7. Four Useful Finite Mixture Models for Regression Analyses of Panel Data with a Categorical Dependent Variable

Published on Dec 1, 2008in Sociological Methodology2.158
· DOI :10.1111/J.1467-9531.2008.00196.X
Kazuo Yamaguchi19
Estimated H-index: 19
(U of C: University of Chicago)
Sources
Abstract
This paper describes and contrasts two useful ways to employ a latent class variable as a mixture variable in regression analyses of panel data with a categorical dependent variable. One way is to model unobserved heterogeneity in the trajectory, or change in the distribution, of the dependent variable. Two models that accomplish this are the latent trajectory model and latent growth curve model for a categorical dependent variable having ordered categories. Each latent class here represents a distinct trajectory of the dependent variable. The latent trajectory model introduces covariate effects on the composition of latent classes, while the latent growth curve model introduces covariate effects on both the “intercept” and the “slope” of growth in logit, which may vary among latent classes.The other useful way is to model unobserved heterogeneity in the state dependence of the dependent variable. Two models that accomplish this are introduced for a simultaneous analysis of response probability and respon...
📖 Papers frequently viewed together
2006
1 Author (Li Qin)
References30
Newest
#1Chin-Shang LiH-Index: 58
#2Jeremy M. G. Taylor (UM: University of Michigan)H-Index: 95
A cure model is a useful approach for analysing failure time data in which some subjects could eventually experience, and others never experience, the event of interest. A cure model has two components: incidence which indicates whether the event could eventually occur and latency which denotes when the event will occur given the subject is susceptible to the event. In this paper, we propose a semi-parametric cure model in which covariates can affect both the incidence and the latency. A logisti...
Source
#2Donald B. RubinH-Index: 130
Source
#1Kazuo YamaguchiH-Index: 4
#2Denise B. KandelH-Index: 1
Source
#1Bengt MuthénH-Index: 92
Source
#1Kenneth C. LandH-Index: 66
#2Daniel S. NaginH-Index: 106
Last. Patricia L. McCallH-Index: 24
view all 3 authors...
Previous methodological research has shown that hidden heterogeneity in hazard rate regression models—in the form of systematic differences between sample members in the risk or hazard of making a transition due to unobserved variables not accounted for by the measured covariates—can produce biased parameter estimates and erroneous inferences. However, few empirical applications of hazard regression do more than pay lip service to the complications of hidden heterogeneity. In part, this is d...
Source
This article describes the method and application of multinomial logit latent‐class regression models in sociological research. This group of models is the categorical analogue of latent‐variable regression for continuous latent variables such as those employed in LIS‐REL or LISCOMP; therefore, though never yet employed in sociological research, the potential usefulness of these models in such research is very high. These models are regression extensions of log‐linear latent‐class models with gr...
Source
#1Karen Bandeen-Roche (Johns Hopkins University)H-Index: 81
#2Diana L. Miglioretti (Johns Hopkins University)H-Index: 80
Last. Paul J. Rathouz (U of C: University of Chicago)H-Index: 65
view all 4 authors...
Abstract Quantifying human health and functioning poses significant challenges in many research areas. Commonly in the social and behavioral sciences and increasingly in epidemiologic research, multiple indicators are utilized as responses in lieu of an obvious single measure for an outcome of interest. In this article we study the concomitant latent class model for analyzing such multivariate categorical outcome data. We develop practical theory for reducing and identifying such models. We deta...
Source
#1Kenneth C. LandH-Index: 66
#2Patricia L. McCallH-Index: 24
Last. Daniel S. NaginH-Index: 106
view all 3 authors...
Specifications and moment properties of the univariate Poisson and negative binomial distributions are briefly reviewed and illustrated. Properties and limitations of the corresponding poisson and negative binomial (gamma mixtures of Poissons) regression models are described. It is shown how a misspecification of the mixing distribution of a mixed Poisson model to accommodate hidden heterogeneity ascribable to unobserved variables—although not affecting the consistency of maximum likelihood es...
Source
#1Clifford C. CloggH-Index: 34
#2Tamas RudastH-Index: 1
Last. Liwen XiH-Index: 1
view all 3 authors...
