Estimation and Testing of Random Effects Semiparametric Regression Model with Separable Space-Time Filters

This paper focuses on studying a random effects semiparametric regression model (RESPRM) with separable space-time filters. The cannot only capture the linearity and nonlinearity existing in dataset, but also avoid inefficient estimators caused by ignoring spatial correlation serial error term of data model. Its profile quasi-maximum likelihood (PQMLE) for parameters nonparametric functions, generalized F-test statistic checking existence nonlinear relationships are constructed. asymptotic properties distribution test derived. Monte Carlo simulations imply that our have good finite sample performance. Indonesian rice farming used to illustrate methods.