PsychometrikaPub Date : 2026-11-03DOI: 10.1017/psy.2026.10150
Yu Wang, Chia-Yi Chiu
{"title":"Q-Matrix Completeness for Multiple-Choice Items in Cognitive Diagnosis.","authors":"Yu Wang, Chia-Yi Chiu","doi":"10.1017/psy.2026.10150","DOIUrl":"https://doi.org/10.1017/psy.2026.10150","url":null,"abstract":"<p><p>Research in the development of cognitive diagnosis (CD) methods for multiple-choice (MC) items has advanced. However, some key statistical properties of the Q-matrix for MC items remain unexplored. One such critical property is completeness, which, when satisfied, ensures that all possible attribute profiles in the data can be identified. An incomplete Q-matrix may result in the misclassification of examinees, leading to distorted interpretations of results and misguided pedagogical interventions. Moreover, a complete Q-matrix is a fundamental assumption in several important areas of CD research, such as model identifiability. In light of these undesirable consequences, this study aims to establish sufficient and necessary conditions for determining the completeness of the Q-matrix for MC items. However, this problem is not a simple extension of the corresponding one for binary items, because an MC item may contain additional diagnostic information through its coded distractors. Consequently, conditions that are sufficient and necessary for completeness in the binary setting may no longer be necessary in the MC setting. To support the proposed theorem, a lemma is developed, followed by corollaries that enhance its applicability. All theoretical advancements are rigorously justified through formal mathematical proofs. Subsequently, a simulation study is conducted to illustrate the implication of the proposed theorem.</p>","PeriodicalId":54534,"journal":{"name":"Psychometrika","volume":" ","pages":"1-25"},"PeriodicalIF":2.9,"publicationDate":"2026-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149327534","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PsychometrikaPub Date : 2026-10-21DOI: 10.1017/psy.2026.10149
Yuxuan Xu, Lea Kaufmann, Yunxiao Chen, Maria Kateri, Irini Moustaki
{"title":"Sparse Latent Class Analysis for Dichotomous Responses: Post-Estimation Refinement via Item-Level Pseudo-Likelihood.","authors":"Yuxuan Xu, Lea Kaufmann, Yunxiao Chen, Maria Kateri, Irini Moustaki","doi":"10.1017/psy.2026.10149","DOIUrl":"https://doi.org/10.1017/psy.2026.10149","url":null,"abstract":"<p><p>Latent class analysis (LCA) is widely used to identify unobserved subgroups in social and behavioral sciences. A long-standing challenge for LCA is the interpretability of the latent classes, due to the high complexity of the estimated item-response probability matrix. To address this, we propose a computationally efficient post-estimation refinement procedure that enhances model interpretability by a sparse model estimate. The method begins by estimating a classical, unrestricted, latent class model and determining the number of classes using the Bayesian information criterion. It is followed by a refinement step that further performs model selection on the item-specific response probabilities based on the initial estimate. This refinement penalizes the number of distinct response probability levels per item, collapsing redundant levels to yield a sparse matrix that is significantly easier to interpret than those produced by classical LCA. We provide asymptotic theory showing that the proposed procedure consistently recovers the sparse pattern of the item-response probabilities for each item and further validate its performance through extensive simulations. The practical power of the proposed method is further illustrated via an application to survey data on social role performance, where it provides a parsimonious and clear characterization of the resulting latent classes.</p>","PeriodicalId":54534,"journal":{"name":"Psychometrika","volume":" ","pages":"1-19"},"PeriodicalIF":2.9,"publicationDate":"2026-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149240322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PsychometrikaPub Date : 2026-10-16DOI: 10.1017/psy.2026.10147
Chih-Han Leng, Ulf Böckenholt
{"title":"Familiarity and Liking in Classroom Networks: A Multilayer Analysis of Rated Peer Relations.","authors":"Chih-Han Leng, Ulf Böckenholt","doi":"10.1017/psy.2026.10147","DOIUrl":"https://doi.org/10.1017/psy.2026.10147","url":null,"abstract":"<p><p>Many social network datasets consist of ordinal ratings exchanged among the same set of individuals on multiple relational dimensions. Such data are common in educational and behavioral research but pose challenges due to ordinal measurement, asymmetric sender and receiver roles, and dependence within and across relations. We analyze classroom network data from Taiwanese senior high schools, in which students provided ratings of familiarity and liking, to examine relational dimensionality, reciprocity, cross-relational overlap, and individual characteristics. To this end, we develop and apply a latent-space rated-network model that