×

Copula functions for residual dependency. (English) Zbl 1286.62101

Summary: Most item response theory models are not robust to violations of conditional independence. However, several modeling approaches (e.g., conditioning on other responses, additional random effects) exist that try to incorporate local item dependencies, but they have some drawbacks such as the nonreproducibility of marginal probabilities and resulting interpretation problems. In this paper, a new class of models making use of copulas to deal with local item dependencies is introduced. These models belong to the bigger class of marginal models in which margins and association structure are modeled separately. It is shown how this approach overcomes some of the problems associated with other local item dependency models.

MSC:

62P15 Applications of statistics to psychology
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Akaike, H. (1973). Information theory and an extension of the maximum likelihood principle. In B.N. Petrov & F. Csáki (Eds.), 2nd international symposium on information theory (pp. 267–281). Armenia, USSR: Tsahkadsov. · Zbl 0283.62006
[2] Ashford, J.R., & Sowden, R.R. (1970). Multivariate probit analysis. Biometrics, 26, 535–546. · doi:10.2307/2529107
[3] Bahadur, R. (1961). A representation of the joint distribution of responses to n dichotomous items. In H. Solomon (Ed.), Studies in item analysis and prediction (pp. 158–168). Palo Alto, CA: Standford University Press. · Zbl 0103.36701
[4] Bell, R.C., Pattison, P.E., & Withers, G.P. (1988). Conditional independence in a clustered item test. Applied Psychological Measurement, 12, 15–16. · doi:10.1177/014662168801200103
[5] Bradlow, E.T., Wainer, H., & Wang, X. (1999). A Bayesian random effects model for testlets. Psychometrika, 64, 153–168. · Zbl 1365.62451 · doi:10.1007/BF02294533
[6] Chen, W., & Thissen, D. (1997). Local dependence indexes for item pairs using item response theory. Journal of Educational and Behavioral Statistics, 22, 265–289.
[7] Clayton, D.G. (1978). A model for association in bivariate life tables and its application in epidemiological studies of familial tendency in chronic disease incidence. Biometrika, 65, 141–151. · Zbl 0394.92021 · doi:10.1093/biomet/65.1.141
[8] Cook, R.D., & Johnson, M.E. (1981). A family of distributions to modeling non-elliptically symmetric multivariate data. Journal of the Royal Statistical Society, Series B, 43, 210–218. · Zbl 0471.62046
[9] Cox, D.R. (1972). The analysis of multivariate binary data. Applied Statistics, 21, 113–120. · doi:10.2307/2346482
[10] De Boeck, P., & Wilson, M. (2004). Explanatory item response models: A generalized linear and nonlinear approach. New York: Springer. · Zbl 1098.91002
[11] Ferrara, S., Huynh, H., & Michaels, H. (1999). Contextual explanations of local dependence in item clusters in a large-scale hands-on science performance assessment. Journal of Educational Measurement, 36, 119–140. · doi:10.1111/j.1745-3984.1999.tb00550.x
[12] Fitzmaurice, G.M., Laird, N.M., & Rotnitzky, A.G. (1993). Regression models for discrete longitudinal responses. Statistical Science, 8, 284–309. · Zbl 0955.62614 · doi:10.1214/ss/1177010899
[13] Frank, M.J. (1979). On the simultaneous associativity of F(x,y) and x+y-F(x,y). Aequationes Mathematica, 19, 194–226. · Zbl 0444.39003 · doi:10.1007/BF02189866
[14] Fréchet, M. (1951). Sur les tableaux de corrélation dont les marges sont données. Annales de l’Université Lyon, Série 3, 14, 53–57.
[15] Frees, A.W., & Valdez, E.A. (1998). Understanding relationships using copulas. Actuarial Research Clearing House, 1, 5–15. · Zbl 1081.62564
[16] Genest, C., & MacKay, J. (1986). Copules archimédiennes et familles de lois bi-dimensionelles dont les marges sont donées. Canadian Journal of Statistics, 14, 145–159. · Zbl 0605.62049 · doi:10.2307/3314660
[17] Hoeffding, W. (1940). Masstabinvariante Korrelations-Theorie. Schriften des Matematischen Instituts und des Instituts für angewandte Mathematik der Universität Berlin (5:3, pp. 179–223). [Reprinted as Scale-invariant correlation theory in the Collected Works of Wassily Hoeffding, N.I. Fischer, & P.K. Sen (Eds.), New York: Springer].
[18] Holland, P.W. (1990). The Dutch identity: A new tool for the study of item response models. Psychometrika, 55, 5–18. · Zbl 0725.62097 · doi:10.1007/BF02294739
[19] Holland, P.W., & Rosenbaum, P.R. (1986). Conditional association and unidimensionality in monotone latent variable models. Annals of Statistics, 14, 1523–1543. · Zbl 0625.62102 · doi:10.1214/aos/1176350174
[20] Hoskens, M., & De Boeck, P. (1997). A parametric model for local item dependencies among test items. Psychological Methods, 2, 261–277. · doi:10.1037/1082-989X.2.3.261
[21] Ip, E. (2000). Adjusting for information inflation due to local dependence in moderately large item clusters. Psychometrika, 65, 73–81. · Zbl 1291.62217 · doi:10.1007/BF02294187
[22] Ip, E. (2001). Testing for local dependence in dichotomous and polutomous item response models. Psychometrika, 66, 109–132. · Zbl 1293.62246 · doi:10.1007/BF02295736
[23] Ip, E. (2002). Locally dependent latent trait model and the Dutch identity revisited. Psychometrika, 67, 367–386. · Zbl 1297.62231 · doi:10.1007/BF02294990
