Longitudinal Mixed Membership Trajectory Models for Disability Survey Data.

@article{ManriqueVallier2013LongitudinalMM,
  title={Longitudinal Mixed Membership Trajectory Models for Disability Survey Data.},
  author={Daniel Manrique-Vallier},
  journal={The annals of applied statistics},
  year={2013},
  volume={8 4},
  pages={
          2268-2291
        }
}
We develop new methods for analyzing discrete multivariate longitudinal data and apply them to functional disability data on U.S. elderly population from the National Long Term Care Survey (NLTCS), 1982-2004. Our models build on a mixed membership framework, in which individuals are allowed multiple membership on a set of extreme profiles characterized by time-dependent trajectories of progression into disability. We also develop an extension that allows us to incorporate birth-cohort effects… 

Figures and Tables from this paper

Mixed membership trajectory models of cognitive impairment in the multicenter AIDS cohort study

These results provide new insight into the natural history of cognitive dysfunction in HIV disease and provide evidence for a potential difference in the pathophysiology of the development of cognitive impairment based on trajectories to impairment.

Using Longitudinal Complex Survey Data

Common features of longitudinal surveys are complex sampling designs, which must be maintained and extended over time; measurement errors, including memory errors; panel conditioning or

Personalized predictive modeling for patients with Alzheimer’s disease using an extension of Sullivan’s life table model

The SLT/L-GoM model yields accurate maximum likelihood estimates of TLE, DFLE, and DLE for patients with AD; it provides a realistic, comprehensive modeling framework for endpoint and resource use/cost calculations.

Editorial Perspective: Longitudinal research in autism - introducing the concept of 'chronogeneity'.

The case is built for the potential utility of the concept of 'chronogeneity' and it is argued that a refined approach to the longitudinal investigation of autism (and other neurodevelopmental disorders) may move us closer to more precise and adaptive models of care for the children and youth affected by these disorders.

Modeling Social Networks as Mediators: A Mixed Membership Stochastic Blockmodel for Mediation

  • T. Sweet
  • Computer Science
    Journal of Educational and Behavioral Statistics
  • 2018
A new network model for mediation is introduced in which a social network model is embedded into a mediation model and both models are estimated simultaneously, applicable for interventions that affect subgroup structure.

Modelling the Covariance Structure in Marginal Multivariate Count Models: Hunting in Bioko Island

The main goal of this article is to present a flexible statistical modelling framework to deal with multivariate count data along with longitudinal and repeated measures structures. The covariance

Modelling the Covariance Structure in Marginal Multivariate Count Models: Hunting in Bioko Island

The main goal of this article is to present a flexible statistical modelling framework to deal with multivariate count data along with longitudinal and repeated measures structures. The covariance

Dimension-Grouped Mixed Membership Models for Multivariate Categorical Data

This article proposes a new class of Dimension-Grouped MMMs (Gro-M3s) for multivariate categorical data, which improve parsimony and interpretability and derives transparent identifiability conditions for both the unknown grouping structure and model parameters in general settings.

In the psychological literature, the investigation of the relationship between psychoses

Psychiatric studies of suicide provide fundamental insights on the evo6 lution of severe psychopathologies, and contribute to the development of 7 early treatment interventions. Our focus is on

References

SHOWING 1-10 OF 42 REFERENCES

DESCRIBING DISABILITY THROUGH INDIVIDUAL-LEVEL MIXTURE MODELS FOR MULTIVARIATE BINARY DATA.

This work considers an extract of functional disability data from the National Long Term Care Survey (NLTCS) and attempts to develop disability profiles using variations of the Grade of Membership (GoM) model, proving the equivalence between individual-level and population-level mixture models.

Trajectories of Morbidity, Disability, and Mortality among the U.S. Elderly Population

Abstract This article employs a longitudinal form of the Grade of Membership (GoM) model to specify and estimate a multivariate model of the trajectories of morbidity, disability, and mortality among

Multivariate mixture models to describe longitudinal patterns of frailty in American seniors

Large, longitudinal, multivariate population surveys are increasingly common. Many analytic methods inspect changing rates of individual outcomes but ignore heterogeneous subpopulations that may

Longitudinal Data with Follow-up Truncated by Death: Match the Analysis Method to Research Aims.

It is demonstrated how these analysis approaches arise from factorizations of the distribution of longitudinal data and survival information, and which method of accommodating deaths is consistent with research aims, and use analysis methods accordingly.

Towards a Restructuring of the National Long Term Care Survey: A Longitudinal Perspective

Because by design the NLTCS does not unequivocally provide measurements of chronic disability but rather of some combinations of chronic and short-term disability episodes, this issue was addressed by providing suggestions for future longitudinal disability surveys.

Directly parameterized regression conditioning on being alive: analysis of longitudinal data truncated by deaths.

A taxonomy for accommodation of both dropout and death is developed, estimation for binary longitudinal data that applies selection weights to estimating equations with independence working correlation is described, and it is shown that naive use of standard likelihood-based longitudinal methods and generalized estimation equations with non-independence weights may lead to biased estimation of the partly conditional mean model.

Analyzing Criminal Trajectory Profiles: Bridging Multilevel and Group-based Approaches Using Growth Mixture Modeling

The main goals of this article are to contribute to the discussion about different modeling techniques for analyzing data from a life-course perspective and to provide a concrete step-by-step illustration of such an analysis and model checking.

Progressive versus catastrophic disability: a longitudinal view of the disablement process.

Tracking the development of disability provides new and important insights into the disability experience in older men and women that are potentially relevant in planning preventive, intervention, and long-term care strategies.

Analyzing developmental trajectories: A semiparametric, group-based approach

Agroup-based method for identifying distinctive groups of individual trajectories within the population and for profiling the characteristics of group members is demonstrated.

Grade of membership and latent structure models with application to disability survey data

This work examines a relatively new latent structure model, the Grade of Membership (GoM) model, integrating the GoM language and ideas with more standard statistical literature on latent variable models, and presents a general class of mixed membership models that unifies the latent structure of theGoM model and two other mixed Membership models that recently appeared in the genetics and the machine learning literatures.