Bayesian Analysis of KBSID-III Adaptive Behavior Data Using a Zero-Inflated Ordered Probit Model

& (2017). Bayesian Analysis of KBSID-III Adaptive Behavior Data Using a Zero-Inflated Ordered Probit Model. Korean Journal of Psychology: General, 36(2), 215-239, https://doi.org/10.22257/kjp.2017.06.36.2.215

copy

Abstract

Excessive zeros are frequently observed in response variables when behavioral characteristics in the development of children are assessed. For example, in the Korean Bayley Scales of Infant and Toddler Development-Third Edition (KBSID-III)-adaptive behavior test, zero scale was excessively recorded more than other scales, such as 1, 2, or 3. A regular ordered probit (OP) model can be used when more than two outcomes appear in ordinal dependent variables. However, it is not appropriate for an OP model to be used with zero-inflated ordinal data. An OP model also has a limitation when there are two semantically distinctive groups, genuine non-participant and potential participant groups. We applied a two-step zero-inflated ordered probit (ZIOP) model in a Bayesian framework to the KBSID-III-adaptive behavior data. In the first step, the adaptive group (potential adaptive group was included) was separated from the genuine non-adaptive group using a probit model. In the second step, an OP model was applied to the adaptive group. A Bayesian estimation procedure to the ZIOP model was carried out with a Gibbs sampling algorithm using the open-source software R. The utility of the ZIOP model with zero-inflated ordered categorical variables was verified by checking the maginal effect of predictors on the change in the probability of a certain category.

keywords: 영과잉 순서형 프로빗 모형, 베이지안 추론, MCMC, 깁스샘플링, 베일리 검사, Zero-inflated, Ordered probit model, Bayesian inference, MCMC, Gibbs sampling, Bayley-III

Reference

김준엽, 신혜숙 (2009). 다층 영과잉 포아송 모형의 적용: 청소년 비행의 발생여부 및 발생빈도 분석, 교육평가연구, 22(2), 471-493.

김호정 (2015). 베일리-III 검사를 사용한 미국과한국 영유아 적응행동 비교 연구, 이화여자대학교 박사학위논문.

유정희 (2008). 생활자립훈련중심 전환교육활동이 정신지체학생의 적응행동기술에 미치는효과. 대구대학교 대학원 박사학위 논문.

이복희 (2001). 신체활동중심의 치료레크리에이션 활동이 정신지체아동의 적응행동 및 정서적 행동에 미치는 효과. 한국특수체육학회지, 9(2), 73-87.

이준석, 유재연, 신현기, 전병운, & 고등영. (2007). 초등학생용 적응행동검사의 실제적 기술 영역 문항 타당성 검토. 특수교육학연구, 41, 37-53.

홍성두, 여승수, 김남순, 박상희, 이선재 (2009). 지적장애 연구를 위한 영과잉 모형의 활용방안 탐색. 지적장애연구, 11(4), 179-197.

Akaike, H. (1973). Maximum likelihood identification of Gaussian autoregressive moving average models. Biometrika, 255-265.

Atkins, D. C., Baldwin, S. A., Zheng, C., Gallop, R. J., & Neighbors, C. (2013). A tutorial on count regression and zero-altered count models for longitudinal substance use data. Psychology of Addictive Behaviors, 27(1), 166-177.

Bayley, N. (2006). Bayley scales of infant and toddler development-third edition: Technical manual. San Antonio, TX: Harcourt Assessment.

10.

Bollen, K. A. (1989). Structural equation models with latent variables. New York: Wiley.

11.

Ghosh, S. K., Mukhopadhyay, P., & Lu, J. C. J. (2006). Bayesian analysis of zero-inflated regression models. Journal of Statistical Planning and Inference, 136(4), 1360-1375.

12.

Gurmu, S., & Dagne, G. A. (2012). Bayesian approach to zero-inflated bivariate ordered probit regression model, with an application to tobacco use. Journal of Probability and Statistics, 2012, 1-26.

13.

Gurmu, S., & Trivedi, P. K. (1996). Excess zeros in count models for recreational trips. Journal of Business & Economic Statistics, 14(4), 469-477.

14.

Geman, S., & Geman, D. (1984). Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 6(6), 721-741.

15.

Harris, M. N., & Zhao, X. (2007). A zero-inflated ordered probit model, with an application to modelling tobacco consumption. Journal of Econometrics, 141(2), 1073-1099.

16.

Harrison, P., &Oakland, T. (2003). Adaptive behavior assessment system (ABAS-II). San Antonio, TX: The Psychological Corporation.

17.

Lambert, D. (1992). Zero-inflated Poisson regression with an application to defects in manufacturing. Technometrics, 34, 1-14.

18.

McCoach, D. B., Gable, R. K., & Madura, J. P. (2013). Instrument development in the affective domain. New York, NY: Springer.

19.

Metropolis, N., Rosenbluth, A. W., Rosenbluth, M. N., Teller, A. H., & Teller, E. (1953). Equation of state calculations by fast computing machines. The Journal of Chemical Physics, 21(6), 1087-1092.

20.

Musio, M., Sauleau, E. A., & Buemi, A. (2010). Bayesian semi-parametric ZIP models with space–time interactions: an application to cancer registry data. Mathematical Medicine and Biology, 27(2), 181-194.

21.

Muthén, L. K., & Muthén, B. O. (1998-2016). Mplus User’s Guide 7.0. Los Angeles, CA;Muthén & Muthén.

22.

Neelon, B. H., O’Malley, A. J., & Normand, S.-L. T. (2010). A Bayesian model for repeated measures zero-inflated count data with application to outpatient psychiatric service use. Statistical Modelling, 10(4), 421-439.

23.

Nelder, J. A., & Wedderburn, R. W. M. (1972). Generalized linear models, Journal of the Royal Statistical Society A, 135, 370-384.

24.

Nunnally, J. C., & Bernstein, I. H. (1994). Psychometric theory (3rd ed.). New York:McGraw-Hill.

25.

R Core Team (2015). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL https://www.R-project.org/.

26.

Schwarz, G. (1978). Estimating the dimension of a model. The annals of statistics, 6(2), 461-464.

27.

Rizzo, M. L. (2007). Statistical computing with R. CRC Press.

28.

Singh, S. (1963). A note on inflated Poisson distribution. Journal of the Indian Statistical Association, 1, 140-144.

29.

Spiegelhalter, D. J., Best, N. G., Carlin, B. P., &Van Der Linde, A. (2002). Bayesian measures of model complexity and fit. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 64(4), 583-639.

30.

Stegmueller, D. (2013). How many countries for multilevel modeling? A comparison of frequentist and Bayesian approaches. American Journal of Political Science, 57(3), 748-761.

31.

Wang, P. (2003). A bivariate zero-inflated negative binomial regression model for count data with excess zeros. Economics Letters, 78(3), 373-378.

32.

Wirth, R. J., & Edwards, M. C. (2007). Item factor analysis: Current approaches and future directions. Psychological Methods, 12(1), 58-79.

33.

Wright, A. G., Pincus, A. L., & Lenzenweger, M. F. (2012). An empirical examination of distributional assumptions underlying the relationship between personality disorder symptoms and personality traits. Journal of Abnormal Psychology, 121(3), 699-706.

바로가기메뉴

Article Contents

Vol.36 No.2

Bayesian Analysis of KBSID-III Adaptive Behavior Data Using a Zero-Inflated Ordered Probit Model

Abstract

Reference

Korean Journal of Psychology: General