In this paper, we propose a two-parameter normal ogive model with ability-based guessing (2PNO-AG), which extends the one-parameter logistic AG (1PL-AG) model by allowing item discrimination parameters to vary across items. To facilitate parameter estimation, we develop a stochastic expectation-maximization (StEM) algorithm tailored to the 2PNO-AG structure. The performance of the proposed model and estimation algorithm is evaluated through both simulation studies and empirical data analysis. The simulation results demonstrate that (a) the StEM algorithm yields accurate and stable parameter estimates under a range of initial values and prior specifications, and (b) the 2PNO-AG model offers greater robustness and flexibility compared to the 1PL-AG and three-parameter normal ogive models. Furthermore, an empirical analysis using data from 664 German fourth-grade students, obtained from the item response warehouse, confirms the superiority of the 2PNO-AG model, showing a significantly better model fit than competing alternatives.
AlbertJ. H. (1992). Bayesian estimation of normal ogive item response curves using Gibbs sampling. Journal of Educational Statistics, 17(3), 251–269.
2.
BakerF. B. (1985). The basics of item response theory. Heinemann.
3.
BéguinA. A.GlasC. A. (2001). MCMC estimation and some model-fit analysis of multidimensional IRT models. Psychometrika, 66(4), 541–561.
4.
BirnbaumA. (1968). Some latent trait models and their use in inferring an examinee's ability. In LordF. M.NovickM. R. (Eds.), Statistical theories of mental test scores (pp. 396–479). Addison-Wesley.
5.
CaoJ.StokesS. L. (2008). Bayesian IRT guessing models for partial guessing behaviors. Psychometrika, 73, 209–230.
6.
CeleuxG. (1985). The SEM algorithm: a probabilistic teacher algorithm derived from the EM algorithm for the mixture problem. Computational Statistics Quarterly, 2, 73–82.
7.
CeleuxG.HurnM.RobertC. P. (2000). Computational and inferential difficulties with mixture posterior distributions. Journal of the American Statistical Association, 95(451), 957–970.
8.
CulpepperS. A. (2016). Revisiting the 4-parameter item response model: Bayesian estimation and application. Psychometrika, 81(4), 1142–1163.
9.
EfronB.HinkleyD. V. (1978). Assessing the accuracy of the maximum likelihood estimator: Observed versus expected Fisher information. Biometrika, 65(3), 457–483.
10.
FoxJ.-P. (2003). Stochastic EM for estimating the parameters of a multilevel IRT model. British Journal of Mathematical and Statistical Psychology, 56(1), 65–81.
11.
FoxJ.-P.GlasC. A. (2001). Bayesian estimation of a multilevel IRT model using Gibbs sampling. Psychometrika, 66(2), 271–288.
12.
GuoS.WuT.ZhengC.ChenY. (2021). Bayesian modal estimation for the one-parameter logistic ability-based guessing (1PL-AG) model. Applied Psychological Measurement, 45(3), 195–213.
13.
GuoS.ZhengC. (2019). The Bayesian expectation-maximization-maximization for the 3PLM. Frontiers in Psychology, 10, 1175.
McKinleyR. L.MillsC. N. (1985). A comparison of several goodness-of-fit statistics. Applied Psychological Measurement, 9(1), 49–57.
17.
MengX.XuG. (2023). A mixed stochastic approximation EM (MSAEM) algorithm for the estimation of the four-parameter normal ogive model. Psychometrika, 88(4), 1407–1442.
18.
MengX.-L.RubinD. B. (1993). Maximum likelihood estimation via the ECM algorithm: A general framework. Biometrika, 80(2), 267–278.
19.
MengX.-L.SchillingS. (1996). Fitting full-information item factor models and an empirical investigation of bridge sampling. Journal of the American Statistical Association, 91(435), 1254–1267.
20.
OrlandoM.ThissenD. (2000). Likelihood-based item-fit indices for dichotomous item response theory models. Applied Psychological Measurement, 24(1), 50–64.
21.
OrlandoM.ThissenD. (2003). Further investigation of the performance of S-X2: An item fit index for use with dichotomous item response theory models. Applied Psychological Measurement, 27(4), 289–298.
22.
ParkR.PituchK. A.KimJ.DoddB. G.ChungH. (2015). Marginalized maximum likelihood estimation for the 1PL-AG IRT model. Applied Psychological Measurement, 39(6), 448–464.
23.
PokropekA. (2016). Grade of membership response time model for detecting guessing behaviors. Journal of Educational and Behavioral Statistics, 41(3), 300–325.
24.
SideridisG.AlahmadiM. (2022). Estimation of person ability under rapid and effortful responding. Journal of Intelligence, 10(3), 67.
25.
WiseS. L.DeMarsC. E. (2006). An application of item response time: The effort-moderated IRT model. Journal of Educational Measurement, 43(1), 19–38.
26.
WollackJ. A.BoltD. M.CohenA. S.LeeY.-S. (2002). Recovery of item parameters in the nominal response model: A comparison of marginal maximum likelihood estimation and Markov Chain Monte Carlo Estimation. Applied Psychological Measurement, 26(3), 339–352.
27.
YenW. M. (1981). Using simulation results to choose a latent trait model. Applied Psychological Measurement, 5(2), 245–262.
28.
ZhangS.ChenY.LiuY. (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.
29.
ZhengC.GuoS.KernJ. L. (2021). Fast Bayesian estimation for the four-parameter logistic model (4PLM). SAGE Open, 11(4), 21582440211052556.
30.
ZhengC.MengX.GuoS.LiuZ. (2018). Expectation-maximization-maximization: A feasible MLE algorithm for the three-parameter logistic model based on a mixture modeling reformulation. Frontiers in Psychology, 8, 2302.
31.
ZhuZ.WangC.TaoJ. (2019). A two-parameter logistic extension model: An efficient variant of the three-parameter logistic model. Applied Psychological Measurement, 43(6), 449–463.
