The choice of a model in the analysis of patient health care costs and utilization is critical for a clear understanding of the behavior and estimation of quantities like incremental costs or cost-effectiveness. In studying heath care claims related to pregnancy, it would not be surprising that a small portion of the women have costs associated with their care and treatment that might be extrem...

Variational inference is a scalable technique for approximate Bayesian inference. Deriving variational inference algorithms requires tedious model-specific calculations; this makes it di cult for non-experts to use. We propose an automatic variational inference algorithm, automatic di erentiation variational inference ( ); we implement it in Stan (code available), a probabilistic programming sy...

Results 69 RCTs reporting longitudinal QOL analyses were identified. 29 (42%) use an analysis to account for the nature of the missing data. Methods varied widely, eg pattern-mixture models, conditional linear models, QTWiST, joint longitudinal models, generalised estimating equations, selection models and Markov models. Fourteen papers used more than one method check the robustness of their re...

Modeling a collection of similar regression or classification tasks can be improved by making the tasks ‘learn from each other’. In machine learning, this subject is approached through ‘multitask learning’, where parallel tasks are modeled as multiple outputs of the same network. In multilevel analysis this is generally implemented through the mixed-effects linear model where a distinction is m...

In this paper we present a novel discriminative mixture model for statistical machine translation (SMT). We model the feature space with a log-linear combination of multiple mixture components. Each component contains a large set of features trained in a maximumentropy framework. All features within the same mixture component are tied and share the same mixture weights, where the mixture weight...

Abstract Mixture of linear experts (MoE) model is one the widespread statistical frameworks for modeling, classification, and clustering data. Built on normality assumption error terms mathematical computational convenience, classical MoE has two challenges: (1) it sensitive to atypical observations outliers, (2) might produce misleading inferential results censored The aim then resolve these c...

We present log-linear mixture models as a fully discriminative approach to object category recognition which can, analogously to kernelised models, represent non-linear decision boundaries. We show that this model is the discriminative counterpart to Gaussian mixtures and that either one can be transformed into the respective other. However, the proposed model is easier to extend toward fusing ...

tlemix implements a general framework for robustly fitting discrete mixtures of regression models in the R statistical computing environment. It implements the FAST-TLE algorithm and uses the R package FlexMix as a computational engine for fitting mixtures of general linear models (GLMs) and model-based clustering in R.

This material is posted here with permission of the IEEE. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by sending a blank email message to [email protected]. By choosing to view this doc...