Open AccessEvaluating Forecasts from State-Dependent Autoregressive Models for US GDP Growth Rate. Comparison with Alternative Approaches
Author(s) -
Fabio Gobbi
Publication year - 2021
Publication title -
advances in management and applied economics
Language(s) - English
Resource type - Journals
ISSN - 1792-7544
DOI - 10.47260/amae/1167
Subject(s) - autoregressive model , setar , univariate , econometrics , autoregressive conditional heteroskedasticity , mean squared error , autoregressive integrated moving average , statistics , series (stratigraphy) , forecast error , mathematics , time series , economics , star model , multivariate statistics , volatility (finance) , paleontology , biology
The aim of the paper is to compare the forecasting performance of a class of statedependent autoregressive (SDAR) models for univariate time series with twoalternative families of nonlinear models, such as the SETAR and the GARCHmodels. The study is conducted on US GDP growth rate using quarterly data. Twomethods of forecast comparison are employed. The first method consists inevaluation the average performance by using two measures such as the root meansquare error (RMSE) and the mean absolute error (MAE) over different forecasthorizons, while the second method make use of one of the most used statistical testto compare the accuracy of two forecast methods such as the Diebold-Mariano test.JEL classification numbers: C22, E37, F47.Keywords: Nonlinear models for time series, GDP growth rate, Forecastingaccuracy.