accounts for ordinal rating scales, sender and receiver heterogeneity, and higher-order interaction structure. The model allows familiarity and liking to be treated either as a single relational dimension or as distinct but interdependent layers and decomposes within- and cross-layer dependence into interpretable, role-specific components linked to classical network summaries, such as reciprocity and multiplexity. In application, the model shows that high descriptive overlap between familiarity and liking does not imply a common generative process. Latent interaction patterns are shared across relations, but differences emerge in dispersion of latent positions, particularly by gender. Moreover, familiarity ratings are associated with both sender and receiver personality traits, whereas liking ratings are primarily associated with receiver traits.</p>","PeriodicalId":54534,"journal":{"name":"Psychometrika","volume":" ","pages":"1-41"},"PeriodicalIF":2.9,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149197781","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PsychometrikaPub Date : 2026-10-16DOI: 10.1017/psy.2026.10143
Sunbeom Kwon, Susu Zhang
{"title":"A Copula-Based Joint Model for Speed and Accuracy.","authors":"Sunbeom Kwon, Susu Zhang","doi":"10.1017/psy.2026.10143","DOIUrl":"https://doi.org/10.1017/psy.2026.10143","url":null,"abstract":"<p><p>This study proposes a copula-based model that relaxes the multivariate normality assumption among latent traits in the joint modeling of multimodal data, such as item response and response times. In the structural model, the joint distribution of latent traits is defined via a copula with tail dependence. An expectation-maximization algorithm with stochastic approximation is implemented for parameter estimation. A simulation study evaluates the proposed method's accuracy in ability estimation under various conditions, comparing it to traditional approaches. By better capturing the dependence structure between latent ability and speed, the proposed method outperforms the traditional approach with multivariate normality assumption. Applied to a variety of empirical datasets, the proposed method's flexibility and the improvement in model fit are illustrated. The copula-based latent variable modeling can be generalized to broader applications in psychological testing involving multivariate latent traits.</p>","PeriodicalId":54534,"journal":{"name":"Psychometrika","volume":" ","pages":"1-57"},"PeriodicalIF":2.9,"publicationDate":"2026-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149197731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PsychometrikaPub Date : 2026-10-15DOI: 10.1017/psy.2026.10145
Naomi Kaplan-Damary, Binyamin Oz, Hal S Stern
{"title":"Preference or Confidence? Untangling Heterogeneity in Paired Comparisons.","authors":"Naomi Kaplan-Damary, Binyamin Oz, Hal S Stern","doi":"10.1017/psy.2026.10145","DOIUrl":"https://doi.org/10.1017/psy.2026.10145","url":null,"abstract":"<p><p>Paired comparison models analyze data from experiments in which items are compared two at a time. Each item is often associated with a strength parameter, and parameter differences determine choice probabilities. The parameters carry two kinds of information. Their order encodes ordinal preferences, and their magnitude reflects the confidence or consistency with which those preferences are expressed. Standard paired comparison models often assume that a single set of strength parameters characterizes all decision-makers. One way to relax this assumption is to fit a mixture model with a fixed number of groups, each with its own parameter set. However, if individual variation in confidence is not modeled, estimation may allocate the limited number of groups to capture magnitude differences rather than differences in order. This article presents a framework that integrates random effects into mixture models, allowing population subgroups and individual-level confidence variation to be estimated simultaneously. By absorbing within-group confidence variation, the available groups are freed to capture meaningful differences in preference order. Simulation studies show improved estimation and interpretability and demonstrate that covariate-based partitioning cannot replace direct modeling of intra-individual variation. Model performance is illustrated using data on juror perceptions of forensic evidence reports.</p>","PeriodicalId":54534,"journal":{"name":"Psychometrika","volume":" ","pages":"1-23"},"PeriodicalIF":2.9,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149197833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PsychometrikaPub Date : 2026-10-06DOI: 10.1017/psy.2026.10146
Jinwen Luo, Sijia Huang, Minjeong Jeon
