Bayesian spatio-temporal zero-inflated mixed models for overdispersion on chronic disease mapping
- Osuji, Georgeleen O https://orcid.org/0000-0002-8408-3928
- Authors: Osuji, Georgeleen O https://orcid.org/0000-0002-8408-3928
- Date: 2021-12
- Subjects: Medical mapping , Bayesian statistical decision theory
- Language: English
- Type: Doctoral theses , text
- Identifier: http://hdl.handle.net/10353/23644 , vital:58230
- Description: Background: Life expectancy in most developing countries has remarkably increased and decreased in mortality, but under 5 years old mortality has increased due to HIV and Tuberculosis incidence. Many factors have been established to influence the mortality rate among HIV patients and understanding the factors contribution to the risk of under 5-year-old mortality is important for designing appropriate health interventions. Excess zeros usually occur in such HIV mortality count data. Mixed models consisting of count part and zero part are often used to describe the observed excess zero in the data. Poisson models are popular modeling inference, but Negative-Binomial models are more flexible in analyzing count data and dealing with overdispersion. Method: This research proposed to develop two-part hurdle models in analyzing areal zero count data. A spatial Bayesian lognormal-logit hurdle model (BLLHM) with random effects characterizes and cross-spatial dependencies were introduced. The parameter inferences and predictions were evaluated using the Markov Chain Monte Carlo algorithm. The model proposed was applied to HIV-positive under 5-year-old mortality collected from the Eastern Cape Department of Health. Results: Bayesian lognormal-logit hurdle model is selected as the best model fit. It is observed that the total number of HIV patients not on ART-HIVnotTB (0.000612, p <0.000) was positively and statistically significantly associated with the HIV-positive mortality of under 5 years patients. Both CD4 counts were done on newly diagnosed HIV rate (CD4count) and HIV-positive new patients screened for TB rate (HIVTBrate) were negatively and statistically significantly associated with the HIV-positive mortality of under 5 years patients (-0.6294, p = 0.000 and -0.00056, p = 0.0052). However, the covariate HIV positive Tuberculosis Preventive therapy (TPT) uptake rate (HIVandTB) was not statistically significantly associated with the HIV-positive mortality of under 5 years patients (-0.00155, p = 0.5392). Conclusion: The model is flexible to deal with zero-inflated and over-dispersed count data. There is a need to consider the risk of cause-specific under-5-year-old mortality in terms of spatial effects. , Thesis (PhD) -- Faculty of Science and Agriculture, 2021
- Full Text:
- Date Issued: 2021-12
- Authors: Osuji, Georgeleen O https://orcid.org/0000-0002-8408-3928
- Date: 2021-12
- Subjects: Medical mapping , Bayesian statistical decision theory
- Language: English
- Type: Doctoral theses , text
- Identifier: http://hdl.handle.net/10353/23644 , vital:58230
- Description: Background: Life expectancy in most developing countries has remarkably increased and decreased in mortality, but under 5 years old mortality has increased due to HIV and Tuberculosis incidence. Many factors have been established to influence the mortality rate among HIV patients and understanding the factors contribution to the risk of under 5-year-old mortality is important for designing appropriate health interventions. Excess zeros usually occur in such HIV mortality count data. Mixed models consisting of count part and zero part are often used to describe the observed excess zero in the data. Poisson models are popular modeling inference, but Negative-Binomial models are more flexible in analyzing count data and dealing with overdispersion. Method: This research proposed to develop two-part hurdle models in analyzing areal zero count data. A spatial Bayesian lognormal-logit hurdle model (BLLHM) with random effects characterizes and cross-spatial dependencies were introduced. The parameter inferences and predictions were evaluated using the Markov Chain Monte Carlo algorithm. The model proposed was applied to HIV-positive under 5-year-old mortality collected from the Eastern Cape Department of Health. Results: Bayesian lognormal-logit hurdle model is selected as the best model fit. It is observed that the total number of HIV patients not on ART-HIVnotTB (0.000612, p <0.000) was positively and statistically significantly associated with the HIV-positive mortality of under 5 years patients. Both CD4 counts were done on newly diagnosed HIV rate (CD4count) and HIV-positive new patients screened for TB rate (HIVTBrate) were negatively and statistically significantly associated with the HIV-positive mortality of under 5 years patients (-0.6294, p = 0.000 and -0.00056, p = 0.0052). However, the covariate HIV positive Tuberculosis Preventive therapy (TPT) uptake rate (HIVandTB) was not statistically significantly associated with the HIV-positive mortality of under 5 years patients (-0.00155, p = 0.5392). Conclusion: The model is flexible to deal with zero-inflated and over-dispersed count data. There is a need to consider the risk of cause-specific under-5-year-old mortality in terms of spatial effects. , Thesis (PhD) -- Faculty of Science and Agriculture, 2021
- Full Text:
- Date Issued: 2021-12
Bayesian hierarchical modelling with application in spatial epidemiology
- Authors: Southey, Richard Robert
- Date: 2018
- Subjects: Bayesian statistical decision theory , Spatial analysis (Statistics) , Medical mapping , Pericarditis , Mortality Statistics
