rec04 - MIT OpenCourseWare http/ocw.mit.edu 14.384 Time...

Info iconThis preview shows pages 1–4. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full Document Right Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: MIT OpenCourseWare http://ocw.mit.edu 14.384 Time Series Analysis Fall 2008 For information about citing these materials or our Terms of Use, visit: http://ocw.mit.edu/terms . Spectrum Estimation 1 14.384 Time Series Analysis, Fall 2008 Recitation by Paul Schrimpf Supplementary to lectures given by Anna Mikusheva September 26, 2008 Recitation 4 Spectrum Estimation We have a stationary series, { z iω t } with covariances γ j j and spectrum S ( ω ) = ∞ j = γ j e − . We want to −∞ estimate S ( ω ). Using Covariances As in lecture 5, we can estimate the spectrum in the same way that we estimate the long-run variance. Na¨ ıve approach We cannot estimate all the covariances from a finite sample. Let’s just estimate all the covariances that we can 1 T γ ˆ j = z j z j − k T j = k +1 and use them to form S ˆ ( ω ) = T − 1 γ ˆ j e − iωj j = − ( T − 1) This estimator is not consistent. It convergers to a distribution instead of a point. To see this, let y ω = √ 1 T t T =1 e − iωt z t , so that S ˆ ( ω ) = y ω y ¯ ω If ω = 0 2 S ˆ ( ω ) S ( ω ) χ 2 (2) ⇒ Kernel Estimator S T S ˆ ( ω ) = 1 − | j | γ ˆ j e − iωj S T j = − S T Under appropriate conditions on S T ( S T → ∞ , but more slowly than T ), this estimator is consistent 1 This can be shown in a way similar to the way we showed the Newey-West estimator is consistent. “ ” 1 In a uniform sense, i.e. P sup ω ∈ [ − π,π ] | S ˆ ( ω ) − S ( ω ) | > → Using Covariances 2 Proof. This is an informal “proof” that sketches the ideas, but isn’t completely rigorous. It is nearly identical to the proof of HAC consistency in lecture 3....
View Full Document

{[ snackBarMessage ]}

Page1 / 6

rec04 - MIT OpenCourseWare http/ocw.mit.edu 14.384 Time...

This preview shows document pages 1 - 4. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online