Quantitative Psychology: The 88th Annual Meeting of the Psychometric Society, Maryland, USA, 2023 (Springer Proceedings in Mathematics & Statistics, 452)

Preface
Contents
A Family of Discrete Kernels for Presmoothing Test Score Distributions
	1 Introduction
	2 Kernel Estimation
		2.1 Density Estimation
		2.2 Probability Mass Function Estimation
	3 Discrete Kernels
		3.1 Three Discrete Kernels
			3.1.1 Binomial Kernel
			3.1.2 Triangular Kernel
			3.1.3 Dirac Discrete Uniform Kernel
	4 Log-Linear Modeling
	5 Empirical Illustration
		5.1 Results
	6 Discussion
	References
Priors in Bayesian Estimation Under the Graded Response Model
	1 Introduction
		1.1 Graded Response Model and Priors
		1.2 Model Selection
	2 Method
	3 Results
		3.1 French Test Estimates
		3.2 DIC Results
	4 Discussion
	References
Identifiability Conditions in Cognitive Diagnosis: Implications for Q-Matrix Estimation Algorithms
	1 Introduction and Research Objectives
	2 Review of Key Technical Concepts
	3 Simulation Study
	4 Results
	5 Discussion
	References
A Two-Stage Approach to a Latent Variable Mixed-Effects Location-Scale Model
	1 Introduction
	2 Midlife in the United States (MIDUS) Study
	3 MELS Models
		3.1 Latent MELS Model for a Normal Outcome
	4 Two-Stage Approach
	5 Results
	6 Concluding Remarks
	References
A Hierarchical Prior for Bayesian Variable Selection with Interactions
	1 Introduction
	2 Bayesian Variable Selection with Strong Heredity
	3 Methods
		3.1 SSVS Prior
		3.2 Dirac Spike and Slab Prior
		3.3 Hyper g-Prior
	4 Simulation Study
		4.1 Simulation I
		4.2 Simulation II
	5 Real Data Example
	6 Conclusion and Discussion
	References
Application of Topic Modeling Techniques in Meta-analysis Studies
	1 Introduction
	2 Methods
		2.1 Data Collection
		2.2 Data Analysis
	3 Results and Conclusions
		3.1 Topic Structure by Interpreting the Top 10 Words and Top 20 Representative Abstracts
		3.2 Application of Extracted Topic Structure to Understand Two- to Three-Topic Indexed Abstracts
	4 Discussion
	References
Comparing Maximum Likelihood to Markov Chain Monte Carlo Estimation of the Multivariate Social Relations Model
	1 Introduction
		1.1 The Univariate Social Relations Model
		1.2 The Multivariate Social Relations Model
		1.3 Estimation of Social Relations Models
	2 Method
		2.1 Population Values and Simulation Conditions
		2.2 Analysis Plan
	3 Results
		3.1 Accuracy of Point Estimates
		3.2 Accuracy of Interval Estimates
		3.3 Relative Efficiency of Estimators
	4 Discussion
	References
Exploring Attenuation of Reliability in Categorical Subscore Reporting
	1 Methods
	2 Resampling Study Design
	3 Results
	4 Discussion
	References
Assessing Cross-Level Interactions in Clustered Data Using CATE Estimation Methods
	1 Introduction
		1.1 Potential Outcomes Notation in Clustered Data
		1.2 Subgroup Analysis and CATE
	2 Statistcal Methods for Multilevel Data
		2.1 Multilevel Models and Cross-Level Interactions
		2.2 Causal Machine Learning Methods for CATE
	3 Application: Moderating Effects of School Characteristics on Student Outcome
		3.1 Data and Variables
		3.2 CATE for Cross-Level Interactions
	4 Discussion
	References
A Comparison of Full Information Maximum Likelihood and Machine Learning Missing Data Analytical Methods in Growth Curve Modeling
	1 Introduction
	2 Growth Curve Models
	3 Missing Data Analytical Methods
		3.1 Full Information Maximum Likelihood Method
		3.2 Random Forest Imputation Method
		3.3 K-Nearest Neighbors Imputation Method
	4 A Simulation to Compare the Performance of FIML, RF, and KNN
		4.1 Simulation Design
		4.2 Results
	5 Discussion and Conclusion
	References
Investigating Variable Selection Techniques Under Missing Data: A Simulation Study
	1 Introduction
	2 Methods
		2.1 Simulation Design
		2.2 Variable Selection and Algorithmic Evaluation
	3 Results
	4 Discussion
	References
Comparison of DIF Detection Methods
	1 Introduction
	2 Methods
	3 Simulation Design
	4 Results
	5 Conclusion
	References
Validity Evidence for an ECE Classroom Observation Tool
	1 Introduction
	2 Objective
		2.1 Research Questions
	3 Methods
		3.1 Participants and Settings
