Fixed effects spatial panel interval-valued autoregressive models and applications

Interval-valued data has garnered attention across various applications, leading to increased research into spatial interval-valued data models. The integration of uncertainty variables into spatial panel data models has become crucial. This paper presents a spatial panel interval-valued autoregressive model with fixed effects, utilizing the parametric method. The quasi-maximum likelihood method is employed for parameter estimation, and its consistency and asymptotic properties are discussed. Additionally, three special cases and two degenerated models derived from our framework are presented, elucidating their significance in spatial statistics. Monte Carlo simulations are used to validate the fitting and forecasting performance of our proposed models across diverse scenarios. Furthermore, the models are implemented in real-world air quality and house price datasets for forecasting purposes. Through rigorous experimentation, the superior performance of the models is demonstrated. These results highlight the practical utility of the spatial panel interval-valued autoregressive models in addressing spatial data challenges.