期刊名称：International Journal of Environment and Bioenergy
电子版ISSN：2165-8951
出版年度：2012
卷号：2
期号：2
页码：92-99
语种：English
出版社：Modern Scientific Press
摘要：Bayesian approach necessitates use of prior information and Baye's theorem provides the basis for making use of this information in a formal manner. In the present paper Bayesian analysis has been carried out on rice production data using the Exchangeability Technique given by Lindley and Smith in 1972. The effect of weather parameters viz temperature, humidity, rainfall, sunshine, wind velocity and evaporation is measured on the yield of rice crop and the results are compared with the usual (nonBayesian approach) least square technique (LS). The linear and non-linear regression models have been fitted to the real data set using both the approaches. Bayesian approach is found to be better than the least square approach as the value of the coefficient of determination is higher in case of the former, and the non-linear models are better than linear models when fitted by using both the approaches, which is determined by MSE's of estimators.
