BARTLETT CORRECTION IN THE STABLE AR(1) MODEL WITH INTERCEPT AND TREND
Bartlett corrections are derived for testing hypotheses about the autoregressive parameter <italic>ρ</italic> in the stable (a) AR(1) model, (b) AR(1) model with intercept, (c) AR(1) model with intercept and linear trend. The correction is found explicitly as a function of <italic>ρ</italic>. In the models with deterministic terms, the correction factor is asymmetric in <italic>ρ</italic>. Furthermore, the Bartlett correction is monotonically increasing in <italic>ρ</italic> and tends to infinity when <italic>ρ</italic> approaches the stability boundary of + 1. Simulation results indicate that the Bartlett corrections are useful in controlling the size of the likelihood ratio statistic in small samples, although these corrections are not the ultimate panacea.
| Year of publication: |
2009
|
|---|---|
| Authors: | Giersbergen, Noud P.A. van |
| Published in: |
Econometric Theory. - Cambridge University Press. - Vol. 25.2009, 03, p. 857-872
|
| Publisher: |
Cambridge University Press |
| Description of contents: | Abstract [journals.cambridge.org] |
Saved in:
Saved in favorites
Similar items by person
-
Bias Correction in a Stable AD(1,1) Model
Giersbergen, Noud P.A. van, (2001)
-
On the effect of deterministic terms on the bias in stable AR models
Giersbergen, Noud P.A. van, (2005)
-
How to implement the Bootstrap in Static or Stable Dynamic Regression Models
Giersbergen, Noud P.A. van, (2001)
- More ...