Filters








25,538 Hits in 3.2 sec

Identifying latent clusters of variability in longitudinal data

Michael R. Elliott
2007 Biostatistics  
We develop a latent cluster model that relates underlying "clusters" of variability to baseline or outcome measures of interest.  ...  Means or other central tendency measures are by far the most common focus of statistical analyses.  ...  The random effects u i have been integrated out of the complete data model (see 2.5); hence, they are not required except when computingŷ i as in (2.4).  ... 
doi:10.1093/biostatistics/kxm003 pmid:17267391 fatcat:xragoso7ybd5fgvymefazach74

Explaining Preference Heterogeneity with Mixed Membership Modeling

Marc R. Dotson, Joachim BBschken, Greg M. Allenby
2017 Social Science Research Network  
Keywords Choice models, mixed membership models, hierarchical Bayes, grade of membership, preference heterogeneity 1  ...  This paper provides an important step in both a proper accounting for extremes in preference heterogeneity and a continued synthesis between marketing models and mixed membership models, which include  ...  This is accomplished by integrating a grade of membership model, part of the class of mixed membership models, with a choice model to estimate membership vectors for use in a hierarchical Bayesian random  ... 
doi:10.2139/ssrn.2758644 fatcat:ihwo3u5ok5fc5b2dlra4ilrorq

Comparing definitions of spatial relations for the analysis of geographic disparities in mortality within a Bayesian mixed-effects framework

Diego Fernando Rojas-Gualdrón
2017 Revista Brasileira de Epidemiologia  
Crude and adjusted Bayesian mixed effects regressions were performed for each definition of spatial relation.  ...  Model fit statistics, spatial autocorrelation of residuals and estimated mortality rates, geographic disparity measures, relative ratios and relative differences were compared.  ...  Despite these differences between models, the proportional reduction of the geographic disparity measures after adjustment was similar: 4% for MRR and 10% for IqRR.  ... 
doi:10.1590/1980-5497201700030011 pmid:29160440 fatcat:kp6sfpismnc2hnsbetmljxbdpy

On collapsed representation of hierarchical Completely Random Measures [article]

Gaurav Pandey, Ambedkar Dukkipati
2016 arXiv   pre-print
We use completely random measures~(CRM) and hierarchical CRM to define a prior for Poisson processes.  ...  The aim of the paper is to provide an exact approach for generating a Poisson process sampled from a hierarchical CRM, without having to instantiate the infinitely many atoms of the random measures.  ...  We hope that this will encourage the use of hierarchical random measures, other than HDP and BNBP, for mixed-membership modelling and will lead to further research into an understanding of the applicability  ... 
arXiv:1509.01817v2 fatcat:3vvofl4l4razfo2i3mxjdxs5xi

Analytic complexities associated with group therapy in substance abuse treatment research: Problems, recommendations, and future directions

Antonio A. Morgan-Lopez, William Fals-Stewart
2006 Experimental and clinical psychopharmacology  
as foundations for the development of more appropriate analytic methods for data from group therapy research (i.e., non-hierarchical data modeling, pattern mixture approaches) are also briefly described  ...  as fully hierarchical), and (c) provide recommendations for handling data from therapy groups using presently available methods In addition, promising data analytic frameworks that may eventually serve  ...  Hierarchical Modeling Approaches A more modern approach is to treat data from therapy groups as fully hierarchical and to analyze the data in readily available mixed model, multilevel, or structural equation  ... 
doi:10.1037/1064-1297.14.2.265 pmid:16756430 pmcid:PMC4631029 fatcat:77ya3kfms5hpvbff3hkpq6lfoe

Mixed effect frameworks in the analysis of longitudinal data

Anupama K R, Chandrashekara S
2014 Internet Journal of Rheumatology and Clinical Immunology  
Hierarchical or multilevel models Mixed model with hierarchical structure where the variables are measured at more than one level.  ...  If only intercept is modeled is known as random intercept model. If a slope is also modeled is known as random co-efficient model. Mixed effects Mixed models with both fixed and random effects.  ... 
doi:10.15305/ijrci/v2i1/82 fatcat:hzqk7d545reolbdyb3u2tbongi

Discussion of the community detection algorithm based on statistical inference

Liangxun Shuo, Bianfang Chai
2016 Perspectives in Science  
This paper aims to solve the model and parameters with the discussion from the algorithm characteristics of model, the analysis of each algorithm, solving the difficulties, problems and development direction  ...  Mixed Membership Degree Random Block Model The mixed membership degree model and the random block model are combined with (Airoldi et al., 2008; Airoldi and Fienberg, 2006) , and the model is established  ...  community detection model and mixed membership model.  ... 
doi:10.1016/j.pisc.2015.11.020 fatcat:llblhdotf5d35lasmgcbseb24e

