Bayesian multivariate conditional autoregressive model for tuberculosis and HIV in India.


Srinivasan, R.; Ponnuraja, C.; Venkatesan, P.

Indian Journal of Applied Research; 2018; 8(1): 148-150.   

Abstract: Background: Multivariate disease mapping is a collection of two or more disease, each corresponding to the same geographic region, in orders to know information from the joint distribution of disease. This joint model gives understanding of diseases dynamics and relationships between diseases of tuberculosis and HIV incidence jointly, rather than mapping of each disease separately.


Objective: The objective of the study is to construct the Bayesian multivariate CAR (MCAR) model for studying tuberculosis and HIV in India.


Material and methods: National Family Health Survey data on tuberculosis were used in this study. Monte Carlo Markov Chain (MCMC) simulation techniques was used to estimate the parameter. WinBUGS software was used for disease mapping of MCAR model.


Results and Conclusion: The results of the study revealed that spatial autocorrelation between TB and HIV exist and conclude that Bayesian method is proved to be a useful tool for disease modeling of multiple diseases.     


Keywords: MCAR; MCMC; Bayesian; Autocorrelation

Back to List of publications / Home