, 27(6), pp.715~723 (2007), Elsevier BV[DOI]
  19. Li‐tze Hu, "Cutoff criteria for fit indexes in covariance structure analysis: Conventional criteria versus new alternatives", Structural Equation Modeling: A Multidisciplinary Journal, 6(1), pp.1~55 (1999), Informa UK Limited[DOI]
  20. Jan N. Hughes, "Trajectories of teacher-student warmth and conflict at the transition to middle school: Effects on academic engagement and achievement", Journal of School Psychology, 67, pp.148~162 (2018), Elsevier BV[DOI]
  21. Shanna Smith Jaggars, "Examining the Earnings Trajectories of Community College Students Using a Piecewise Growth Curve Modeling Approach", Journal of Research on Educational Effectiveness, 9(3), pp.445~471 (2016), Informa UK Limited[DOI]
  22. Jöreskog, K. G., "LISREL 7:A guide to the program and applications" (1989), SPSS
  23. Kohli, N., "Modeling growth in latent variables using a piecewise function", Multivariate behavioral research, 48(3), pp.370~397 (2013)
  24. Kohli, N., "Longitudinal mathematics development of students with learning disabilities and students without disabilities: A comparison of linear, quadratic, and piecewise linear mixed effects models", Journal of school psychology, 53(2), pp.105~120 (2015)[DOI]
  25. Nidhi Kohli, "Fitting a linear–linear piecewise growth mixture model with unknown knots: A comparison of two common approaches to inference.", Psychological Methods, 20(2), pp.259~275 (2015), American Psychological Association (APA)[DOI]
  26. Oi-Man Kwok, "Using Modification Indexes to Detect Turning Points in Longitudinal Data: A Monte Carlo Study", Structural Equation Modeling: A Multidisciplinary Journal, 17(2), pp.216~240 (2010), Informa UK Limited[DOI]
  27. Fuzhong Li, "Piecewise Growth Mixture Modeling of Adolescent Alcohol Use Data", Structural Equation Modeling: A Multidisciplinary Journal, 8(2), pp.175~204 (2001), Informa UK Limited[DOI]
  28. Guo-Xiang Liu, "Jump-detection and curve estimation methods for discontinuous regression functions based on the piecewise B-spline function", Communications in Statistics - Theory and Methods, 47(23), pp.5729~5749 (2017), Informa UK Limited[DOI]
  29. Liu, J., "Estimating knots and their association in parallel bilinear spline growth curve models in the framework of individual measurement occasions" (2021), Psychological Methods. Advance online publication
  30. Eric F. Lock, "Detecting Multiple Random Changepoints in Bayesian Piecewise Growth Mixture Models", Psychometrika, 83(3), pp.733~750 (2017), Springer Science and Business Media LLC[DOI]
  31. David Markland, "The golden rule is that there are no golden rules: A commentary on Paul Barrett’s recommendations for reporting model fit in structural equation modelling", Personality and Individual Differences, 42(5), pp.851~858 (2007), Elsevier BV[DOI]
  32. Herbert W. Marsh, "In Search of Golden Rules: Comment on Hypothesis-Testing Approaches to Setting Cutoff Values for Fit Indexes and Dangers in Overgeneralizing Hu and Bentler's (1999) Findings", Structural Equation Modeling: A Multidisciplinary Journal, 11(3), pp.320~341 (2004), Informa UK Limited[DOI]
  33. McArdle, J. J., "Longitudinal data analysis using structural equation models" (2014), American Psychological Association
  34. William Meredith, "Latent curve analysis", Psychometrika, 55(1), pp.107~122 (1990), Springer Science and Business Media LLC[DOI]
  35. (2017)[URL]
  36. Ling Ning, "Specifying Turning Point in Piecewise Growth Curve Models: Challenges and Solutions", Frontiers in Applied Mathematics and Statistics, 3 (2017), Frontiers Media SA[DOI]
  37. Robert E. Ployhart, "Longitudinal Research: The Theory, Design, and Analysis of Change", Journal of Management, 36(1), pp.94~120 (2009), SAGE Publications[DOI]
  38. Stephen W. Raudenbush, "Effects of study duration, frequency of observation, and sample size on power in studies of group differences in polynomial change.", Psychological Methods, 6(4), pp.387~401 (2001), American Psychological Association (APA)[DOI]
  39. James H. Steiger, "Structural Model Evaluation and Modification: An Interval Estimation Approach", Multivariate Behavioral Research, 25(2), pp.173~180 (1990), Informa UK Limited[DOI]
  40. Wei Wu, "Proportionality Assumption in Latent Basis Curve Models: A Cautionary Note", Structural Equation Modeling: A Multidisciplinary Journal, 23(1), pp.140~154 (2015), Informa UK Limited[DOI]
  41. Ke-Hai Yuan, "Fit Indices Versus Test Statistics", Multivariate Behavioral Research, 40(1), pp.115~148 (2005), Informa UK Limited[DOI]

관련 논문AI추천

분위 로지스틱 성장 곡선 추정 절차의 비교배소영, 장승민한국심리학회 · 한국심리학회지:일반2014 · 제33권 제4호잠재성장모형의 사용을 위한 표본크기 결정김수영, 석혜은한국심리학회 · 한국심리학회지:일반2015 · 제34권 제2호모의실험을 이용한 3-수준 다층성장모형과 3-수준 다중소속다층성장모형의 비교전현정, 정혜원교육연구소 · 교육연구논총2015 · 제36권 제3호다지표 잠재성장모형에서 요인동일성과 요인척도 설정의 문제: 모형 적합도와 모수 추정값에 미치는 영향박송이, 장승민한국심리학회 · 한국심리학회지:일반2018 · 제37권 제1호종단 문항반응이론 혼합모형의 적용을 통한 청소년 자아존중감 변화 유형 탐색박찬호, 서공주한국청소년정책연구원 · 한국청소년연구2020 · 제31권 제3호분할함수 성장모형을 활용한 청소년 불안의 변화 추정과 생태학적 영향 요인의 검증김진호, 홍세희한국교육방법학회 · 교육방법연구2012 · 제24권 제2호

이 간행물의 다른 논문 (2건)

국가 차원의 근거-기반 심리서비스 제도의 필요성박수현, 최기홍, 홍은택pp. 287-307효과적인 심리서비스 제공을 위한 교육 및 수련제도: 5개 법안 비교와 구체적인 제안정경미, 민병배, 이승아pp. 309-331
원문 보기