Clustering [chapter]

Ron Wehrens
2020 Use R!  
agnes(wines.dist, method = "complete") Complete linkage is doing the best job for these data, according to this quality measure.  ...  Thus, the "EEI" model stands for diagonal covariance matrices (the "I") with equal volumes and shapes, and the "VEV" model indicates an ellipsoidal model with equal shapes for all clusters, but complete  ... 
doi:10.1007/978-3-662-62027-4_6 fatcat:2oocebrkzja25jxolwnvfve5by

Nonparametric Bayesian Negative Binomial Factor Analysis [article]

Mingyuan Zhou
2017 arXiv   pre-print
, which either completely ignore burstiness, or model only the burstiness of the covariates but not that of the factors.  ...  address this limitation, we construct negative binomial factor analysis (NBFA) to factorize the matrix under the negative binomial likelihood, and relate it to a Dirichlet-multinomial distribution based mixed-membership  ...  Acknowledgments The author would like to thank the editor-in-chief, editor, associate editor, and two anonymous referees for their invaluable comments and suggestions, which have helped improve the paper  ... 
arXiv:1604.07464v2 fatcat:6yw2yjvrwravpk3vs5ug7i5vtu

The Nonparametric Metadata Dependent Relational Model [article]

Dae Il Kim, Erik Sudderth
2012 arXiv   pre-print
The NMDR allows the entities associated with each node to have mixed membership in an unbounded collection of latent communities.  ...  We introduce the nonparametric metadata dependent relational (NMDR) model, a Bayesian nonparametric stochastic block model for network data.  ...  Edo Airoldi for helpful information regarding the Sampson monastery data. This research supported in part by IARPA under AFRL contract number FA8650-10-C-7059. D. Kim and M. C.  ... 
arXiv:1206.6414v1 fatcat:qvccrxlidzam5c3kty3imvp6lu

Multiple membership multiple classification (MMMC) models

William J Browne, Harvey Goldstein, Jon Rasbash
2001 Statistical Modelling  
Secondly, we consider multiple membership models where an observation does not belong simply to one member of a classification.  ...  Over the past two decades there has been an increase in the use of multilevel modelling techniques that account for nested data structures.  ...  Membership on this list does not imply agreement with the ideas expressed here, nor are any of these people responsible for any errors that may be present.  ... 
doi:10.1177/1471082x0100100202 fatcat:areoa23xcrgslecahyoyymlrny

Multiple membership multiple classification (MMMC) models

W.J. Browne, H. Goldstein, J. Rasbash
2001 Statistical Modelling  
Secondly, we consider multiple membership models where an observation does not belong simply to one member of a classification.  ...  Over the past two decades there has been an increase in the use of multilevel modelling techniques that account for nested data structures.  ...  Membership on this list does not imply agreement with the ideas expressed here, nor are any of these people responsible for any errors that may be present.  ... 
doi:10.1191/147108201128113 fatcat:ip3otaiebnfuhboob5it2xncuq

Nonparametric Bayesian Negative Binomial Factor Analysis

Mingyuan Zhou
2018 Bayesian Analysis  
, which either completely ignore burstiness, or model only the burstiness of the attributes but not that of the factors.  ...  address this limitation, we construct negative binomial factor analysis (NBFA) to factorize the matrix under the negative binomial likelihood, and relate it to a Dirichlet-multinomial distribution based mixed-membership  ...  Exploiting this property, for our models built on completely random measures, we construct a sampling procedure that adaptively truncates the total number of atoms in each iteration.  ... 
doi:10.1214/17-ba1070 fatcat:f7ccrykl7zhg7pnruhe2lsgczi

Page 136 of School Psychology Review Vol. 35, Issue 1 [page]

2006 School Psychology Review  
with hierarchical linear modeling (HLM; Bryk & Raudenbush, 1992).  ...  HLM is an example of a linear mixed model (LMM), which is particularly well suited to the type of problem addressed in this study (Fitzmaurice, Laird, & Ware, 2004). 136 LMMs are useful for analyzing longitudinal  ... 

Beta-Negative Binomial Process and Exchangeable Random Partitions for Mixed-Membership Modeling [article]

Mingyuan Zhou
2014 arXiv   pre-print
mixing, and state-of-the-art predictive performance.  ...  A fully collapsed Gibbs sampler is developed for the BNBP, leading to a novel nonparametric Bayesian topic model that is distinct from existing ones, with simple implementation, fast convergence, good  ...  A marginal sampler for σ-stable Poisson-Kigman mixture models (but not mixed-membership models) is proposed in [13] , encompassing a large class of random probability measures and their corresponding  ... 
arXiv:1410.7812v2 fatcat:35ux4gmxyzefzom5ogisx57meu
« Previous Showing results 1 — 15 out of 25,538 results