A1888
Title: Inference of spatially varying coefficient model with covariate measurement errors
Authors: Bohai Zhang - Beijing Normal-Hong Kong Baptist University (China) [presenting]
Abstract: Spatially varying coefficient (SVC) models offer an effective way to characterize the heterogeneous effects of covariates on the response variable. However, existing SVC models assume accurately measured covariates, ignoring real-world measurement errors that may arise from many aspects. A statistically and computationally efficient framework for the inference of SVC models is developed based on profile model likelihood, with explicit consideration of covariate measurement error. Focusing on spatial clustered coefficient models, an SVC model is formulated that allows functional covariate measurement errors. Bias-corrected estimators are then derived by leveraging techniques of high-dimensional measurement error models and unbiased estimating functions, ensuring consistent parameter estimation. Additionally, a joint weighted estimation procedure is developed that accounts for unequal variances of the residuals, markedly enhancing the estimation efficiency over the unweighted alternative. Finally, the effectiveness of the proposed approaches is demonstrated through comprehensive simulation studies and an analysis of the Arctic sea ice dataset.
