Using Response Times as Collateral Information About Latent Traits in Psychological Tests
Abstract
Abstract. In psychological tests, the time needed to respond to the items provides collateral information about the latent traits of the test takers. This, however, requires a measurement model that incorporates the response times in addition to the responses. Such a measurement model is usually based on a full specification of the response time distribution. In the present article, we suggest a novel modeling approach that requires fewer assumptions. In the approach, the responses are modeled with a unidimensional two-parameter logistic model. The single response times are summed to the scale-specific total testing time which is then related to the latent trait of the two-parameter logistic model via a smooth adaptive Gaussian mixture (SAGM) model. The approach can be justified against the background of the bivariate generalized linear item response theory modeling framework (Molenaar, Tuerlinckx, & van der Maas, 2015a). Its utility is investigated in two simulation studies and an empirical example.
References
1999). The goodness of fit of latent trait models in attitude measurement. Sociological Methods & Research, 27, 524–546. https://doi.org/10.1177/0049124199027004003
(2016). A test for conditional independence between response time and accuracy. British Journal of Mathematical and Statistical Psychology, 69, 62–79. https://doi.org/10.1111/bmsp.12059
(2018). Improving precision of ability estimation: Getting more from response times. British Journal of Mathematical and Statistical Psychology, 71, 13–38. https://doi.org/10.1111/bmsp.12104
(2019). Item response and response time model for personality assessment via linear ballistic accumulation. Japanese Journal of Statistics and Data Science, 2, 263–297. https://doi.org/10.1007/s42081-019-00040-4
(2014). Incorporating response time to analyze test data with mixture structural equation modeling. Psychological Testing, 61, 463–488.
(2010). The impact of fallible item parameter estimates on latent trait recovery. Psychometrika, 75, 280–291. https://doi.org/10.1007/s11336-009-9144-x
(1972). Complete automation of the MMPI and a study of its response latencies. Journal of Consulting and Clinical Psychology, 39, 381–387. https://doi.org/10.1037/h0033855
(2012). Utilizing response time distributions for item selection in CAT. Journal of Educational and Behavioral Statistics, 37, 655–670. https://doi.org/10.3102/1076998611422912
(2006). Person-item distance and response time: An empirical study in personality measurement. Psicológica, 27, 137–148.
(2016). An extended multidimensional IRT formulation for the linear item factor analysis model. Methodology, 12, 1–10. https://doi.org/10.1027/1614-2241/a000098
(2007a). An item response theory model for incorporating response time data in binary personality items. Applied Psychological Measurement, 31, 525–543. https://doi.org/10.1177/0146621606295197
(2007b). A measurement model for Likert responses that incorporates response time. Multivariate Behavioral Research, 42, 675–706. https://doi.org/10.1080/00273170701710247
(2017). GESIS Panel – Standard Edition. (ZA5665 Data file Version 22.0.0 ed.). GESIS Data Archive. https://doi.org/10.4232/1.12903
. (2006). The international personality item pool and the future of public-domain personality measures. Journal of Research in Personality, 40, 84–96. https://doi.org/10.1016/j.jrp.2005.08.007
(2009). The elements of statistical learning. Berlin, Germany: Springer.
