In this paper, we propose a Bayesian PG-INLA algorithm which is tailored to both one-dimensional and multidimensional 2-PL IRT models. The proposed PG-INLA algorithm utilizes a computationally efficient data augmentation strategy via the Pólya-Gamma variables, which can avoid low computational efficiency of traditioanl Bayesian MCMC algorithms for IRT models with a logistic link function. Meanwhile, combined with the advanced and fast INLA algorithm, the PG-INLA algorithm is both accurate and computationally efficient. We provide details on the derivation of posterior and conditional distributions of IRT models, the method of introducing the Pólya-Gamma variable into Gibbs sampling, and the implementation of the PG-INLA algorithm for both one-dimensional and multidimensional cases. Through simulation studies and an application to the data analysis of the IPIP-NEO personality inventory, we assess the performance of the PG-INLA algorithm. Extensions of the proposed PG-INLA algorithm to other IRT models are also discussed.

References

• Albert, J., & Chib, S. (1993). Bayesian analysis of binary and polychotomous response data. Journal of the American Statistical Association, 88(422), 669–679. https://doi.org/10.1080/01621459.1993.10476321
• Béguin, A., & Glas, C. A. (2001). MCMC estimation and some model-fit analysis of multidimensional IRT models. Psychometrika, 66(4), 541–561. https://doi.org/10.1007/BF02296195
• Biane, P., Pitman, J., & Yor, M. (1999). Probability laws related to the Jacobi theta and Riemann zeta functions, and Brownian excursions. Bulletin of the American Mathematical Society, 38(4), 435–465. https://doi.org/10.1090/bull/2001-38-04
• Bock, R. D., & Aitkin, M. (1981). Marginal maximum likelihood estimation of item parameters: Application of an EM algorithm. Psychometrika, 46(4), 443–459. https://doi.org/10.1007/BF02293801
• Cai, L. (2010a). High-dimensional exploratory item factor analysis by a Metropolis–Hastings Robbins–Monro algorithm. Psychometrika, 75(1), 33–57. https://doi.org/10.1007/s11336-009-9136-x
• Cai, L. (2010b). Metropolis–Hastings Robbins–Monro algorithm for confirmatory item factor analysis. Journal of Educational and Behavioral Statistics, 35(3), 307–335. https://doi.org/10.3102/1076998609353115
• Celeux, G., & Diebolt, J. (1985). The SEM algorithm: A probabilistic teacher algorithm derived from the EM algorithm for the mixture problem. Computational Statistics Quarterly, 2, 73–82.
• Chen, Y., Li, X., & Zhang, S. (2017). Structured latent factor analysis for large-scale data: Identifiability, estimability, and their implications. Journal of the American Statistical Association, 115(532), 1756–1770. https://doi.org/10.1080/01621459.2019.1635485
• Chen, Y., & Zhang, S. (2020). Estimation methods for item factor analysis: An overview. In Y. Zhao & D. G. Chen (Eds.), Modern statistical methods for health research (pp. 329–350). Springer.
• Costa, P. T., & McCrae, R. R. (2008). The revised NEO personality inventory (NEO-PI-R). In G. J. Boyle, G. Matthews & D. H. Saklofske (Eds.), The Sage handbook of personality theory and assessment: Personality measurement and testing (Vol. 2, pp. 179–198). Sage Publications, Inc.
• Dempster, A. P., Laird, N. M., & Rubin, D. B. (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society: Series B, 39(1), 1–22. https://doi.org/10.1111/j.2517-6161.1977.tb01600.x
• Digman, J. M. (1997). Higher-order factors of the big five. Journal of Personality and Social Psychology, 73(6), 1246–1256. https://doi.org/10.1037/0022-3514.73.6.1246
• Eckes, T., & Baghaei, P. (2015). Using testlet response theory to examine local dependence in C-tests. Applied Measurement in Education, 28(2), 85–98. https://doi.org/10.1080/08957347.2014.1002919
• Edwards, M. C. (2010). A Markov chain Monte Carlo approach to confirmatory item factor analysis. Psychometrika, 75(3), 474–497. https://doi.org/10.1007/s11336-010-9161-9
• Embretson, S. E., & Reise, S. P. (2000). Item response theory for psychologists. Lawrence Erlbaum Associates Publishers.
• Feinberg, R., & Rubright, J. (2016). Conducting simulation studies in psychometrics: Conducting simulation studies in psychometrics. Educational Measurement: Issues and Practice, 35(2), 36–49. https://doi.org/10.1111/emip.2016.35.issue-2
• Harwell, M. R., & Baker, F. B. (1991). The use of prior distributions in marginalized Bayesian item parameter estimation: A didactic. Applied Psychological Measurement, 15(4), 375–389. https://doi.org/10.1177/014662169101500409
• Imai, K., & Dyk, D. A. V. (2005). A Bayesian analysis of the multinomial probit model using marginal data augmentation. Journal of Econometrics, 124(2), 311–334. https://doi.org/10.1016/j.jeconom.2004.02.002
• Ip, E. H. (2002). On single versus multiple imputation for a class of stochastic algorithms estimating maximum likelihood. Computational Statistics, 17(4), 517–524. https://doi.org/10.1007/s001800200124