[24] Ip, E., Wang, Y.J., De Boeck, P., & Meulders, M. (2004). Locally dependent latent trait models for polytomous responses. Psychometrika, 69, 191–216. · Zbl 1306.62438 · doi:10.1007/BF02295940
[25] Joe, H. (1993). Parametric families of multivariate distributions with given margins. Journal of Multivariate Analysis, 46, 262–282. · Zbl 0778.62045 · doi:10.1006/jmva.1993.1061
[26] Joe, H. (1997). Multivariate models and dependence concepts. London: Chapman & Hall. · Zbl 0990.62517
[27] Junker, B.W. (1991). Essential independence and likelihood-based ability estimation for polytomous items. Psychometrika, 56, 255–278. · Zbl 0761.62162 · doi:10.1007/BF02294462
[28] Kotz, S., Balakrishnan, N., & Johnson, N. (2000). Continuous multivariate distributions (Vol. 1). New York: Wiley. · Zbl 0946.62001
[29] Liang, K.-Y., Zeger, S.L., & Qaqish, B. (1992). Multivariate regression analyses for categorical data. Journal of the Royal Statistical Society, Series B, 54, 3–10. · Zbl 0775.62172
[30] Mantel, N., & Haenszel, W. (1959). Statistical aspects of the analysis of data from retrospective studies of disease. Journal of National Cancer Institute, 22, 719–748.
[31] Masters, G.N. (1988). Item discrimination: When more is worse. Journal of Educational Measurement, 25, 15–19. · doi:10.1111/j.1745-3984.1988.tb00288.x
[32] McCullagh, P. (1989). Models for discrete multivariate responses. Bulletin of the International Statistics Institute, 53, 407–418.
[33] Meester, S.G. (1991). Methods for clustered categorical data. Unpublished doctoral dissertation. University of Waterloo, Canada.
[34] Molenberghs, G., & Verbeke, G. (2005). Models for discrete longitudinal data. New York: Springer. · Zbl 1093.62002
[35] Mood, A.M., Graybill, F.A., & Boes, D.C. (1974). Introduction to the theory of statistics. New York: McGraw-Hill. · Zbl 0277.62002
[36] Nelsen, R.B. (1999). An introduction to copulas. New York: Springer. · Zbl 0909.62052
[37] Rasch, G. (1960). Probabilistic models for some intelligence and achievement tests. Copenhagen: Danish Institute for Educational Research.
[38] Rosenbaum, P.R. (1984). Testing the conditional independence and monotonicity assumptions of item response theory. Psychometrika, 49, 425–435. · Zbl 0569.62097 · doi:10.1007/BF02306030
[39] Samejima, F. (1969). Estimation of latent ability using a response pattern of graded scores. Psychometrika Monograph Supplement, 7.
[40] Schwarz, G. (1978). Estimating the dimension of a model. Annals of Statistics, 6, 461–464. · Zbl 0379.62005 · doi:10.1214/aos/1176344136
[41] Scott, S.L., & Ip, E. (2002). Empirical Bayes and item clustering effects in a latent variable hierarchical model: A case study from the national assessment of educational progress. Journal of the American Statistical Association, 97, 409–419. · Zbl 1073.62512 · doi:10.1198/016214502760046961
[42] Self, G.H., & Liang, K.-Y. (1987). Asymptotic properties of maximum likelihood estimators and likelihood ratio tests under nonstandard conditions. Journal of the American Statistical Association, 82, 605–610. · Zbl 0639.62020 · doi:10.2307/2289471
[43] Sireci, S.G., Thissen, D., & Wainer, H. (1991). On the reliability of testlet-based tests. Journal of Educational Measurement, 28, 237–247. · doi:10.1111/j.1745-3984.1991.tb00356.x
[44] Sklar, A. (1959). Fonctions de répartition à n dimension et leurs marges. Publications Statistiques Université de Paris, 8, 229–231. · Zbl 0100.14202
[45] Tate, R. (2003). A comparison of selected empirical methods for assessing the structure of responses to test items. Applied Psychological Measurement, 27, 159–203. · doi:10.1177/0146621603027003001
[46] Tuerlinckx, F., & De Boeck, P. (2001a). The effect of ignoring item interactions on the estimated discrimination parameters in item response theory. Psychological Methods, 6, 181–195. · doi:10.1037/1082-989X.6.2.181
[47] Tuerlinckx, F., & De Boeck, P. (2001b). Non-modeled item interactions lead to distorted discrimination parameters: A case study. Methods of Psychological Research, 6. [Retrieved May 20, 2005 from http://www.mpr-online.de/issue14/art3/Tuerlinckx.pdf ].
[48] Tuerlinckx, F., & De Boeck, P. (2004). Models for residual dependencies. In P. De Boeck & M. Wilson (Eds.), Explanatory item response models: A generalized linear and nonlinear approach (pp. 289–316). New York: Springer.
[49] Vansteelandt, K. (2000). Formal models for contextualized personality psychology. Unpublished doctoral dissertation. K.U. Leuven, Belgium.
[50] Verhelst, N.D., & Glas, C.A.W. (1993). A dynamic generalization of the Rasch model. Psychometrika, 58, 395–415. · Zbl 0797.62101 · doi:10.1007/BF02294648
[51] Yen, W.M. (1984). Effects of local item dependence on the fit and equating performance of the three-parameter logistic model. Applied Psychological Measurement, 8, 125–145. · doi:10.1177/014662168400800201
[52] Yen, W.M. (1993). Scaling performance assessments: Strategies for managing local item dependence. Journal of Educational Measurement, 30, 187–213. · doi:10.1111/j.1745-3984.1993.tb00423.x
[53] Zhao, L.P., & Prentice, R.L. (1990). Correlated binary regression using a generalized quadratic model. Biometrics, 77, 642–648. · doi:10.1093/biomet/77.3.642
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.