Maximum Likelihood Estimation of Two-Level Latent Variable Models with Mixed Continuous and Polytomous Data
BiometricsPublished 1 September 2001
Sik‐Yum Lee, Jian-Qing Shi
Citations60
SJR quartileQ1
SJR score1.26
SNIP1.20
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A maximum likelihood approach is proposed for analyzing a latent variable model with two‐level data set concerning the development and preliminary findings from an AIDS preventative intervention for Filipina commercial sex workers where the relationship between some latent quantities is investigated.
Abstract
Two-level data with hierarchical structure and mixed continuous and polytomous data are very common in biomedical research. In this article, we propose a maximum likelihood approach for analyzing a latent variable model with these data. The maximum likelihood estimates are obtained by a Monte Carlo EM algorithm that involves the Gibbs sampler for approximating the E-step and the M-step and the bridge sampling for monitoring the convergence. The approach is illustrated by a two-level data set concerning the development and preliminary findings from an AIDS preventative intervention for Filipina commercial sex workers where the relationship between some latent quantities is investigated.
Keywords
Computer ScienceMathematics
Journal of the Royal Statistical Society Series B (Statistical Methodology)Maximum Likelihood from Incomplete Data Via the <i>EM</i> Algorithm
49,657 Citations1977A. P. Dempster, N. M. Laird +1 more
IEEE Transactions on Pattern Analysis and Machine IntelligenceStochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
17,980 Citations1984Stuart Geman, Donald Geman
The analogy between images and statistical mechanics systems is made and the analogous operation under the posterior distribution yields the maximum a posteriori (MAP) estimate of the image given the degraded observations, creating a highly parallel ``relaxation'' algorithm for MAP estimation.
Social ForcesTesting Structural Equation Models.
8,255 Citations1995Clifford C. Clogg, Kenneth A. Bollen +1 more
Medical Entomology and ZoologyLisrel 8: Structural Equation Modeling With the Simplis Command Language
7,764 Citations1993Karl G. Jöreskog, Dag Sörbom
The SIMPLIS language shifts the focus away from the technical question "How to do it", so that researchers can concentrate on the question, "What does it all mean?"
Journal of the Royal Statistical Society Series B (Statistical Methodology)Finding the Observed Information Matrix When Using the <i>EM</i> Algorithm
2,243 Citations1982Thomas A. Louis
A procedure is derived for extracting the observed information matrix when the EM algorithm is used to find maximum likelihood estimates in incomplete data problems and a method useful in speeding up the convergence of the EM algorithms is developed.
PsychometrikaA General Structural Equation Model with Dichotomous, Ordered Categorical, and Continuous Latent Variable Indicators
2,028 Citations1984Bengt Muthén
Journal of the American Statistical AssociationA Monte Carlo Implementation of the EM Algorithm and the Poor Man's Data Augmentation Algorithms
1,135 Citations1990Wei Gao, Martin A. Tanner
Two modifications to the MCEM algorithm (the poor man's data augmentation algorithms), which allow for the calculation of the entire posterior, are presented and serve as diagnostics for the validity of the posterior distribution.
Journal of the American Statistical AssociationA Monte Carlo Implementation of the EM Algorithm and the Poor Man's Data Augmentation Algorithms
913 Citations1990Greg C. G. Wei, Martin A. Tanner
BiometrikaMultilevel mixed linear model analysis using iterative generalized least squares
777 Citations1986Harvey Goldstein
Latent Variable Models
619 Citations2004John C. Loehlin
Journal of the Royal Statistical Society Series B (Statistical Methodology)Maximizing Generalized Linear Mixed Model Likelihoods With an Automated Monte Carlo EM Algorithm
557 Citations1999James G. Booth, James P. Hobert
Two new implementations of the EM algorithm are proposed for maximum likelihood fitting of generalized linear mixed models using random sampling to construct Monte Carlo approximations at the E‐step, and can be considerably more efficient than those based on Markov chain Monte Carlo algorithms.
