Semiparametric Estimation in the Rasch Model and Related Exponential Response Models, Including a Simple Latent Class Model for Item Analysis

Lindsay, Bruce G.; Clogg, Clifford C.; Grego, John M.

doi:10.2307/2289719

Cited by 95 publications

(108 citation statements)

References 0 publications

Supporting

Mentioning

106

Contrasting

Unclassified

Order By: Relevance

“…This section discusses different approaches that are well suited for this purpose: restricted as well as unrestricted versions of latent class models, semi-parametric, and parametric item-response models. These models have proven useful for the analysis of categorical data in many social and behavioral science applications (Lazarsfeld and Henry, 1968;Lindsay et al, 1991). We modify these models to accommodate RR schemes and, subsequently, extend them to allow for two different types of response biases which may result when respondents do not follow the randomization scheme.…”

Section: Multivariate Analysis Of Randomized-response Datamentioning

confidence: 99%

“…Because Â t is independent of the item involved, it is straightforward to interpret differences between subpopulations. Equation (3) is a latent-class version of a Rasch model (Lindsay et al, 1991;Formann, 1992). For fixed T, the Rasch constraint can be tested via a nested log-likelihood ratio test against its unrestricted counterpart (1).…”

Section: Semi-parametric Rasch Randomized Response Modelmentioning

confidence: 99%

See 1 more Smart Citation

Do randomized‐response designs eliminate response biases? An empirical study of non‐compliance behavior

Böckenholt

Barlas

Heijden

2009

J of Applied Econometrics

View full text Add to dashboard Cite

SUMMARYOut of the toolbox of survey methods for obtaining honest answers to sensitive issues, the method of randomized responses (RR) has proven to be the most effective one. So far, in applications of RR methods it has been assumed that they eliminate response biases. We investigate the validity of this assumption by applying multivariate RR models that allow for different types of response biases. Our data analyses show that RR methods do not eliminate response biases but that they can be modeled in informative ways: accounting for response biases leads to estimates that are at least twice the size of the estimates obtained when response biases are ignored.

show abstract

Section: Multivariate Analysis Of Randomized-response Datamentioning

confidence: 99%

Section: Semi-parametric Rasch Randomized Response Modelmentioning

confidence: 99%

Do randomized‐response designs eliminate response biases? An empirical study of non‐compliance behavior

Böckenholt

Barlas

Heijden

2009

J of Applied Econometrics

View full text Add to dashboard Cite

show abstract

“…For instance, subject homogeneity may be determined by a continuous variable, in which case homogeneity within levels of X may occur to a decent approximation only for relatively large L. Or, lack of fit may occur because of violations of the assumption of no three-factor interaction for {jsri . From results in Lindsay et al (1991), it follows that one can check this assumption by comparing the fit of the QLC model to that of the ordinary LC model having the same number of latent classes. Though the scope of QLC models may be limited, we believe they are worthy of notice because of the economical description available when they do fit well.…”

Section: Application To Modeling Interrater Agreementmentioning

confidence: 99%

Quasi-Symmetric Latent Class Models, with Application to Rater Agreement

Agresti¹,

Joseph²

1993

Biometrics

View full text Add to dashboard Cite

JSTOR is a not-for-profit service that helps scholars, researchers, and students discover, use, and build upon a wide range of content in a trusted digital archive. We use information technology and tools to increase productivity and facilitate new forms of scholarship. For more information about JSTOR, please contact support@jstor.org.International Biometric Society is collaborating with JSTOR to digitize, preserve and extend access to Biometrics.http://www.jstor.org SUMMARYSuppose we observe responses on several categorical variables having the same scale. We consider latent class models for the joint classification that satisfy quasi-symmetry. The models apply when subject-specific response distributions are such that (i) for a given subject, responses on different variables are independent, and (ii) odds ratios comparing marginal distributions of the variables are identical for each subject. These assumptions are often reasonable in modeling multirater agreement, when a sample of subjects is rated independently by different observers. In this application, the model parameters describe two components of agreement-strength of association between classifications by pairs of observers and degree of heterogeneity among the observers' marginal distributions. We illustrate the models by analyzing a data set in which seven pathologists classified 118 subjects in terms of presence or absence of carcinoma, yielding seven categorical classifications with the same binary scale. A good-fitting model has a latent classification that differentiates between subjects on whom there is agreement and subjects on whom there is disagreement. Introduction

show abstract

“…We seek to show that methodological options other than located latent class models (LLCM; e.g., Lindsay, Clogg, & Grego, 1991) or unidimensional DCMs, which are isomorphic to Guttman scales, are needed to model linear attribute hierarchies because of the possible states of empirical data. von Davier and Haberman (2014) showed that a Guttman scale given by set G = {0, 1, 2, 3} was one-to-one with set…”

Section: The Distinction Of Guttman Scales and Linear Attribute Hieramentioning

confidence: 99%

The Use and Misuse of Psychometric Models

Templin

Bradshaw

2014

Psychometrika

View full text Add to dashboard Cite

The purpose of our paper entitled Hierarchical Diagnostic Classification Models: A Family of Models for Estimating and Testing Attribute Hierarchies was two-fold: to create a psychometric model and framework that would enable attribute hierarchies to be parameterized as dependent binary latent traits, and to formulate an empirically driven hypothesis test for the purpose of falsifying proposed attribute hierarchies. The methodological contributions of this paper were motivated by a curious result in the analysis of a real data set using the log-linear cognitive diagnosis model, or LCDM (Henson, Templin, & Willse, 2009). In the analysis of the Examination for Certification of Proficiency in English (ECPE; Templin & Hoffman, 2013), results indicated that few, if any, examinees were classified into four of the possible eight attribute profiles that are hypothesized in the LCDM for a test of three binary latent attributes. Further, when considering the four profiles lacking examinees, it appeared that some attributes must be mastered before others, suggesting what is commonly called an attribute hierarchy (e.g., Leighton, Gierl, & Hunka, 2004). Although the data analysis alerted us to the notion that such a data structure might be present, we lacked the methodological tools to falsify the presence of such an attribute hierarchy. As such, we developed the Hierarchical Diagnostic Classification Model, or HDCM, in an attempt to fill the need for such tools.We note that the driving force behind the HDCM is one of seeking a simpler, or more parsimonious, solution when model data misfit is either evident from LCDM results or implied by the hypothesized theories underlying the assessed constructs. As a consequence of the ECPE data results, we worked to develop a more broadly defined set of models that would allow for empirical evaluation of hypothesized attribute hierarchies. We felt our work was timely, as a number of methods, both new and old, are now using implied attribute hierarchies to assess examinees in many large scale analyses-from so-called intelligent tutoring systems (e.g

show abstract

Semiparametric Estimation in the Rasch Model and Related Exponential Response Models, Including a Simple Latent Class Model for Item Analysis

Cited by 95 publications

References 0 publications

Do randomized‐response designs eliminate response biases? An empirical study of non‐compliance behavior

Do randomized‐response designs eliminate response biases? An empirical study of non‐compliance behavior

Quasi-Symmetric Latent Class Models, with Application to Rater Agreement

The Use and Misuse of Psychometric Models

Contact Info

Product

Resources

About