Model comparison for generalized linear models with dependent observations

Eguchi, Shoichi

doi:10.1016/j.ecosta.2017.04.003

Cited by 5 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because of this, there is greater flexibility between the mean of the variable of interest and the linear predictor η. The GLM is an extension of the linear regression models, as they have a linear structure and consists of three components ( Eguchi, 2017 ; Cordeiro and Andrade, 2009 Gracindo et al., 2011 ): random component represented by a set of independent values Y 1 , Y 2 , ..., Y n with distribution belonging to the exponential family; systematic component enters the model as the linear sum of the effects of the explanatory variables that is given by;

where

the model matrix,

the parameter vector and

T the linear predictor; link function (g) that makes the connection between the average of the observations and the systematic part.

…”

Section: Methodsmentioning

confidence: 99%

Optimization of the photocatalytic degradation process of aromatic organic compounds applied to mangrove sediment

Silva

Soares

Santos

et al. 2020

Heliyon

View full text Add to dashboard Cite

Polycyclic aromatic hydrocarbons (PAHs) are part of a class of organic compounds resistant to natural degradation. In this way, heterogeneous photocatalysis becomes useful to degrade persistent organic pollutants, however it can be influenced by environmental variables (i.e.: organic matter) and experimental factors such as: mass of the photocatalyst and irradiation time. The objective of this research was to use a factorial design 2 k as a function of the multiple response (MR) to evaluate simultaneously experimental conditions for the photodegradation of polycyclic aromatic hydrocarbons in contaminated mangrove sediment and its application in oil from Potiguar Basin in Brazil. The sediment samples collected in Belmonte city (Southern Bahia state) were contaminated with 0.25 mg kg −1 of Acenaphthene, Anthracene, Benzo[a]Anthracene, Indene[1,2,3cd]pyrene, Dibenzo[ah]anthracene, Benzo[ghi]pyrene. Factors such as mass of the photocatalyst and irradiation time were evaluated in factorial design 2 2 , with triplicate from the central point, to 1g of the PAH contaminated sediment. After performing the experiments, it was found that the best experimental condition for the degradation of all PAHs indicated by MR was the central point (0.5 g of photocatalyst and 12h of irradiation). For such conditions, the half-life of PAHs varied from 3.51 to 9.37 h and the degradation speed constant between 0.0740 to 0.1973 h −1 . The comparison of the optimized methodology between photolysis tests and heterogeneous photocatalysis was performed using the Kruskal-Wallis test, which indicated a difference for the reference solution, where heterogeneous photocatalysis was more efficient in the degradation of PAHs. The optimized methodology was apply in samples contaminated with crude oil from Potiguar Basin, no significant difference was observed in the aromatic fraction, using for the Kruskal-Wallis test. Heterogeneous photocatalysis has shown to be a promising remediation technique to remedy aromatic organic compounds in mangrove sediments.

show abstract

where

the model matrix,

the parameter vector and

T the linear predictor; link function (g) that makes the connection between the average of the observations and the systematic part.

…”

Section: Methodsmentioning

confidence: 99%

Optimization of the photocatalytic degradation process of aromatic organic compounds applied to mangrove sediment

Silva

Soares

Santos

et al. 2020

Heliyon

View full text Add to dashboard Cite

show abstract

“…Among others, well-known model selection criteria include the Akaike information criterion (AIC) [1,2] and Bayesian information criterion (BIC) [32], where the former is based on the Kullback-Leibler (KL) divergence principle of model selection and the latter is originated from the Bayesian principle of model selection. A great deal of work has been devoted to understanding and extending these model selection criteria to different model settings; see, for example, [4,20,25,24,8,9,27,30,11,23]. The connections between the AIC and cross-validation have been investigated in [34,21,31] for various contexts.…”

Section: Introductionmentioning

confidence: 99%

Large-Scale Model Selection with Misspecification

Demirkaya,

Feng,

Basu

et al. 2018

Preprint

View full text Add to dashboard Cite

Model selection is crucial to high-dimensional learning and inference for contemporary big data applications in pinpointing the best set of covariates among a sequence of candidate interpretable models. Most existing work assumes implicitly that the models are correctly specified or have fixed dimensionality. Yet both features of model misspecification and high dimensionality are prevalent in practice. In this paper, we exploit the framework of model selection principles in misspecified models originated in Lv and Liu (2014) and investigate the asymptotic expansion of Bayesian principle of model selection in the setting of high-dimensional misspecified models. With a natural choice of prior probabilities that encourages interpretability and incorporates Kullback-Leibler divergence, we suggest the high-dimensional generalized Bayesian information criterion with prior probability (HGBIC p ) for large-scale model selection with misspecification. Our new information criterion characterizes the impacts of both model misspecification and high dimensionality on model selection. We further establish the consistency of covariance contrast matrix estimation and the model selection consistency of HGBIC p in ultra-high dimensions under some mild regularity conditions. The advantages of our new method are supported by numerical studies.

show abstract

Econometrics—Selected Models

Vrbka

2021

Studies in Computational Intelligence

View full text Add to dashboard Cite

Model comparison for generalized linear models with dependent observations

Cited by 5 publications

References 27 publications

Optimization of the photocatalytic degradation process of aromatic organic compounds applied to mangrove sediment

Optimization of the photocatalytic degradation process of aromatic organic compounds applied to mangrove sediment

Large-Scale Model Selection with Misspecification

Econometrics—Selected Models

Contact Info

Product

Resources

About