- Language: English
- Type: text , Thesis , Masters , MSc
- Identifier: http://hdl.handle.net/10962/59489 , vital:27617
- Description: Disease mapping and spatial statistics have become an important part of modern day statistics and have increased in popularity as the methods and techniques have evolved. The application of disease mapping is not only confined to the analysis of diseases as other applications of disease mapping can be found in Econometric and financial disciplines. This thesis will consider two data sets. These are the Georgia oral cancer 2004 data set and the South African acute pericarditis 2014 data set. The Georgia data set will be used to assess the hyperprior sensitivity of the precision for the uncorrelated heterogeneity and correlated heterogeneity components in a convolution model. The correlated heterogeneity will be modelled by a conditional autoregressive prior distribution and the uncorrelated heterogeneity will be modelled with a zero mean Gaussian prior distribution. The sensitivity analysis will be performed using three models with conjugate, Jeffreys' and a fixed parameter prior for the hyperprior distribution of the precision for the uncorrelated heterogeneity component. A simulation study will be done to compare four prior distributions which will be the conjugate, Jeffreys', probability matching and divergence priors. The three models will be fitted in WinBUGS® using a Bayesian approach. The results of the three models will be in the form of disease maps, figures and tables. The results show that the hyperprior of the precision for the uncorrelated heterogeneity and correlated heterogeneity components are sensitive to changes and will result in different results depending on the specification of the hyperprior distribution of the precision for the two components in the model. The South African data set will be used to examine whether there is a difference between the proper conditional autoregressive prior and intrinsic conditional autoregressive prior for the correlated heterogeneity component in a convolution model. Two models will be fitted in WinBUGS® for this comparison. Both the hyperpriors of the precision for the uncorrelated heterogeneity and correlated heterogeneity components will be modelled using a Jeffreys' prior distribution. The results show that there is no significant difference between the results of the model with a proper conditional autoregressive prior and intrinsic conditional autoregressive prior for the South African data, although there are a few disadvantages of using a proper conditional autoregressive prior for the correlated heterogeneity which will be stated in the conclusion.
- Full Text:
- Date Issued: 2018
- Authors: Southey, Richard Robert
- Date: 2018
- Subjects: Bayesian statistical decision theory , Spatial analysis (Statistics) , Medical mapping , Pericarditis , Mortality Statistics
- Language: English
- Type: text , Thesis , Masters , MSc
- Identifier: http://hdl.handle.net/10962/59489 , vital:27617
- Description: Disease mapping and spatial statistics have become an important part of modern day statistics and have increased in popularity as the methods and techniques have evolved. The application of disease mapping is not only confined to the analysis of diseases as other applications of disease mapping can be found in Econometric and financial disciplines. This thesis will consider two data sets. These are the Georgia oral cancer 2004 data set and the South African acute pericarditis 2014 data set. The Georgia data set will be used to assess the hyperprior sensitivity of the precision for the uncorrelated heterogeneity and correlated heterogeneity components in a convolution model. The correlated heterogeneity will be modelled by a conditional autoregressive prior distribution and the uncorrelated heterogeneity will be modelled with a zero mean Gaussian prior distribution. The sensitivity analysis will be performed using three models with conjugate, Jeffreys' and a fixed parameter prior for the hyperprior distribution of the precision for the uncorrelated heterogeneity component. A simulation study will be done to compare four prior distributions which will be the conjugate, Jeffreys', probability matching and divergence priors. The three models will be fitted in WinBUGS® using a Bayesian approach. The results of the three models will be in the form of disease maps, figures and tables. The results show that the hyperprior of the precision for the uncorrelated heterogeneity and correlated heterogeneity components are sensitive to changes and will result in different results depending on the specification of the hyperprior distribution of the precision for the two components in the model. The South African data set will be used to examine whether there is a difference between the proper conditional autoregressive prior and intrinsic conditional autoregressive prior for the correlated heterogeneity component in a convolution model. Two models will be fitted in WinBUGS® for this comparison. Both the hyperpriors of the precision for the uncorrelated heterogeneity and correlated heterogeneity components will be modelled using a Jeffreys' prior distribution. The results show that there is no significant difference between the results of the model with a proper conditional autoregressive prior and intrinsic conditional autoregressive prior for the South African data, although there are a few disadvantages of using a proper conditional autoregressive prior for the correlated heterogeneity which will be stated in the conclusion.
- Full Text:
- Date Issued: 2018
- «
- ‹
- 1
- ›
- »