		3.2 Measurement Tool: Teach ECE
		3.3 Psychometric Models and Data Analysis
	4 Results
	5 Conclusions
	Appendix: Code in R
	References
Enhancing Multilevel Models Through Supervised Machine Learning
	1 Introduction
	2 Linear (LME) and Non-linear Mixed-Effects Model
	3 Mixed Effects in Machine Learning (MixedML) Framework
		3.1 Estimation
		3.2 Application in Traditional Mixed-Effects Models
		3.3 Prediction
	4 Empirical Example
	5 Conclusion and Discussion
	References
Assessing the Effects of a Yearly Renewable Education Program Through Causal Mediation Analysis
	1 Evaluating Yearly Renewable Education Programs as Time-Varying Treatments
	2 Disentangling Time-Varying Treatment Effects as Causal Mediation Effects
		2.1 Long-Term Effects of the Initial Treatment as Natural Direct Effects
		2.2 Sequential Effects of Time-Varying Treatments as Natural Indirect Effects
	3 Regression-Based Estimation of Causal Mediation Effects
	4 Empirical Example: The Effects of Head Start on Children\'s School Readiness by Attendance History
		4.1 Data and Analysis
		4.2 Results
	5 Discussion
	References
Gumbel-Reverse Gumbel (GRG) Model: A New Asymmetric IRT Model for Binary Data
	1 Introduction
	2 The Gumbel-Reverse Gumbel Model
	3 Empirical Example: Synthetic Aperture Personality Assessment Intelligence Items
		3.1 Methods
		3.2 Results
	4 Discussion
	References
Fisher Information-Based Item Difficulty and Discrimination Indices for Binary Item Response Models
	1 Introduction
	2 Fisher Information for the 2PL Model
	3 3PL Example
		3.1 Using Fisher Information in Analogy to the 2PL
	4 Asymmetric IRT Example
		4.1 Logistic Positive Exponent Model
		4.2 Complementary Log–Log Model
		4.3 Using Fisher Information in Analogy to the 2PL
	5 Discussion
	References
Investigating the Impact of Equating on Measurement Error Using Generalizability Theory
	1 Introduction
	2 A Framework for Generalizability Theory Applications and Example Designs
	3 The Contribution of Equating to Individual and Group Mean Error Variances
	4 Data Simulation
	5 Generalizability Analysis Results
	6 Concluding Remarks
	References
Fitting a Drift–Diffusion Item Response Theory Model to Complex Cognition Response Times
	1 Introduction
	2 Describing Diffusion Process as a Markov Random Walk Process
	3 Simulating Response Distributions Using DDM Random Walk
		3.1 Drift Rate Configurations
		3.2 Random Walk
	4 The Q-Diffusion Model (QDM)
	5 Bayesian Modeling of the Q-Diffusion Model
		5.1 Bayesian Inference
		5.2 Bayesian Model Fit Evaluation
	6 Results
		6.1 Simulated Dataset
		6.2 Model Fit
	7 Conclusion
	References
Comparing Correlation Tests
	1 Introduction
	2 Testing Methods
		2.1 Traditional Parametric Procedure
		2.2 Bivariate Bootstrapping Procedure
		2.3 Univariate Bootstrap Procedure
		2.4 Bootstrap Hypothesis Testing Procedure
	3 Inference of Correlation
		3.1 Data Generation Methods
		3.2 Asymptotic Distribution of Covariance Matrix
		3.3 Asymptotic Distribution of Correlation
	4 Simulation Studies
	5 Results
	6 Conclusions and Discussion
	References
Optimizing Maximum Likelihood Estimation in Performance Factor Analysis: A Comparative Study of Estimation Methods
	1 Background and Motivation
	2 Method
		2.1 Research Design
		2.2 PFA Model and Parameters
		2.3 MLE Optimizers
		2.4 Model Evaluation
	3 Results
	4 Discussion
	References
Validation of the Household Food Security Survey Module (HFSSM) Using Factor Analysis and Rasch Measurement Theory
	1 Introduction
		1.1 Purpose
	2 Methodology
		2.1 Participants
		2.2 Procedure
		2.3 Instrument
		2.4 Models
	3 Results
	4 Discussion
	References
Are We Playing the Same Game? Translating Fairness Content
	1 Background
	2 Methods
		2.1 Assessments
		2.2 Data Collection
		2.3 Factor Model
		2.4 Factorial Invariance Testing
	3 Results
		3.1 European Spanish
		3.2 Latin American Spanish
		3.3 Comparing the Spanish Dialects
	4 Discussion
	5 Conclusion
	References
Diagnosing Skills and Misconceptions with Bayesian Networks Applied to Diagnostic Multiple-Choice Tests
	1 Introduction
	2 A Brief Introduction to Bayesian Networks
	3 Bayesian Networks in Psychometrics Research