(2017). Comparison of uni- and multidimensional models applied in testlet-based tests. Methodology, 13, 135–143. https://doi.org/10.1027/1614-2241/a000137
(2018). Comparing the performance of agree/disagree and item-specific questions across PCs and smartphones. Methodology, 14, 109–118. https://doi.org/10.1027/1614-2241/a000151
(2009). A Box-Cox normal model for response times. British Journal of Mathematical and Statistical Psychology, 62, 621–640. https://doi.org/10.1348/000711008X374126
(1973). Response processes and relative location of subject and item. Educational and Psychological Measurement, 33, 545–563. https://doi.org/10.1177/001316447303300302
(2014). Semi-parametric proportional hazards models with crossed random effects for psychometric response times. British Journal of Mathematical and Statistical Psychology, 67, 304–327. https://doi.org/10.1111/bmsp.12020
(2017). A semi-parametric within subject mixture approach to the analyses of responses and response times. British Journal of Mathematical and Statistical Psychology, 71, 205–228. https://doi.org/10.1111/bmsp.12117
(2015a). A bivariate generalized linear item response theory modeling framework to the analysis of responses and response times. Multivariate Behavioral Research, 50, 56–74. https://doi.org/10.1080/00273171.2014.962684
(2015b). A generalized linear factor model approach to the hierarchical framework for responses and response times. British Journal of Mathematical and Statistical Psychology, 68, 197–219. https://doi.org/10.1111/bmsp.12042
(2010). Approximation of conditional densities by smooth mixtures of regressions. The Annals of Statistics, 38, 1733–1766. https://doi.org/10.1214/09-AOS765
(2003). Further investigation of the performance of S–χ2: An item fit index for use with dichotomous item response theory models. Applied Psychological Measurement, 27, 289–298. https://doi.org/10.1177/0146621603027004004
(2013a). Modeling responses and response times in personality tests with rating scales. Psychological Test and Assessment Modeling, 55, 361–382.
(2013b). A note on the hierarchical model for responses and response times in tests of van der Linden (2007). Psychometrika, 78, 538–544. https://doi.org/10.1007/s11336-013-9324-6
(2012). A flexible latent trait model for response times in tests. Psychometrika, 77, 31–47. https://doi.org/10.1007/s11336-011-9231-7
(2018). Modeling responses and response times in rating scales with the linear ballistic accumulator. Methodology, 14, 119–132. https://doi.org/10.1027/1614-2241/a000152
(2012). A latent trait model for response times on tests employing the proportional hazards model. British Journal of Mathematical and Statistical Psychology, 65, 334–349. https://doi.org/10.1111/j.2044-8317.2011.02032.x
(2005). Are unshifted distributional models appropriate for response time? Psychometrika, 70, 377–381. https://doi.org/10.1007/s11336-005-1297-7
(1998). Analyzing data from experimental studies: A latent variable structural equation modeling approach. Journal of Counseling Psychology, 45, 18–29. https://doi.org/10.1037/0022-0167.45.1.18
(2016).
(Diffusion-based item response theory modeling . In W. van der LindenR. HambletonEds., Handbook of modern item response theory (pp. 283–301). London, UK: Chapman and Hall/CRC Press. https://doi.org/10.1201/97813153745122007). A hierarchical framework for modeling speed and accuracy on test items. Psychometrika, 72, 287–308. https://doi.org/10.1007/s11336-006-1478-z
(2008). Using response times for item selection in adaptive tests. Journal of Educational and Behavioral Statistics, 31, 5–20. https://doi.org/10.3102/1076998607302626
(2009a). A bivariate lognormal response-time model for the detection of collusion between test takers. Journal of Educational and Behavioral Statistics, 34, 378–394. https://doi.org/10.3102/1076998609332107
(2009b). Conceptual issues in response-time modeling. Journal of Educational Measurement, 46, 247–272. https://doi.org/10.1111/j.1745-3984.2009.00080.x
(2010). IRT parameter estimation with response times as collateral information. Applied Psychological Measurement, 34, 327–347. https://doi.org/10.1177/0146621609349800
(2005). A psychometric analysis of chess expertise. American Journal of Psychology, 118, 29–60. https://doi.org/10.2307/30039042
(2009). Regression density estimation using smooth adaptive Gaussian mixtures. Journal of Econometrics, 153, 155–173. https://doi.org/10.1016/j.jeconom.2009.05.004
(2013). The linear transformation model with frailties for the analysis of item response times. British Journal of Mathematical and Statistical Psychology, 66, 144–168. https://doi.org/10.1111/j.2044-8317.2012.02045.x
(2013). A semiparametric model for jointly analyzing response times and accuracy in computerized testing. Journal of Educational and Behavioral Statistics, 38, 381–417. https://doi.org/10.3102/1076998612461831
(2015). A mixture hierarchical model for response times and response accuracy. British Journal of Mathematical and Statistical Psychology, 68, 456–477. https://doi.org/10.1111/bmsp.12054
(1982). Maximum likelihood estimation of misspecified models. Econometrica, 50, 1–25. https://doi.org/10.2307/1912526
(