Model selection and model averaging for analysis of truncated and censored data with measurement error

This paper studies a discriminant problem of location-scale family in case of prediction from type II censored samples. Three model selection approaches and two types of predictors are, respectively, proposed to predict the future order statistics from censored data when the best underlying distribution is not clear with several candidates. Two members in the location-scale family, the normal distribution and smallest extreme value distribution, are used as candidates to illustrate the best model competition for the underlying distribution via using the proposed prediction methods. The performance of correct and incorrect selections under correct specification and misspecification is evaluated via using Monte Carlo simulations. Simulation results show that model misspecification has impact on the prediction precision and the proposed three model selection approaches perform well when more than one candidate distributions are competing for the best underlying distribution. Finally, the proposed approaches are applied to three data sets.

Download Full-text

Characterizing the effects of sex, APOE ɛ4, and literacy on mid-life cognitive trajectories: Application of Information-Theoretic model-averaging and multi-model inference techniques to the Wisconsin Registry for Alzheimer’s Prevention Study

10.1101/229237 ◽

2017 ◽

Author(s):

Rebecca L. Koscik ◽

Derek L. Norton ◽

Samantha L. Allison ◽

Erin M. Jonaitis ◽

Lindsay R. Clark ◽

...

Keyword(s):

Model Selection ◽

Cognitive Decline ◽

Model Averaging ◽

Parameter Estimates ◽

Theoretic Model ◽

Traditional Model ◽

Test Model ◽

Prevention Study ◽

Information Theoretic ◽

Modifiable Factors

ObjectiveIn this paper we apply Information-Theoretic (IT) model averaging to characterize a set of complex interactions in a longitudinal study on cognitive decline. Prior research has identified numerous genetic (including sex), education, health and lifestyle factors that predict cognitive decline. Traditional model selection approaches (e.g., backward or stepwise selection) attempt to find models that best fit the observed data; these techniques risk interpretations that only the selected predictors are important. In reality, several models may fit similarly well but result in different conclusions (e.g., about size and significance of parameter estimates); inference from traditional model selection approaches can lead to overly confident conclusions.MethodHere we use longitudinal cognitive data from ~1550 late-middle aged adults the Wisconsin Registry for Alzheimer’s Prevention study to examine the effects of sex, Apolipoprotein E (APOE) ɛ4 allele (non-modifiable factors), and literacy achievement (modifiable) on cognitive decline. For each outcome, we applied IT model averaging to a model set with combinations of interactions among sex, APOE, literacy, and age.ResultsFor a list-learning test, model-averaged results showed better performance for women vs men, with faster decline among men; increased literacy was associated with better performance, particularly among men. APOE had less of an effect on cognitive performance in this age range (~40-70).ConclusionsThese results illustrate the utility of the IT approach and point to literacy as a potential modifier of decline. Whether the protective effect of literacy is due to educational attainment or intrinsic verbal intellectual ability is the topic of ongoing work.

Download Full-text

Bayesian Model Averaging to Account for Model Uncertainty in Estimates of a Vaccine's Effectiveness

10.1101/2021.05.12.21257126 ◽

2021 ◽

Author(s):

Carlos R Oliveira ◽

Eugene D Shapiro ◽

Daniel M Weinberger

Keyword(s):

Model Selection ◽

Model Uncertainty ◽

Bayesian Model ◽

Bayesian Model Averaging ◽

Model Averaging ◽

Selection Methods ◽

Final Model ◽

Negative Case ◽

Confounder Selection ◽

Control Study

Vaccine effectiveness (VE) studies are often conducted after the introduction of new vaccines to ensure they provide protection in real-world settings. Although susceptible to confounding, the test-negative case-control study design is the most efficient method to assess VE post-licensure. Control of confounding is often needed during the analyses, which is most efficiently done through multivariable modeling. When a large number of potential confounders are being considered, it can be challenging to know which variables need to be included in the final model. This paper highlights the importance of considering model uncertainty by re-analyzing a Lyme VE study using several confounder selection methods. We propose an intuitive Bayesian Model Averaging (BMA) framework for this task and compare the performance of BMA to that of traditional single-best-model-selection methods. We demonstrate how BMA can be advantageous in situations when there is uncertainty about model selection by systematically considering alternative models and increasing transparency.

