Estimation and forecast in nonlinear autoregression models

• Grant number: 23/10493-6
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: October 01, 2023
• End date: September 30, 2024
• Field of knowledge: Applied Social Sciences - Economics - Quantitative Methods Applied to Economics
• Principal Investigator: Carlos Cesar Trucios Maza
• Grantee: Felipe Scalabrin Dosso
• Host Institution: Instituto de Matemática, Estatística e Computação Científica (IMECC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil

Abstract

Autoregressive models are widely used in time series. However, these models are based on the linear relationship of the series with its own past, a restriction that does not allow exploring non-linear relationships in the dynamics of the data. Aiming at greater flexibility, non-linear autoregressive models were proposed and competitive results in terms of prediction have been seen in several applications. In this research, in order to better understand in which situations the performance of nonlinear autoregressive models will be as expected, we will study several properties in finite samples of the model. The results will also be evaluated using empirical data.