Fitting logistic multilevel models with crossed random effects via Bayesian Integrated Nested Laplace Approximations: a simulation study

Grilli, Leonardo; Innocenti, Francesco

doi:10.1080/00949655.2017.1341886

Cited by 5 publications

(6 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As Bayesian statistics using Markov chain Monte Carlo (MCMC) can be computationally intensive and difficult to parametrize, a method using INLA to approximate the posterior marginal distribution and developed for R was used in our study [ 51 , 53 ]. Studies comparing R-INLA to other regression modeling methods have shown that R-INLA can be simpler to use and quicker in computation whilst yielding similar estimates to other Bayesian or generalized linear approaches [ 55 , 62 ]. We believe this was the most cost-effective approach in this particular study.…”

Section: Discussionmentioning

confidence: 99%

Accessibility to rabies centers and human rabies post-exposure prophylaxis rates in Cambodia: A Bayesian spatio-temporal analysis to identify optimal locations for future centers

Baron

Chevalier

et al. 2022

PLoS Negl Trop Dis

View full text Add to dashboard Cite

Rabies is endemic in Cambodia. For exposed humans, post-exposure prophylaxis (PEP) is very effective in preventing this otherwise fatal disease. The Institut Pasteur du Cambodge (IPC) in Phnom Penh was the primary distributor of PEP in Cambodia until 2018. Since then, and to increase distribution of PEP, two new centers have been opened by IPC in the provinces of Battambang and Kampong Cham. Data on bitten patients, who sometimes bring the head of the biting animal for rabies analyses, have been recorded by IPC since 2000. However, human cases are not routinely recorded in Cambodia, making it difficult to establish a human burden of disease and generate a risk map of dog bites to inform the selection of future PEP center locations in high-risk areas. Our aim was to assess the impact of accessibility to rabies centers on the yearly rate of PEP patients in the population and generate a risk map to identify the locations where new centers would be the most beneficial to the Cambodian population. To accomplish this, we used spatio-temporal Bayesian regression models with the number of PEP patients as the outcome. The primary exposure variable considered was travel time to the nearest IPC center. Secondary exposure variables consisted of travel time to a provincial capital and urban proportion of the population. Between 2000 and 2016, a total of 293,955 PEP patient records were identified. Our results showed a significant negative association between travel time to IPC and the rate of PEP patients: an increase in one hour travel time from the living location to IPC PEP centers leads to a reduction in PEP rate of 70% to 80%. Five provinces were identified as the most efficient locations for future centers to maximize PEP accessibility: Banteay Meanchey, Siem Reap, Takeo, Kampot and Svay Rieng. Adding a PEP center in every provincial capital would increase the proportion of Cambodians living within 60 minutes of a PEP center from 26.6% to 64.9%, and living within 120 minutes from 52.8% to 93.3%, which could save hundreds of lives annually.

show abstract

Section: Discussionmentioning

confidence: 99%

Accessibility to rabies centers and human rabies post-exposure prophylaxis rates in Cambodia: A Bayesian spatio-temporal analysis to identify optimal locations for future centers

Baron

Chevalier

et al. 2022

PLoS Negl Trop Dis

View full text Add to dashboard Cite

show abstract

“…The R-INLA inbuilt standard priors are the nature of R-INLA packages of INLA function. Different researchers [13][14][15] briefly used it. According to the study [7] by default, a flat improper prior for the intercept assumed in INLA and all other components of parameters assumed independent Gaussian with mean zero Normal (0,σ 2 ) with fixed precision σ −2 = 0.0001 a priori.…”

Section: Prior Distributions Of Parametersmentioning

confidence: 99%

Determining factors associated with cholera disease in Ethiopia using Bayesian hierarchical modeling

2022

View full text Add to dashboard Cite

Background Cholera is a diarrheal disease caused by infection of the intestine with the gram-negative bacteria Vibrio cholera. It is caused by the ingestion of food or water and infected all age groups. This study aimed at identifying risk factors associated with cholera disease in Ethiopia using the Bayesian hierarchical model. Methods The study was conducted in Ethiopia across regions and this study used secondary data obtained from the Ethiopian public health institute. Latent Gaussian models were used in this study; which is a group of models that contains most statistical models used in practice. The posterior marginal distribution of the Latent Gaussian models with different priors is determined by R-Integrated Nested Laplace Approximation. Results There were 2790 cholera patients in Ethiopia across the regions. There were 81.61% of patients are survived from cholera outbreak disease and the rest 18.39% have died. There was 39% variation across the region in Ethiopia. Latent Gaussian models including random and fixed effects with standard priors were the best model to fit the data based on deviance. The odds of surviving from cholera outbreak disease for inpatient status are 0.609 times less than the outpatient status. Conclusions The authors conclude that the fitted latent Gaussian models indicate the predictor variables; admission status, aged between 15 and 44, another sick person in a family, dehydration status, oral rehydration salt, intravenous, and antibiotics were significantly associated with cholera outbreak disease.

show abstract

“…In addition, the marginal posterior distribution for each element of hyper-parameter vector: Different researchers [11][12][13] briefly used it. According to the study [14] by default, a flat improper prior for the intercept assumed in INLA and all other components of parameters assumed independent Gaussian with mean zero Normal (0,𝜎 2 ) with fixed precision 𝜎 −2 = 0.0001 a priori.…”

Section: Integrated Nested Laplace Approximation (Inla)mentioning

confidence: 99%

Determining Factors Associated with Cholera Disease in Ethiopia using Bayesian Hierarchical Modeling

Letta

Belay

Ali

2022

Preprint

View full text Add to dashboard Cite

Background: Cholera is a diarrheal disease caused by infection of the intestine with the gram-negative bacteria Vibrio cholera. It is caused by the ingestion of food or water and infected all age groups. This study aimed at identifying risk factors associated with cholera disease in Ethiopia using the Bayesian hierarchical model. Methods: The study was conducted in Ethiopia across regions and this study used secondary data obtained from the Ethiopian public health institute. Latent Gaussian models were used in this study; which is a group of models that contains most statistical models used in practice. The posterior marginal distribution of the Latent Gaussian models with different priors is determined by R-Integrated Nested Laplace Approximation. Results: There were 2790 cholera patients in Ethiopia across the regions. There were 81.61% of patients are survived from cholera outbreak disease and the rest 18.39% have died. There was 39% variation across the region in Ethiopia. Latent Gaussian models including random and fixed effects with standard priors were the best model to fit the data based on deviance. The odds of surviving from cholera outbreak disease for inpatient status are 0.609 times less than the outpatient status. Conclusions: The authors conclude that the fitted latent Gaussian models indicate the predictor variables; admission status, aged between 15 and 44, another sick person in a family, dehydration status, oral rehydration salt, intravenous, and antibiotics were significantly associated with cholera outbreak disease.

show abstract

Fitting logistic multilevel models with crossed random effects via Bayesian Integrated Nested Laplace Approximations: a simulation study

Cited by 5 publications

References 37 publications

Accessibility to rabies centers and human rabies post-exposure prophylaxis rates in Cambodia: A Bayesian spatio-temporal analysis to identify optimal locations for future centers

Accessibility to rabies centers and human rabies post-exposure prophylaxis rates in Cambodia: A Bayesian spatio-temporal analysis to identify optimal locations for future centers

Determining factors associated with cholera disease in Ethiopia using Bayesian hierarchical modeling

Determining Factors Associated with Cholera Disease in Ethiopia using Bayesian Hierarchical Modeling

Contact Info

Product

Resources

About