Download Full-text

How to improve parameter estimates in GLM-based fMRI data analysis: cross-validated Bayesian model averaging

10.1101/095778 ◽

2016 ◽

Cited By ~ 2

Author(s):

Joram Soch ◽

Achim Pascal Meyer ◽

John-Dylan Haynes ◽

Carsten Allefeld

Keyword(s):

Data Analysis ◽

Model Selection ◽

Bayesian Model ◽

Bayesian Model Averaging ◽

Model Averaging ◽

Bayesian Model Selection ◽

Fmri Data ◽

Parameter Estimates ◽

Fmri Data Analysis ◽

Level Analysis

AbstractIn functional magnetic resonance imaging (fMRI), model quality of general linear models (GLMs) for first-level analysis is rarely assessed. In recent work (Soch et al., 2016: “How to avoid mismodelling in GLM-based fMRI data analysis: cross-validated Bayesian model selection”, NeuroImage, vol. 141, pp. 469-489; DOI: 10.1016/j. neuroimage.2016.07.047), we have introduced cross-validated Bayesian model selection (cvBMS) to infer the best model for a group of subjects and use it to guide second-level analysis. While this is the optimal approach given that the same GLM has to be used for all subjects, there is a much more efficient procedure when model selection only addresses nuisance variables and regressors of interest are included in all candidate models. In this work, we propose cross-validated Bayesian model averaging (cvBMA) to improve parameter estimates for these regressors of interest by combining information from all models using their posterior probabilities. This is particularly useful as different models can lead to different conclusions regarding experimental effects and the most complex model is not necessarily the best choice. We find that cvBMS can prevent not detecting established effects and that cvBMA can be more sensitive to experimental effects than just using even the best model in each subject or the model which is best in a group of subjects.

Download Full-text

How to improve allometric equations to estimate forest biomass stocks? Some hints from a central African forest

Canadian Journal of Forest Research ◽

10.1139/cjfr-2013-0520 ◽

2014 ◽

Vol 44 (7) ◽

pp. 685-691 ◽

Cited By ~ 10

Author(s):

Quentin Moundounga Mavouroulou ◽

Alfred Ngomanda ◽

Nestor Laurier Engone Obiang ◽

Judicaël Lebamba ◽

Hugues Gomat ◽

...

Keyword(s):

Measurement Error ◽

Bayesian Model Averaging ◽

Sampling Error ◽

Forest Biomass ◽

Model Averaging ◽

Allometric Equation ◽

Allometric Equations ◽

Data Set ◽

Equation Error ◽

Source Of Error

Predicting the biomass of a forest stand using forest inventory data and allometric equations involves a chain of propagation of errors going from the sampling error to the tree measurement error. Using a biomass data set of 101 trees in a tropical rain forest in Gabon, we compared two sources of error: the error due to the choice of allometric equation, assessed using Bayesian model averaging, and the biomass measurement error when tree biomass is calculated from tree volume rather than directly weighed. Differences between allometric equations resulted in a between-equation error of about 0.245 for log-transformed biomass compared with a residual within-equation error of 0.297. Because the residual error is leveled off when randomly accumulating trees whereas the between-equation error is incompressible, the latter turned out to be a major source of error at the scale of a 1 ha plot. Measuring volumes rather than masses resulted in an error of 0.241 for log-transformed biomass and an average overestimation of the biomass by 19%. These results confirmed the choice of the allometric equation as a major source of error but unexpectedly showed that measuring volumes could seriously bias biomass estimates.

Download Full-text