{"title":"Investigating Within-Person Variation in Response Processes for Likert-Scale Data with a Response-Level Mixture IRTree Model.","authors":"Jinwen Luo, Sijia Huang, Minjeong Jeon","doi":"10.1017/psy.2026.10146","DOIUrl":"https://doi.org/10.1017/psy.2026.10146","url":null,"abstract":"<p><p>Self-report scales are central to psychological and behavioral science, yet most analyses assume a single response process. In practice, respondents may follow cognitively distinct processes to answer the same item, and a respondent may switch processes across items. Ignoring between-person and/or within-person heterogeneity in item response process may bias item parameter estimates and person scores. In this study, we introduce a response-level mixture model, namely, MIX-R. The proposed model represents two or more distinct response processes using item response trees and specifies the probability that a specific process is used with a prevalence model, which includes additive person and item effects and optional covariates. We fit MIX-R in a fully Bayesian framework. Applied to three-category items from the verbal aggression questionnaire, MIX-R reveals distinct process-specific item functioning so that expected scores of the same item vary across response processes. As shown in our simulation studies, MIX-R exhibits better model fit when it is consistent with the data-generating process and does not overfit. In addition, it accurately recovers person-level and item-level process prevalence and item parameters. We conclude this study by discussing its limitations and outlining directions for future research.</p>","PeriodicalId":54534,"journal":{"name":"Psychometrika","volume":" ","pages":"1-25"},"PeriodicalIF":2.9,"publicationDate":"2026-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149118473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PsychometrikaPub Date : 2026-09-30DOI: 10.1017/psy.2026.10144
Francis Tuerlinckx, Hernán Robledo
{"title":"Geodesic Ability in Unidimensional IRT Models: A Geometric Perspective on Parametrization Invariance.","authors":"Francis Tuerlinckx, Hernán Robledo","doi":"10.1017/psy.2026.10144","DOIUrl":"https://doi.org/10.1017/psy.2026.10144","url":null,"abstract":"<p><p>Psychometric models use latent variables to quantify psychological traits, but statistical and substantive inferences based on these variables may depend on how the latent scale is parametrized. Consequently, the same fitted model can yield qualitatively different conclusions under different parametrizations. Building on Ramsay's (1996, <i>Behaviormetrika</i>, 23, 3-16) geometric perspective, we reinterpret this problem using differential geometry. While Ramsay defined ability via an arc length in Euclidean space, psychometric models can be seen instead as a curved statistical manifold with the Fisher-Rao metric. This allows for a parametrization-invariant definition of ability, which we term geodesic ability. We illustrate this concept for unidimensional item response theory models, including the Rasch and 3PL models, and compare it to Ramsay's arc-length approach.</p>","PeriodicalId":54534,"journal":{"name":"Psychometrika","volume":" ","pages":"1-15"},"PeriodicalIF":2.9,"publicationDate":"2026-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149082811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PsychometrikaPub Date : 2026-09-21DOI: 10.1017/psy.2026.10134
Bin Lv, Yincai Tang, Siliang Zhang
{"title":"A Cumulative Ordered Spike-and-Slab Prior for Adaptive Dimension Selection in Joint Latent Space Models.","authors":"Bin Lv, Yincai Tang, Siliang Zhang","doi":"10.1017/psy.2026.10134","DOIUrl":"https://doi.org/10.1017/psy.2026.10134","url":null,"abstract":"<p><p>Network models are increasingly vital in psychometrics for analyzing relational data, which are often accompanied by high-dimensional node attributes. Joint latent space models provide an elegant framework for integrating these data sources by assuming a shared underlying latent representation; however, a persistent methodological challenge is determining the dimension of the latent space, as existing methods typically require pre-specification or rely on computationally intensive post-hoc procedures. The key innovation of this work is a cumulative ordered spike-and-slab prior, which we incorporate within a Bayesian joint latent space modeling framework. This prior enables the latent dimension to be inferred automatically and simultaneously with all model parameters. We develop an efficient Markov chain Monte Carlo algorithm for posterior computation. Theoretically, we establish that the posterior distribution concentrates on the true latent dimension and that parameter estimates achieve Hellinger consistency at a near-optimal rate that adapts to the unknown dimensionality. Through extensive simulations and three real-data applications, we demonstrate the method's superior performance in both dimension recovery and parameter estimation. Our work offers a principled, computationally efficient, and theoretically grounded solution for adaptive dimension selection in psychometric network models.</p>","PeriodicalId":54534,"journal":{"name":"Psychometrika","volume":" ","pages":"1-23"},"PeriodicalIF":2.9,"publicationDate":"2026-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149012995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}