Estimation of propensity score using spatial logistic regression

Propensity score is a method used to reduce bias due to confounding factors in the estimation of the treatment impact on observational data. Propensity score is the conditional probability to get certain treatments involving the observed covariates. In general, propensity score can be calculated using two methods, they are logistic regression and Classification and Regression Tree Analysis (CART). Logistic regression model is the most common method used. In which, logistic regression model is a model used to estimate the probability of an event. In other side, collecting data by observing many subjects in different place will be influenced spatial effect. Thus, this paper will estimate propensity score using spatial logistic regression.