• Jaakkola, T. S., & Jordan, M. I. (2000). Bayesian parameter estimation via variational methods. Statistics and Computing, 10(1), 25–37. https://doi.org/10.1023/A:1008932416310
• Jiang, Z., & Templin, J. L. (2018). Gibbs samplers for logistic item response models via the Pólya gamma distribution: A computationally efficient data-augmentation strategy. Psychometrika, 84(2), 358–374. https://doi.org/10.1007/s11336-018-9641-x
• Johnson, J. A. (2014). Measuring thirty facets of the five factor model with a 120-item public domain inventory: Development of the IPIP-NEO-120. Journal of Research in Personality, 51, 78–89. https://doi.org/10.1016/j.jrp.2014.05.003
• Junker, B. W., Patz, R. J., & VanHoudnos, N. M. (2017). Markov Chain Monte Carlo for item response models. In Wim J. van der Linden (Ed.), Handbook of item response theory: Volume two: Statistical tools (pp. 271–312). Chapman and Hall/CRC.
• Lawley, D. N., & Maxwell, A. E. (1962). Factor analysis as a statistical method. Journal of the Royal Statistical Society. Series D, 12(3), 209–229.
• Liu, Y., Magnus, B., O'Connor, H., & Thissen, D. (2018). Multidimensional item response theory. In P. Irwing, T. Booth, & D. J. Hughes (Eds.), The Wiley handbook of psychometric testing (Vol. 2–2, pp. 445–493). John Wiley and Sons, Ltd.
• Lord, F. M. (1980). Applications of item response theory to practical testing problems. Routledge.
• Lord, F., Novick, M., & Birnbaum, A. (1968). Some latent trait models and their use in inferring an examinee's ability. Addison-Wesley.
• Lynch, S. M. (2007). Introduction to applied Bayesian statistics and estimation for social scientists. Springer.
• Mair, P., & Gruber, K. (2022). Bayesian explanatory additive IRT models. British Journal of Mathematical and Statistical Psychology, 75(1), 59–87. https://doi.org/10.1111/bmsp.v75.1
• Matlock, K. L. , Turner, R. C., & Gitchel, W. D. (2018). A study of reverse-worded matched item pairs using the generalized partial credit and nominal response models. Educational and Psychological Measurement, 78(1), 103–127. https://doi.org/10.1177/0013164416670211
• McDonald, R. P. (2013). Test theory: A unified treatment. Psychology Press.
• Moraga, P. (2020). Geospatial health data: Modeling and visualization with R-INLA and shiny (1st ed.). CRC Press.
• Muraki, E. (1992). A generalized partial credit model: Application of an EM algorithm. Applied Psychological Measurement, 16(2), 159–176. https://doi.org/10.1177/014662169201600206
• Murphy, J. P. (2021). Explanatory item response models for dyadic data from multiple groups. Sociological Methodology, 51(1), 112–145. https://doi.org/10.1177/0081175020967392
• Niederreiter, H. (1978). Quasi-Monte Carlo methods and pseudo-random numbers. Bulletin of the American Mathematical Society, 84(6), 957–1041. https://doi.org/10.1090/bull/1978-84-06
• Polson, N. G. , Scott, J. G., & Windle, J. (2013). Bayesian inference for logistic models using Pólya-Gamma latent variables. Journal of the American Statistical Association, 108(504), 1339–1349. https://doi.org/10.1080/01621459.2013.829001
• Reckase, M. D. (2009). Multidimensional item response theory. Handbook of Statistics, 26, 607–642. https://doi.org/10.1016/S0169-7161(06)26018-8
• Rue, H., Martino, S., & Chopin, N. (2009). Approximate Bayesian inference for latent Gaussian models by using integrated nested Laplace approximations. Journal of the Royal Statistical Society: Series B, 71(2), 319–392. https://doi.org/10.1111/j.1467-9868.2008.00700.x
• Samejima, F. (1968). Estimation of latent ability using a response pattern of graded scores. Psychometrika, 34(1), 1–97.
• Sara, M., & Andrea, R. (2020). Integrated nested Laplace approximations (INLA). https://dx.doi.org/10.1002/9781118445112.stat08212
• Song, X. Y., & Lee, S. Y. (2005). A multivariate probit latent variable model for analyzing dichotomous responses. Statistica Sinica, 15(3), 645–664.
• Thissen, D., & Wainer, H. (2001). Test scoring. Routledge.
• van der Linden, W. J., & Hambleton, R. K. (1997). Item response theory: Brief history, common models, and extensions. In Wim J. van der Linden (Ed.), Handbook of modern item response theory (pp. 1–28). Springer.
• Zeithammer, R., & Lenk, P. J. (2006). Bayesian estimation of multivariate-normal models when dimensions are absent. Quantitative Marketing and Economics, 4(3), 241–265. https://doi.org/10.1007/s11129-005-9006-5
• Zhang, S., Chen, Y., & Liu, Y. (2020). An improved stochastic EM algorithm for large-scale full-information item factor analysis. British Journal of Mathematical and Statistical Psychology, 73(1), 44–71. https://doi.org/10.1111/bmsp.v73.1

To cite this article: Xiaofan Lin & Yincai Tang (21 Jan 2025): An efficient PG-INLA algorithm for the Bayesian inference of logistic item response models, Statistical Theory and Related Fields, DOI: 10.1080/24754269.2024.2442174

To link to this article: https://doi.org/10.1080/24754269.2024.2442174