A new index of structure for the analysis and summary description of models for mobility tables and other kinds of crossclassifications is proposed. For a given model, this index measures model misfit (or lack of fit) as the minimum possible proportion of the population outside the specified model. It measures structure in relation to a given model or hypothesis. The framework that gives rise to this index consists of embedding a specified model (independence, quasi-independence,
Source
#1Daniel S. Nagin (CMU: Carnegie Mellon University)H-Index: 106
#2Kenneth C. Land (Duke University)H-Index: 66
This article addresses three issues that are central to the criminal career debate. First, is the life course of individual offending patterns marked by distinctive periods of quiescence? Second, at the level of the individual, do offending rates vary systematically with age? In particular, is the age-crime curve single peaked or flat? Third, are chronic offenders different from less active offenders? Do offenders themselves differ in systematic ways? Using a new approach to the analysis of indi...
Source
Cited By6
Newest
Life course perspectives focus on the variation in trajectories, generally to identify differences in variation dynamics and classify trajectories accordingly. Our goal here is to develop methods to gauge the discontinuity characteristics trajectories exhibit and demonstrate how these measures facilitate analyses aimed to evaluate, compare, aggregate, and classify behaviors based on the event discontinuity they manifest. We restrict ourselves here to binary event sequences, providing directions ...
Source
#1Miriam W. Boeri (KSU: Kennesaw State University)H-Index: 12
#2Thor Whalen (KSU: Kennesaw State University)H-Index: 2
Last. Ellen BallardH-Index: 1
view all 4 authors...
To better understand patterns of drug use trajectories over time, it is essential to have standard measures of change. Our goal here is to introduce measures we developed to quantify change in drug use behaviors. A secondary goal is to provide effective visualizations of these trajectories for applied use. We analyzed data from a sample of 92 older drug users (ages 45 to 65) to identify transition patterns in drug use trajectories across the life course. Data were col- lected for every year sinc...
Source
#1Anna Manzoni (Yale University)H-Index: 10
#2Jeroen K. Vermunt (Tilburg University)H-Index: 63
Last. Ruud Muffels (Tilburg University)H-Index: 28
view all 4 authors...
Event history data constitute a valuable source to analyze life courses, although the reliance of such data on autobiographical memory raises many concerns over their reliability. In this paper, we use Swedish survey data to investigate bias in retrospective reports of employment biographies, applying a novel model-based latent Markov method. A descriptive comparison of the biographies as reconstructed by the same respondents at two interviews carried out about 10 years apart reveals that career...
Source
#1Diana Worts (U of T: University of Toronto)H-Index: 13
#2Amanda Sacker (University of Essex)H-Index: 63
Last. Peggy McDonough (U of T: University of Toronto)H-Index: 21
view all 3 authors...
This paper addresses a key methodological challenge in the modeling of individual poverty dynamics—the influence of measurement error. Taking the US and Britain as case studies and building on recent research that uses latent Markov models to reduce bias, we examine how measurement error can affect a range of important poverty estimates. Our data are taken from the British Household Panel Survey and the US Panel Study of Income Dynamics, for working-aged adults over the period 1993–2003. For bot...
Source
#1Peggy McDonough (U of T: University of Toronto)H-Index: 21
#2Diana Worts (U of T: University of Toronto)H-Index: 13
Last. Amanda Sacker (University of Essex)H-Index: 63
view all 3 authors...
Drawing on theory and research on the fundamental causes of health, the life course, and the welfare state, we investigate social inequalities in dynamic self-rated health for working-aged Britons and Americans. We use data from the British Household Panel Survey and Panel Study of Income Dynamics (1990-2004) and a mixture latent Markov model to test a theoretical model of health as a discrete state that may remain stable or change over time. Our contributions are threefold. First, our finding o...
Source
#1Chad Westerland (UA: University of Arizona)H-Index: 7
COURSE OVERVIEW: We will cover a series of advanced methodological topics in this course. While the subject material in this course is varied, all of the topics we will cover are directly related to the ongoing research of the graduate students taking the course. We will usually spend 2-3 weeks covering each topic. For most of what we cover, the assigned readings will only cover an introduction to the subject. As we progress, I will highlight the necessary additional reading if you are applying ...
This website uses cookies.
We use cookies to improve your online experience. By continuing to use our website we assume you agree to the placement of these cookies.
To learn more, you can find in our Privacy Policy.