	4 Application: Diagnosing “Bugs” in Multicolumn Subtraction
	5 Discussion
	References
Exploring Conceptual Differences Among Nonparametric Estimators of Treatment Heterogeneity in the Context of Clustered Data
	1 Causal Inference and the Potential Outcomes Framework
		1.1 Continuous Covariates and CATE
	2 Simulation Study
		2.1 Trends in International Mathematics and Sciences Study
		2.2 Data Generation Method
	3 Methods
		3.1 Nonparametric Methods for Estimating CATE
		3.2 Background on Selected Methods
			3.2.1 Causal Forests
			3.2.2 Bayesian Causal Forests
			3.2.3 Multilevel Model + Bayesian Additive Regression Trees
	4 Results
	5 Discussion
	References
Assessment of Testlet Effects: Testing it All at Once
	1 Introduction
	2 Testlets and the Assumption of Local Independence
		2.1 Methods for Testing Testlet Effects
	3 Parametric Bootstrap Mantel–Haenszel Statistic
	4 Simulation Studies
		4.1 Simulation Study I: Type-I-Error
		4.2 Simulation Study II: Power
	5 Discussion
	References
Item Response Theory Modeling with Response Times: Some Issues
	1 Introduction
	2 Studies on Within-Person Variability
		2.1 Study 1: Within-Person Modeling of the Abstract Reasoning Test
		2.2 Study 2: Within-Person Modeling of the Mathematical Achievement Test
	3 Discussion
	References
DIF Detection in a Response Time Measure: A Likelihood Ratio Test Method
	1 Context
	2 The Likelihood Ratio Test for DIF in Item Responses
	3 The Likelihood Ratio Test for DIF in Response Times
	4 Study 1: Performance of the Method
	5 Study 2: Time Limits
	6 Conclusion
	References
Revisiting the 1PL-AG Item Response Model: Bayesian Estimation and Application
	1 Introduction
	2 IRT Models for Dichotomous Response
	3 Estimation
	4 Results
		4.1 Simulation Study
		4.2 Application
	5 Final Comments
	Appendix: JAGS Code for 1PNAG IRT Model
	References
MAP Estimation Using a Possibly Misspecified Parameter Redundant Model
	1 Introduction
	2 MAP Estimation Theory for Parameter Redundant Models
		2.1 Assumptions and Definitions
			2.1.1 DGP and Modeling Assumptions
			2.1.2 MAP and ML Estimation Algorithms
			2.1.3 Theorem Assumptions and Notation
			2.1.4 Identifiability and Redundancy Definitions
		2.2 Theorems
			2.2.1 Parameter Redundancy and Identifiability
			2.2.2 MAP Estimate Asymptotic Distribution
	3 Simulation Study
		3.1 Methods
			3.1.1 Data Set, Model, and Estimation Algorithm
			3.1.2 Evaluation of Confidence Interval Estimation Methods
		3.2 Results and Discussion
	References
Global Validity of Assessments: Location and Currency Effects
	1 Background
	2 Study Design
		2.1 Data Collection
		2.2 Constructs
		2.3 Measurement Invariance Testing
	3 Results
		3.1 Currency
		3.2 Location
	4 Conclusion
	References
The Deconstruction of Measurement Invariance (and DIF)
	1 A Geometric Perspective on Measurement and Measurement Invariance
		1.1 Measurement
		1.2 Measurement Invariance
	2 A Taxonomy of Measurement Invariance and DIF
		2.1 Complete Overlap
		2.2 Complete Parallelism
		2.3 Embedded Dimensions without Overlap
		2.4 Partial Parallelism
		2.5 Neither Parallelism nor Overlap
		2.6 Singular Overlap
		2.7 Nonsingular Overlap
		2.8 Embeddedness
		2.9 General Remarks
	3 Conclusions
	References
Assessment of Misspecification in CDMs Using a Generalized Information Matrix Test
	1 Introduction
	2 Mathematical Theory
		2.1 Model Misspecification
		2.2 Cognitive Diagnostic Model Specification
			2.2.1 Data Set
			2.2.2 Evidence Model
			2.2.3 Proficiency Model
		2.3 Model Parameter Estimation
		2.4 Information Matrix Test Methods for Detection of Model Misspecification
			2.4.1 Determinant Generalized Information Matrix Test Statistical Theory
	3 Simulation Study
		3.1 Data set
		3.2 Methods
		3.3 Results and Discussion
	References
The Impact of Generating Model on Preknowledge Detection in CAT
	1 Introduction
	2 Method
		2.1 Modeling Item Scores
		2.2 Modeling Item Response Times
		2.3 Model Comparison
	3 Simulation Study
		3.1 Design and Analysis
		3.2 Results
	4 Discussion
	References
Empirical Comparisons Among Models in Detecting Extreme Response Style
	1 Introduction
	2 Methods
	3 Results
	4 Discussion
	References
Index