Adaptive Monte Carlo for Bayesian Variable Selection in Regression Models

Lamnisos, Demetris; Griffin, Jim E.; Steel, Mark F. J.

doi:10.1080/10618600.2012.694756

Cited by 27 publications

(42 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each metric from IMUs or hdEMG, the algorithm built any possible subset of the 281 structural features. For each subset, a Monte Carlo simulation algorithm was applied to find the optimum coefficients of the linear model (Lamnisos, Griffin, & Steel, ). Variables were added to the model under a criterion of prevention of overfitting, that is, assessing each new model update on a subset of the total sample.…”

Section: Methodsmentioning

confidence: 99%

Tremor severity in Parkinson's disease and cortical changes of areas controlling movement sequencing: A preliminary study

Benito‐León

Serrano

Louis

et al. 2018

J of Neuroscience Research

View full text Add to dashboard Cite

There remains much to learn about the changes in cortical anatomy that are associated with tremor severity in Parkinson's disease (PD). For this reason, we used a combination of structural neuroimaging to measure cortical thickness and neurophysiological studies to analyze whether PD tremor was associated with cortex integrity. Magnetic resonance imaging and neurophysiological assessment were performed in 13 nondemented PD patients (9 women, 69.2%) with a clearly tremor-dominant phenotype. Cortical reconstruction and volumetric segmentation were performed with the Freesurfer image analysis software. Assessment of tremor was performed by means of high-density surface electromyography (hdEMG) and inertial measurement units (IMUs). Individual motor unit discharge patterns were identified from surface hdEMG and tremor metrics quantifying motor unit synchronization from IMUs. Increased motor unit synchronization (i.e., more severe tremor) was associated with cortical changes (i.e., atrophy) in wide-spread cortical areas, including caudal middle frontal regions bilaterally (dorsal premotor cortices), left inferior parietal lobe (posterior parietal cortex), left lateral orbitofrontal cortex, cingulate cortex bilaterally, left posterior and transverse temporal cortex, and left occipital lobe, as well as reduced left middle temporal volume. Given that the majority of these areas are involved in controlling movement sequencing, our results support Albert's classic hypothesis that PD tremor may be the result of an involuntary activation of a program of motor behavior used in the genesis of rapid voluntary alternating movements.

show abstract

Section: Methodsmentioning

confidence: 99%

Tremor severity in Parkinson's disease and cortical changes of areas controlling movement sequencing: A preliminary study

Benito‐León

Serrano

Louis

et al. 2018

J of Neuroscience Research

View full text Add to dashboard Cite

show abstract

“…Unlike model selection methods, it also does not assign binary zero-one weights to the OLS coefficients. Other approaches that apply flexible weighting to individual predictors include bagging (Breiman, 1996) which applies differential shrinkage weights to each coefficient, the adaptive Lasso (Zou, 2006) which applies variable-specific weights to the individual predictors in a datadependent adaptive manner, the Elastic Net (Zou and Hastie, 2005;Zou and Zhang, 2009) which introduces extra parameters to control the penalty for inclusion of additional variables, and Bayesian methods such as adaptive Monte Carlo (Lamnisos et al, 2012).…”

Section: Introductionmentioning

confidence: 99%

Complete subset regressions

Elliott¹,

Gargano²,

Timmermann³

2013

Journal of Econometrics

198

132

View full text Add to dashboard Cite

a b s t r a c tThis paper proposes a new method for combining forecasts based on complete subset regressions. For a given set of potential predictor variables we combine forecasts from all possible linear regression models that keep the number of predictors fixed. We explore how the choice of model complexity, as measured by the number of included predictor variables, can be used to trade off the bias and variance of the forecast errors, generating a setup akin to the efficient frontier known from modern portfolio theory. In an application to predictability of stock returns, we find that combinations of subset regressions can produce more accurate forecasts than conventional approaches based on equal-weighted forecasts (which fail to account for the dimensionality of the underlying models), combinations of univariate forecasts, or forecasts generated by methods such as bagging, ridge regression or Bayesian Model Averaging.

show abstract

“…Therefore, τ 1 and τ 2 are chosen to ensure that the acceptance rates for each move type are between 20% and 30%. Alternately, we could have used an adaptive MH algorithm, as in Lamnisos et al [37]. However, the standard MH algorithm that we specify has good convergence properties and is easy to implement.…”

Section: Bayesian Variable Selection For Paired Case-control Datamentioning

confidence: 99%

Bayesian Variable Selection Methods for Matched Case-Control Studies

Asafu‐Adjei

Mahlet

Coull

et al. 2017

The International Journal of Biostatistics

View full text Add to dashboard Cite

Matched case-control designs are currently used in many biomedical applications. To ensure high efficiency and statistical power in identifying features that best discriminate cases from controls, it is important to account for the use of matched designs. However, in the setting of high dimensional data, few variable selection methods account for matching. Bayesian approaches to variable selection have several advantages, including the fact that such approaches visit a wider range of model subsets. In this paper, we propose a variable selection method to account for case-control matching in a Bayesian context and apply it using simulation studies, a matched brain imaging study conducted at Massachusetts General Hospital, and a matched cardiovascular biomarker study conducted by the High Risk Plaque Initiative.

show abstract

Adaptive Monte Carlo for Bayesian Variable Selection in Regression Models

Cited by 27 publications

References 26 publications

Tremor severity in Parkinson's disease and cortical changes of areas controlling movement sequencing: A preliminary study

Tremor severity in Parkinson's disease and cortical changes of areas controlling movement sequencing: A preliminary study

Complete subset regressions

Bayesian Variable Selection Methods for Matched Case-Control Studies

Contact Info

Product

Resources

About