Simulation of truncated normal variables
485 Citations1995Christian P. Robert
Statistics and ComputingSimulation of truncated normal variables
338 Citations1995Christian P. Robert
Journal of the Royal Statistical Society Series B (Statistical Methodology)Latent Variable Models for Mixed Discrete and Continuous Outcomes
316 Citations1997Mary D. Sammel, Louise Ryan +1 more
A latent variable model for mixed discrete and continuous outcomes for birth defects data is proposed and an EM algorithm is proposed for parameter estimation and estimates of the latent variables are produced as a by‐product of the analysis.
British Journal of Mathematical and Statistical PsychologyA two‐stage estimation of structural equation models with continuous and polytomous variables
248 Citations1995Sik‐Yum Lee, Wai‐Yin Poon +1 more
A partition maximum likelihood approach is used to obtain the first stage estimates of the thresholds and the polyserial and polychoric correlations in the underlying correlation matrix, and a generalized least squares approach is employed to estimate the structural parameters in the correlation structure.
Journal of the American Statistical AssociationBivariate Latent Variable Models for Clustered Discrete and Continuous Outcomes
242 Citations1992Paul J. Catalano, Louise Ryan
Journal of the American Statistical AssociationFitting Full-Information Item Factor Models and an Empirical Investigation of Bridge Sampling
152 Citations1996Xiao‐Li Meng, Stephen Schilling
Two ways of implementing Monte Carlo Expectation Maximization algorithm to fit a FIIF model are illustrated, using the Gibbs sampler to carry out the computation for the E steps and how to use bridge sampling to simulate the likelihood ratios for monitoring the convergence of a Monte Carlo EM.
British Journal of Mathematical and Statistical PsychologyBalanced versus unbalanced designs for linear structural relations in two‐level data
141 Citations1989Roderick P. McDonald, Harvey Goldstein
BiometrikaRobustness of statistical inference in factor analysis and related models
123 Citations1987Michael W. Browne
PsychometrikaFactor Analysis for Clustered Observations
121 Citations1992Nicholas T. Longford, Bengt Muthén
Journal of the Royal Statistical Society Series B (Statistical Methodology)Latent Variable Models with Mixed Continuous and Polytomous Data
109 Citations2000Jian-Qing Shi, Sik‐Yum Lee
A maximum likelihood approach is proposed for analyzing a latent variable model with two-level data set concerning the development and preliminary findings from an AIDS preventative intervention for Filipina commercial sex workers where the relationship between some latent quantities is investigated.
BiometricsLatent Variable Models with Fixed Effects
94 Citations1996Mary D. Sammel, Louise Ryan
The proposed model is applied to birth defects data, where continuous data on the size of infants who were exposed to anticonvulsant medications in utero are compared to controls.
British Journal of Mathematical and Statistical PsychologyBayesian sampling‐based approach for factor analysis models with continuous and polytomous data
94 Citations1998Jian‐Qing Shi, Sik‐Yum Lee
PsychometrikaEM and Beyond
92 Citations1991Donald B. Rubin
The basic theme of the EM algorithm, to repeatedly use complete-data methods to solve incomplete data problems, is also a theme of several more recent statistical techniques that combine simulation techniques with complete- data methods to attack problems that are difficult or impossible for EM.
AIDS CareThe effects of establishment practices, knowledge and attitudes on condom use among Filipina sex workers
72 Citations1998Donald E. Morisky, Teodora V. Tiglao +5 more
The preliminary findings point to the importance of an intervention that stresses changes in establishment policies and expectations as a means of reducing risk behaviours associated with HIV/STD transmission.
Journal of the American Statistical AssociationLatent Variable Models for Teratogenesis Using Multiple Binary Outcomes
59 Citations1997Julie Legler, Louise Ryan +1 more
A latent variable model is developed to characterize exposure effects on multiple binary outcomes in the study of birth defects and provides a measure of the “severity” of each child's condition.
ANALYSIS OF TWO-LEVEL STRUCTURAL EQUATION MODELS VIA EM TYPE ALGORITHMS
48 Citations1998Sik‐Yum Lee, Wai‐Yin Poon
The maximum likelihood estimation of a general two-level structural equation model with an unbalanced design is formulated as a missing data problem by treating the latent random vectors at the group level as hypo- thetical missing data.
PsychometrikaAn Estimating Equations Approach for the LISCOMP Model
39 Citations1998Beth A. Reboussin, Kung‐Yee Liang