| By: |
Zongwu Cai (Department of Economics, The University of Kansas, Lawrence, KS 66045, USA);
Gunawan (Department of Economics, The University of Kansas, Lawrence, KS 66045, USA) |
| Abstract: |
Structural breaks in time series forecasting can cause inconsistency in the
conventional OLS estimator. Recent research suggests combining pre and
post-break estimators for a linear model can yield an optimal estimator for
weak breaks. However, this approach is limited to linear models only. In this
paper, we propose a weighted local linear estimator for a nonlinear model.
This estimator assigns a weight based on both the distance of observations to
the predictor covariates and their location in time. We investigate the
asymptotic properties of the proposed estimator and choose the optimal tuning
parameters using multifold cross-validation to account for the dependence
structure in time series data. Additionally, we use a nonparametric method to
estimate the break date. Our Monte Carlo simulation results provide evidence
for the forecasting outperformance of our estimator over the regular
nonparametric post-break estimator. Finally, we apply our proposed estimator
to forecast GDP growth for nine countries and demonstrate its superior
performance compared to the conventional estimator using Diebold-Mariano tests. |
| Keywords: |
Combination Forecasting; Local Linear Fitting; Multifold Cross-Validation; Nonparametric Model; Structural Break Model |
| JEL: |
C14 C22 C53 |
| Date: |
2023–09 |
| URL: |
http://d.repec.org/n?u=RePEc:kan:wpaper:202310&r=for |