THE DEVELOPMENT OF A ZERO-INFLATED RASCH MODEL
4
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
The purpose of this study was to develop a zero-in°ated Rasch (ZI-Rasch) model, a combination of the Rasch model and the ZIP model. The ZI-Rasch model was considered in this study as an appropriate alternative to the Rasch model for zero-in°ated data. To investigate the relative appropriateness of the ZI-Rasch model, several analyses were conducted using PROC NLMIXED procedures in SAS under various simulation conditions. Sets of criteria for model evaluations (-2LL,AIC, AICC, and BIC) and parameter estimations (RMSE, and r) from the ZI-Rasch model were compared with those from the Rasch model. In the data-model ¯t indices, regardless of the simulation conditions, the ZI-Rasch model produced better ¯t statistics than did the Rasch model, even when the response data were generated from the Rasch model. In terms of item parameter ¸ estimations, the ZI-Rasch model produced estimates similar to those of the Rasch model.
Abstract
The purpose of this study was to develop a zero-in°ated Rasch (ZI-Rasch) model, a combination of the Rasch model and the ZIP model. The ZI-Rasch model was considered in this study as an appropriate alternative to the Rasch model for zero-in°ated data. To investigate the relative appropriateness of the ZI-Rasch model, several analyses were conducted using PROC NLMIXED procedures in SAS under various simulation conditions. Sets of criteria for model evaluations (-2LL,AIC, AICC, and BIC) and parameter estimations (RMSE, and r) from the ZI-Rasch model were compared with those from the Rasch model. In the data-model ¯t indices, regardless of the simulation conditions, the ZI-Rasch model produced better ¯t statistics than did the Rasch model, even when the response data were generated from the Rasch model. In terms of item parameter ¸ estimations, the ZI-Rasch model produced estimates similar to those of the Rasch model.
참고문헌 (16)
- "American Invitational Mathematics Examination: In Wikipedia, The Free Encyclope-dia" (2011)[URL]
- "Mathematical Olympiad Challenges" (2010)[URL]
- D. Andrich, "Rasch models for measuremen" (1988), SAGE
- D. Fletcher, "Modelling skewed data with many zeros:A simple approach combining ordinary and logistic regression", Environ. Ecol. Stat, 12, pp.45~54 (2005)
- User's manual for WinGen: Windows software that gen-erates IRT model parameters and item responses, "K.T. Han", Center for Educational Assessment, 516~524, pp.Center for Educational Assessment Research Report 642 (2007)
- M.S. Johnson, "Marginal maximum likelihood estimation of item response models in R", J. stat. soft, 20, pp.1~25 (2007)
- D. Lambert, "Zero Inflated Poisson regression with an application to defects in manu-facturing", Technometrics, 34, pp.1~14 (1992)
- J.D. Lewsey, "The utility of the zero-inflated Poisson and zero-inflated negative binomial models: a case study of cross-sectional and longitudinal DMF data examining the effect of socioeconomic status", Community. Dent. Oral, 32, pp.183~189 (2004)
- W. Mansell, "Top private school dumps too easy GCSEs" (2009), The GuardianE
- T.G. Martin, "Zero tolerance ecology improving ecological inference by modelling the source of zero observations", Ecol. Lett, 8, pp.1235~1246 (2005)
- H. Ogasawara, "Rasch's multiplicative Poisson model with covariates", Psychometrika, 61, pp.73~92 (1996)
- G. Rasch, "Probabilistic models for some intelligence and attainment tests" (1960), Denmark Paedogogische Institut
- M. Ridout, "Models for count data with many zeros", International Biometric Conference (1998)
- SAS Institute, "SAS", STAT user'guide, 2000
- A.H. Welsh, "Modeling the abundance of rare species: Statistical models for counts with extra zeros", J. Ecol. Mode, pp.297~308 (1996)
- S. Yang, "A comparison of unidimensional and multidimensional Rasch models using parameter estimates and fit indices when assumption of unidimensionality is violated", 박사, pp.2007