The authors consider a partially linear autoregressive model and construct kernel-based estimates for both the parametric and nonparametric components. They propose an estimation procedure for the model and illustrate it through simulated and real data. Their work shows that the proposed estimation procedure not only has good asymptotic properties but also works well numerically. It also suggests that a partially linear autoregression is more appropriate than a completely nonparametric autoregression for some sets of data.
- Adaptive estimation
- Dependent process
- Nonlinear time series
- Partially linear autoregression
- Strict stationarity