Bayesian multivariate growth curve latent class models for mixed outcomes.
ABSTRACT In many clinical studies, the disease of interest is multifaceted, and multiple outcomes are needed to adequately capture information about the characteristics of the disease or its severity. In the analysis of such diseases, it is often difficult to determine what constitutes improvement because of the multivariate nature of the outcome. Furthermore, when the disease of interest has an unknown etiology and/or is primarily a symptom-defined syndrome, there is potential for the disease population to have distinct subgroups. Identification of population subgroups is of interest as it may assist clinicians in providing appropriate treatment or in developing accurate prognoses. We propose multivariate growth curve latent class models that group subjects on the basis of multiple symptoms measured repeatedly over time. These groups or latent classes are defined by distinctive longitudinal profiles of a latent variable, which is used to summarize the multivariate outcomes at each point. The mean growth curve for the latent variable in each class defines the features of the class. We develop this model for any combination of continuous, binary, ordinal, or count outcomes within a Bayesian hierarchical framework. We use simulation studies to validate the estimation procedures. We apply our model to data from a randomized clinical trial evaluating the efficacy of Bacillus Calmette-Guerin in treating symptoms of interstitial cystitis where we are able to identify a class of subjects for whom treatment is effective. Copyright © 2012 John Wiley & Sons, Ltd.
- SourceAvailable from: ncbi.nlm.nih.gov[Show abstract] [Hide abstract]
ABSTRACT: In this paper, we propose a multivariate growth curve mixture model that groups subjects based on multiple symptoms measured repeatedly over time. Our model synthesizes features of two models. First, we follow Roy and Lin (2000) in relating the multiple symptoms at each time point to a single latent variable. Second, we use the growth mixture model of Muthén and Shedden (1999) to group subjects based on distinctive longitudinal profiles of this latent variable. The mean growth curve for the latent variable in each class defines that class's features. For example, a class of "responders" would have a decline in the latent symptom summary variable over time. A Bayesian approach to estimation is employed where the methods of Elliott et al (2005) are extended to simultaneously estimate the posterior distributions of the parameters from the latent variable and growth curve mixture portions of the model. We apply our model to data from a randomized clinical trial evaluating the efficacy of Bacillus Calmette-Guerin (BCG) in treating symptoms of Interstitial Cystitis. In contrast to conventional approaches using a single subjective Global Response Assessment, we use the multivariate symptom data to identify a class of subjects where treatment demonstrates effectiveness. Simulations are used to confirm identifiability results and evaluate the performance of our algorithm. The definitive version of this paper is available at onlinelibrary.wiley.com.Applied Statistics 09/2009; 58(4):505-524. · 1.42 Impact Factor
Article: Latent class model diagnosis.[Show abstract] [Hide abstract]
ABSTRACT: In many areas of medical research, such as psychiatry and gerontology, latent class variables are used to classify individuals into disease categories, often with the intention of hierarchical modeling. Problems arise when it is not clear how many disease classes are appropriate, creating a need for model selection and diagnostic techniques. Previous work has shown that the Pearson chi 2 statistic and the log-likelihood ratio G2 statistic are not valid test statistics for evaluating latent class models. Other methods, such as information criteria, provide decision rules without providing explicit information about where discrepancies occur between a model and the data. Identifiability issues further complicate these problems. This paper develops procedures for assessing Markov chain Monte Carlo convergence and model diagnosis and for selecting the number of categories for the latent variable based on evidence in the data using Markov chain Monte Carlo techniques. Simulations and a psychiatric example are presented to demonstrate the effective use of these methods.Biometrics 01/2001; 56(4):1055-67. · 1.52 Impact Factor
- [Show abstract] [Hide abstract]
ABSTRACT: A psychometric analysis of the University of Wisconsin Interstitial Cystitis Scale was conducted on 30 females previously enrolled in a phase II double-blind randomized controlled trial evaluating the efficacy of six weekly intravesical instillations of TICE BCG. The analyses were to: (1) evaluate the adequacy of the seven individual IC component items for measuring the range of patient responses; (2) verify the 2-factor (IC versus reference) construct of the scale; (3) evaluate the internal consistency and reliability of the IC items; (4) better define the scale's applicability and limitations; and (5) if possible, make recommendations for improvements in the scale. Standard psychometric analyses were used to perform the evaluation, and included descriptive analysis of individual items, computing of item-total correlations and Cronbach's internal consistency measures, and the application of factor and Rasch analyses. The original 7-item IC scale was found to have ceiling effects that could limit its use in detecting small therapeutic differences. It was also found that the Pelvic item originally assigned to the reference set of items of the scale should be included as an IC item when used in a comparable IC population. After including this item into the IC scale Cronbach's alpha was 0.84, compared with 0.82. The UW-IC Scale has psychometric properties similar to other measurement instruments used in clinical research, and appears worthy of further study in well-characterized IC populations. The reference items suggest that IC patients do not indiscriminately report high values for generalized body complaints, but do so on bladder related symptoms as recorded by the IC items of the scale. Although the scale has limitations it appears applicable for use in future IC intervention clinical trials.The Journal of Urology 04/1998; 159(3):1085-90. · 3.75 Impact Factor