<b>PReMiuM</b>: An<i>R</i>Package for Profile Regression Mixture Models Using Dirichlet Processes

Liverani, Silvia; Hastie, David I.; Azizi, Lamiae; Papathomas, Michail; Richardson, Sylvia

doi:10.18637/jss.v064.i07

Cited by 118 publications

(146 citation statements)

References 28 publications

Supporting

Mentioning

146

Contrasting

Order By: Relevance

“…To derive a partition of the data, Molitor et al (2010) cluster the data using the pairwise association matrix as a distance measure which is obtained by aggregating over all partitions obtained during MCMC sampling, using partitioning around medoids. The optimal number of clusters is determined by maximizing an associated clustering score; see also Liverani et al (2013).…”

Section: Bayesian Nonparametric Methodsmentioning

confidence: 99%

Model Selection for Mixture Models – Perspectives and Strategies

Celeux¹,

Frühwirth‐Schnatter²,

Robert³

2019

Handbook of Mixture Analysis

View full text Add to dashboard Cite

show abstract

Section: Bayesian Nonparametric Methodsmentioning

confidence: 99%

Model Selection for Mixture Models – Perspectives and Strategies

Celeux¹,

Frühwirth‐Schnatter²,

Robert³

2019

Handbook of Mixture Analysis

View full text Add to dashboard Cite

show abstract

“…and I.J.B. using the freely available package PreMiuM 25, 26 for R statistical software 27 and SAS version 9.3 (SAS Institute, Cary, NC, USA).…”

Section: Methodsmentioning

confidence: 99%

Blood Pressure Differences Associated With Optimal Macronutrient Intake Trial for Heart Health (OMNIHEART)–Like Diet Compared With a Typical American Diet

et al. 2014

Self Cite

View full text Add to dashboard Cite

The DASH-Sodium trial demonstrated beneficial effects on blood pressure (BP) of the DASH diet with lower sodium intake compared to typical American diet. The subsequent OMNIHEART trial reported additional BP benefits from replacing carbohydrate in the DASH diet with either protein or monounsaturated fats. The primary aim of this study is to assess possible BP benefits of an OMNIHEART-like diet in free-living Americans using cross-sectional U.S. population data of the INTERMAP Study. INTERMAP data include four 24-h dietary recalls, two timed 24-h urine collections, eight BP readings for 2,195 individuals ages 40-59 from eight US INTERMAP population samples. Analyses are conducted using two approaches: 1. Regression of BP on a linear OMNIHEART nutrient score calculated for each individual, and 2. A Bayesian approach comparing estimated BP levels of an OMNIHEART-like nutrient profile with a typical American nutrient profile. After adjustment for potential confounders, an OMNIHEART score higher by one point was associated with systolic/diastolic BP differences of −1.0/−0.5 mmHg (both P<0.001). Mean systolic/diastolic BPs were 111.3/68.4 and 115.2/70.6 mmHg for Bayesian OMNIHEART and Control profiles respectively, after controlling for possible confounders, with BP differences of −3.9/−2.2 mmHg, Pr(difference ≤ 0) ≈ 0.98/0.96. Findings were comparable for men and women, for non-hypertensive participants, and with adjustment for antihypertensive treatment. Our findings from data on US population samples indicate broad generalizability of OMNIHEART results beyond the trial setting, and support recommendations for an OMNIHEART-style diet for prevention/control of population-wide adverse BP levels.

show abstract

“…Regarding random parameter models, mlogit (Croissant 2013a), RSGHB (Dumont and Keller 2015) and gmnl (Sarrias and Daziano 2015) allow estimating models with individual heterogeneity in the context of multinomial logit model in a very similar fashion to Rchoice. Other packages such as FlexMix (Grün and Leisch 2008) and PReMiuM (Liverani et al 2015) allow to estimate models with individual heterogeneity by assuming that g(θ) is discrete or a mixture of distributions. All these packages available in R cover almost all possibilities of estimating discrete choice models with random parameters or individual heterogeneity.…”

Section: Introductionmentioning

confidence: 99%

Discrete Choice Models with Random Parameters in R: The Rchoice Package

Sarrias¹

2016

J. Stat. Soft.

View full text Add to dashboard Cite

Rchoice is a package in R for estimating models with individual heterogeneity for both cross-sectional and panel (longitudinal) data. In particular, the package allows binary, ordinal and count response, as well as continuous and discrete covariates. Individual heterogeneity is modeled by allowing the parameter associated with each observed variable (e.g., its coefficient) to vary randomly across individuals according to some pre-specified distribution. Simulated maximum likelihood method is implemented for the estimation of the moments of the distributions. In addition, functions for plotting the conditional individual-specific coefficients and their confidence interval are provided. This article is a general description of Rchoice and all functionalities are illustrated using real databases.

show abstract

PReMiuM: AnRPackage for Profile Regression Mixture Models Using Dirichlet Processes

Cited by 118 publications

References 28 publications

Model Selection for Mixture Models – Perspectives and Strategies

Model Selection for Mixture Models – Perspectives and Strategies

Blood Pressure Differences Associated With Optimal Macronutrient Intake Trial for Heart Health (OMNIHEART)–Like Diet Compared With a Typical American Diet

Discrete Choice Models with Random Parameters in R: The Rchoice Package

Contact Info

Product

Resources

About