Loglinear smoothing (LLS) estimates the latent trait distribution while making fewer assumptions about its form and maintaining parsimony, thus leading to more precise item response theory (IRT) item parameter estimates than standard marginal maximum likelihood (MML). This article provides the expectation-maximization algorithm for MML estimation with LLS embedded and compares LLS to other latent trait distribution specifications, a fixed normal distribution, and the empirical histogram solution, in terms of IRT item parameter recovery. Simulation study results using a 3-parameter logistic model reveal that LLS models matching four or five moments are optimal in most cases. Examples with empirical data compare LLS to these approaches as well as Ramsay-curve IRT.
AkaikeH. (1973). Information theory and an extension of the maximum likelihood principle. In PetrovB. N.CsakiF. (Eds.), Second international symposium on information theory (pp. 267–281). Budapest, Hungary: Academiai Kiado.
2.
AndersenE. B.MadsenM. (1977). Estimating the parameters of a latent population distribution. Psychometrika, 42, 357–374.
3.
BockR. D.AitkinM. (1981). MML estimation of item parameters: Application of an EM algorithm. Psychometrika, 46, 443–459.
4.
BockR. D.LiebermanM. (1970). Fitting a response model for n dichotomously scored items. Psychometrika, 35, 179–197.
5.
BouletJ. R. (1996). The effect of nonnormal ability distributions on IRT parameter estimation using full-information and limited-information methods (IRT, nonlinear factor analysis). Dissertation abstracts online, University of Ottawa (Canada).
6.
CaiL. (2010). A two-tier full-information item factor analysis model with applications. Psychometrika, 75, 581–612.
7.
CaiL. (2013). flexMIRT version 2: Flexible multilevel multidimensional item analysis and test scoring [Computer software]. Chapel Hill, NC: Vector Psychometric Group.
8.
CasabiancaJ. M. (2011). Loglinear smoothing for the latent trait distribution: A two-tiered evaluation. (Doctoral dissertation). ProQuest Dissertations and Theses. (Accession Order No. AAT 3474125).
9.
CasabiancaJ. M.LewisC. (2011a, 4). The Impact of IRT Item Parameter Estimation Error on IRT True Score Equating Functions and CSEMs: A Robustness Study. Paper presented at the annual meeting of the National Council for Measurement in Education. New Orleans, Louisiana.
10.
CasabiancaJ .M.LewisC. (2011b). LLSEM 1.0: LogLinear Smoothing in an Expectation Maximization algorithm for item response theory item parameter estimation. [Computer software]. Bronx, NY.
11.
CasabiancaJ. M.XuX.JiaY.LewisC. (2010, May). Estimation of Item Parameters when the Underlying Latent Trait Distribution of Test Takers is Nonnormal. Paper presented at the annual meeting of the National Council for Measurement in Education. Denver, Colorado.
12.
CressieN.HollandP. W. (1983). Characterizing the manifest probabilities of latent trait models. Psychometrika, 48, 129–141.
13.
De LeeuwJ.VerhelstN. (1986). Maximum likelihood estimation in generalized Rasch models. Journal of Educational Statistics, 11, 183–196.
14.
DempsterA.LairdN.RubinD. (1977). Maximum likelihood from incomplete data via the EM algorithm. Journal of the Royal Statistical Society, Series B, 39, 1–38.
15.
EysenckH. J.EysenckS. B. G. (1991). Eysenck Personality Questionnaire—Revised (EPQ-R). London, England: Hodder and Stoughton.
16.
HabermanS. J. (2005). Identifiability of parameters in item response models with unconstrained ability distributions (Research Report 05-24). Princeton, NJ: Educational Testing Service.
17.
HannanE. J. (1987). Rational transfer function approximation. Statistical Science, 2, 135–151.
18.
HodgsonR. J.RachmanS. (1977). Obsessional-compulsive complaints. Behaviour Research and Therapy, 15, 389–395.
19.
HollandP. W.ThayerD. T. (1987). Notes on the use of loglinear models for fitting discrete probability distributions (Research Report 87-31). Princeton, NJ: Educational Testing Service.
20.
HollandP. W.ThayerD. T. (2000). Univariate and bivariate loglinear models for discrete test score distributions. Journal of Educational and Behavioral Statistics, 25, 133–183.
21.
JohnsonN. L. (1949). Systems of frequency curves generated by methods of translation. Biometrika, 36, 149–176.
22.
KolmogorovA. (1933). Sulla determinazione empirica di una legge di distributione. Giornale dell’Istituto Italiano degli Attuari, 4, 1–11.
23.
LewisC. (1985). Discussion. In WeissD. J. (Ed.), Proceedings of the 1982 IRT and Computerized Adaptive Testing Conference (pp. 203–209). Minneapolis: University of Minnesota, Department of Psychology, Computerized Adaptive Testing Laboratory.
24.
LindsayB.CloggC. C.GregoJ. (1991). Semiparametric estimation in the Rasch model and related exponential response models, including a simple latent class model for item analysis. Journal of the American Statistical Association, 86, 96–107.
25.
LordF. M. (1953). The relation of test score to the trait underlying the test. Educational and Psychological Measurement, 13, 517–549.
26.
LordF. M.NovickM. R. (1968). Statistical theories of mental test scores. Reading, MA: Addison-Wesley.
27.
MatthewsG.DearyI. J.WhitemanM. C. (2003). Personality traits (2nd ed.). New York, NY: Cambridge University Press.
28.
MislevyR. J. (1984). Estimating latent distributions. Psychometrika, 49, 359–381.
29.
