Spatial Logistic and Probit Regression Models for Analysis of Frosting Data in Mazandaran Province

Logistic and Probit regression models are usually used in binary response variable analysis based on independence assumption of the observations. But, in practice, there are many situations in which, due to their different locations in the underling space of study, this assumption dose not satisfies. In spatial statistics, it is generally supposed that the binary observations are analyzed with indicator Kriging. In this paper, we considered the spatial Logistic and Probit regression models with auto correlated errors on a rectangular grid. Also, in a simulation study, the prediction accuracy of the models has been compared. Finally, the implementation of the models for a temperature data set, reported by weather stations in Mazandaran province of Iran, is shown.