Questionnaires that include items eliciting count responses are becoming increasingly common in psychology. This study proposes methodological techniques to overcome some of the challenges associated with analyzing multivariate item response data that exhibit zero inflation, maximum inflation, and heaping at preferred digits. The modeling framework combines approaches from three literatures: item response theory (IRT) models for multivariate count data, latent variable models for heaping and extreme responding, and mixture IRT models. Data from the Behavioral Risk Factor Surveillance System are used as a motivating example. Practical implications are discussed, and recommendations are provided for researchers who may wish to use count items on questionnaires.
AgrestiA. (2002). Categorical data analysis. New York, NY: Wiley.
2.
BockR. D. (1972). Estimating item parameters and latent ability when responses are scored in two or more latent categories. Psychometrika, 37, 29–51. doi:10.1007/BF02291411
3.
BöckenholtU. (2012). Modeling multiple response processes in judgment and choice. Psychological Methods, 17, 665–678. doi:10.1037/a0028111
4.
BöckenholtU.KamakuraW. A.WedelM. (2003). The structure of self-reported emotional experiences: A mixed-effects Poisson factor model. British Journal of Mathematical and Statistical Psychology, 56, 215–229. doi:10.1348/000711003770480011
5.
BoltD. M.JohnsonT. R. (2009). Applications of MIRT model to self-report measures: Addressing score bias and DIF due to individual differences in response style. Applied Psychological Measurement, 33, 335–352. doi:10.1177/0146621608329891
6.
BoltD. M.NewtonJ. R. (2011). Multiscale measurement of extreme response style. Applied Psychological Measurement, 71, 814–833. doi:10.1177/0013164410388411
7.
CameronC.TrivediP. K. (2013). Regression analysis of count data, Econometric Society Monograph No. 53 (2nd ed.). Cambridge, England: Cambridge University Press.
8.
Centers for Disease Control and Prevention. (1984–present). Behavioral risk factor surveillance system survey data. Atlanta, GA: U.S. Department of Health and Human Services, Centers for Disease Control and Prevention.
9.
DebP.TrivediP. K. (1997). Demand for medical care by the elderly: A finite mixture approach. Journal of Applied Econometrics, 12, 313–336. doi:10.1002/(SICI)1099-1255(199705)12:33.0.CO;2-G
10.
De BoeckP.PartchevI. (2012). IRTress: Tree-based item response models of the GLMM family. Journal of Statistical Software, 48, 1–28. doi:10.18637/jss.v048.c01
11.
FinchW. H.PiersonE. E. (2011). A mixture IRT analysis of risky youth behavior. Frontiers in Psychology, 2, 1–10. doi:10.3389/fpsyg.2011.00098
12.
FinkelmanM. D.GreenJ. G.GruberM. J.ZaslavskyA. M. (2011). A zero- and K-inflated mixture model for health questionnaire data. Statistics in Medicine, 30, 1028–1043. doi:10.1002/sim.4217
13.
HagenaarsJ.McCuthcheonA. (2002). Applied latent class analysis. Cambridge, England: Cambridge University Press.
14.
HeitjanD. F.RubinD. B. (1990). Inference from coarse data via multiple imputation with application to age heaping. Journal of the American Statistical Association, 85, 304–314. doi:10.1080/01621459.1990.10476202
15.
HilbeJ. M. (2011). Negative binomial regression (2nd ed.). Cambridge, England: Cambridge University Press.
16.
LambertD. (1992). Zero-inflated Poisson regression, with an application to the defects in manufacturing. Technometrics, 34, 1–14. doi:10.1080/00401706.1992.10485228
17.
LewisM. A.NeighborsC.GeisnerI. M.LeeC. M.KilmerJ. R.AtkinsD. C. (2010). Examining the associations among severity of injunctive drinking norms, alcohol consumption, and alcohol-related negative consequences: The moderating roles of alcohol consumption and identity. Journal of Addictive Behaviors, 24, 177–189. doi:10.1037/a0018302
18.
LoeysT.MoerkerkeB.De SmetO.BuysseA. (2012). The analysis of zero-inflated count data: Beyond zero-inflated Poisson regression. British Journal of Mathematical and Statistical Psychology, 65, 163–180. doi:10.1111/j.2044-8317.2011.02031.x
19.
McCullaghP.NelderJ. A. (1989). Generalized linear models (2nd ed.). Boca Raton, FL: Chapman & Hall.
20.
McGinleyJ. S.CurranP. J.HedekerD. (2015). A novel modeling framework for ordinal data defined by collapsed counts. Statistics in Medicine, 34, 2312–2324. doi:10.1002/sim.6495
ReiseS. P.WallerN. G. (2009). Item response theory and clinical measurement. Annual Review of Clinical Psychology, 5, 27–48. doi:10.1146/annurev.clinpsy.032408.153553
23.
RidoutM. S.MorganB. J. T. (1991). Modelling digit preference in fecundability studies. Biometrics, 47, 1423–1433. doi:10.2307/2532396
24.
RobertsJ. M.BrewerD. D. (2010). Measures and tests of heaping in discrete quantitative distributions. Journal of Applied Statistics, 28, 887–896. doi:10.1080/02664760120074960
25.
RostJ. (1990). Rasch models in latent classes: An integration of two approaches to item analysis. Applied Psychological Measurement, 14, 271–282. doi:10.1177/014662169001400305
26.
RostJ. (1997). Logistic mixture models. In van der LindenW. J.HambletonR. K. (Eds.), Handbook of modern item response theory (pp. 449–463). New York, NY: Springer.
27.
SawatzkyR.RatnerP. A.KopecJ. A.ZumboB. D. (2012). Latent variable mixture models: A promising approach for the validation of patient reported outcomes. Quality of Life Research, 21, 637–650. doi:10.1007/s11136-011-9976-6
28.
ThissenD.CaiL.BockR. D. (2010). The nominal categories item response model. In NeringM. L.OstiniR. (Eds.), Handbook of polytomous item response theory models (pp. 43–76). New York, NY: Routledge.
29.
ThissenD.WainerH. (2001). Test scoring. New York, NY: Routledge.
30.
Thissen-RoeA.ThissenD. (2013). A two-decision model for responses to Likert-type items. Journal of Educational and Behavioral Statistics, 38, 522–547. doi:10.3102/1076998613481500
31.
von DavierM.RostJ. (2006). Mixture distribution item response models. In RaoC. R.SinharayS. (Eds.), Handbook of statistics, Vol. 26: Psychometrics (pp. 643–661). Amsterdam, the Netherlands: North Holland.
32.
WallM. M.ParkJ. Y.MoustakiI. (2015). IRT modeling in the presence of zero-inflation with application to psychiatric disorder severity. Applied Psychological Measurement, 39, 583–597. doi:10.1177/0146621615588184
33.
WangH.HeitjanD. F. (2008). Modeling heaping in self-reported cigarette counts. Statistics in Medicine, 27, 3789–3804. doi:10.1002/sim.3281
34.
WangL. (2010). IRT-ZIP modeling for multivariate zero-inflated count data. Journal of Educational and Behavioral Statistics, 35, 671–692. doi:10.3102/1076998610375838
35.
WedelM.BöckenholtU.KamakuraW. A. (2003). Factor models for multivariate count data. Journal of Multivariate Analysis, 87, 356–369. doi:10.1016/S0047-259X(03)00020-4
36.
WrightD. E.BrayI. (2003). A mixture model for rounded data. The Statistician, 52, 3–13. doi:10.1111/1467-9884.00338
