Preprint
Abstract
We introduce a spatial function-on-function regression model to capture spatial dependencies in functional data by integrating spatial autoregressive techniques with functional principal component analysis. The proposed model addresses a critical gap in functional regression by enabling the analysis of functional responses influenced by spatially correlated functional predictors, a common scenario in fields such as environmental sciences, epidemiology, and socio-economic studies. The model employs a spatial functional principal component decomposition on the response and a classical functional principal component decomposition on the predictor, transforming the functional data into a finite-dimensional multivariate spatial autoregressive framework. This transformation allows efficient estimation and robust handling of spatial dependencies through least squares methods. In a series of extensive simulations, the proposed model consistently demonstrated superior performance in estimating both spatial autocorrelation and regression coefficient functions compared to some favorably existing traditional approaches, particularly under moderate to strong spatial effects. Application of the proposed model to Brazilian COVID-19 data further underscored its practical utility, revealing critical spatial patterns in confirmed cases and death rates that align with known geographic and social interactions. An R package provides a comprehensive implementation of the proposed estimation method, offering a user-friendly and efficient tool for researchers and practitioners to apply the methodology in real-world scenarios.Keywords
All Related Versions
This publication has 38 references indexed in Scilit:
- Modern non-linear function-on-function regressionStatistics and Computing, 2023
- A partial least squares approach for function-on-function interaction regressionComputational Statistics, 2021
- On function-on-function regression: partial least squares approachEnvironmental and Ecological Statistics, 2020
- Multivariate functional random fields: prediction and optimal samplingStochastic Environmental Research and Risk Assessment, 2016
- Prediction of functional data with spatial dependence: a penalized approachStochastic Environmental Research and Risk Assessment, 2016
- Optimal sampling for spatial prediction of functional dataStatistical Methods & Applications, 2015
- A universal kriging approach for spatial functional dataStochastic Environmental Research and Risk Assessment, 2013
- Ordinary kriging for function-valued spatial dataEnvironmental and Ecological Statistics, 2010
- Nonlinear functional models for functional responses in reproducing kernel hilbert spacesCanadian Journal of Statistics, 2007
- An Introduction to Metric Spaces and Fixed Point Theory2001