MislevyR. J.BockR. D. (1985). Implementation of the EM Algorithm in the estimation of item parameters: The BILOG computer program. In WeissD. J. (Ed.), Proceedings of the 1982 IRT and Computerized Adaptive Testing Conference (pp. 189–202). Minneapolis: University of Minnesota, Department of Psychology, Computerized Adaptive Testing Laboratory.
30.
MurakiE.BockR. D. (2003). PARSCALE 4 for Windows: IRT based test scoring and item analysis for graded items and rating scales [Computer software]. Lincolnwood, IL: Scientific Software International.
31.
NeymanJ.ScottE. L. (1948). Consistent estimates based on partially consistent observations. Econometrica, 16, 1–32.
32.
RigdonS. E.TsutakawaR. K. (1983). Parameter estimation in latent trait models. Psychometrika, 48, 567–574.
33.
RostJ.von DavierM. (1992). MIRA—A PC program for the mixed Rasch model user manual. Kiel, Germany: IPN.
34.
RostJ.von DavierM. (1995). Mixture distribution Rasch models. In FischerG. H.MolenaarI. W.. (Eds.), Rasch models: Foundations, recent developments, and applications. (Ch. 14; pp. 257–268). New York, NY: Springer Verlag.
35.
SanathananL.BlumenthalS. (1978). The logistic model and estimation of latent structure. Journal of the American Statistical Association, 73, 794–799.
36.
SchwarzG. (1978). Estimating the dimension of a model. Annals of Statistics, 6, 461–464.
37.
SmirnovN. (1939). Sur les écarts de la courbe de distribution empirique. Recueil Mathématique, 6, 3–26.
38.
StoneC. A. (1992). Recovery of MML estimates in the two-parameter logistic response model: An evaluation of MULTILOG. Applied Psychological Measurement, 16, 1–16.
SwaminathanH.GiffordJ. (1983). Estimation of parameters in the three-parameter latent trait model. In WeissD. J. (Ed.), New horizons in testing: Latent trait test theory and computerized adaptive testing (pp. 13–30). New York, NY: Academic Press.
41.
ThissenD. (2003). MULTILOG 7: Multiple categorical item analysis and test scoring using item response theory [Computer software]. Chicago, IL: Scientific Software.
42.
TsutakawaR. K. (1985). Estimation of item parameters and the GEM algorithm. In WeissD. J. (Ed.), Proceedings of the 1982 IRT and computerized adaptive testing conference (pp. 180–188). Minneapolis: University of Minnesota, Department of Psychology, Computerized Adaptive Testing Laboratory.
43.
TsutakawaR. K.JohnsonJ. C. (1990). The effect of uncertainty of item parameter estimation on ability estimates. Psychometrika, 55, 371–390.
44.
TzamouraniP.KnottM. (2002). Fully semiparametric estimation of the two-parameter latent trait model for binary data. In MarcoulidesG. A.MoustakI. (Eds.), Latent variable and latent structure models (pp. 63–84). Mahwah, NJ: Erlbaum.
45.
van den OordE. J. (2005). Estimating Johnson curve population distributions in MULTILOG. Applied Psychological Measurement, 29(1), 45–64.
46.
von DavierM. (2005). A general diagnostic model applied to language testing data (Research Report 05-16). Princeton, NJ: Educational Testing Service.
47.
WoodsC. M. (2002). Factor analysis of scales composed of binary items: Illustration with the Maudsley Obsessional Compulsive Inventory. Journal of Psychopathology and Behavioral Assessment, 24, 215–223.
48.
WoodsC. M. (2006a). Ramsay-curve item response theory to detect and correct for nonnormal latent variables. Psychological Methods, 11, 253–270.
49.
WoodsC. M. (2006b). RCLOG v.2: Software for item response theory parameter estimation with the latent population distribution represented using spline-based densitiesTechnical Report. St. Louis, MO: Washington University in St. Louis.
50.
WoodsC. M. (2008). Ramsay-curve item response theory for the three-parameter logistic item response model. Applied Psychological Measurement, 32, 447–465.
51.
WoodsC. M.LinN. (2009). IRT with estimation of the latent density using Davidian curves. Applied Psychological Measurement, 33, 102–117.
52.
WoodsC. M.ThissenD. (2006). IRT with estimation of the latent population distribution using spline-based densities. Psychometrika, 71, 281–301.
53.
XuX.JiaY. (2011). The sensitivity of parameter estimates to the latent ability distribution (Research Report 11-40). Princeton, NJ: Educational Testing Service.
54.
XuX.von DavierM. (2008). Fitting the structured general diagnostic model to NAEP data (Research Report 08-27). Princeton, NJ: Educational Testing Service.
55.
YamamotoK.MurakiE. (1991, 4). Non-linear transformation of IRT scale to account for the effect of nonnormal ability distribution on the item parameter estimation. Paper presented at the annual meeting of the American Educational Research Association, Chicago, IL.
56.
ZhangD.DavidianM. (2001). Linear mixed models with flexible distributions of random effects for longitudinal data. Biometrics, 57, 795–802.
57.
ZhangJ. (2011, 4). The role of standard errors of item parameter estimators in IRT-based data analysis. Paper presented at the annual meeting of the National Council on Measurement in Education, New Orleans, LA.
58.
ZhangJ.XieM.SongX.LuT. (2011). Investigating the impact of uncertainty about item parameters on ability estimation. Psychometrika, 76, 97–118.
59.
ZimowskiM. F.MurakiE.MislevyR. J.BockR. D. (2003). BILOG-MG 3 for Windows: Multiple-group IRT analysis and test maintenance for binary items [Computer software]. Lincolnwood, IL: Scientific Software International.
