A Bayesian two-state Markov chain model with categorical responses: An application to climatic conditions for crop growth
Abstract
In this study, Bayesian estimation procedure is presented especially for a binary Markov chain model under the assumption that the prior for had non- informative and informative prior distribution when the number of unfavourable climatic periods for the growth of the crop is more than the favourable period. Thus, a sequence of logical connectives was used to combine climatic variable namely , rainfall and temperature to obtain favourable and unfavourable crop growth conditions for the Pearl millet. Bayed factor revealed the that probability estimates obtained using the informative prior performed better than those obtained using the non-informative prior. There is a lower probability, 0.4227 of a favourable climate for the pearl millet growth, indicating that climate change has an adverse effect on the crop.
Fields of Study & Subjects
Climate change impacts on agriculture
Agricultural risk and resilience
Bayesian Modeling and Causal Inference
Publication details
- Journal / source
- Journal of Statistical Sciences and Computational Intelligence
- Publisher
- Journal of Statistical Sciences and Computational Intelligence
- Volume
- 2
- Issue
- 1
- Pages
- 181–191
- Publication date
- 27 February 2026