Take the 2-minute tour ×
Cross Validated is a question and answer site for people interested in statistics, machine learning, data analysis, data mining, and data visualization. It's 100% free, no registration required.

I would like to apply the Kalman filter in order to get a causal Hodrick-Prescott filter. The Hodrick-Prescott filter models a time series $(y_t)_{t=0}^T$ as $$ y_t = \tau_t + c_t $$ where $\tau_t$ is a trend component and $c_t$ is a cyclical component.

This reference defines a state space formulation of the form $$ y_t = \tau_t + c_t $$ as the measurement equation and $$ \tau_t = 2 \tau_{t−1} − \tau_{t−2} + \epsilon_t $$ for the unobservable trend.

I have three questions on this:

A) $c_t$ is assumed to be a random error here, right? Normally distributed with constant variance. This seems a difficult assumption to me.

B) What's the logic behind the equation for the trend?

C) Does anybody know a different state space formulation for this problem? Or a nother reference?

Thanks!

share|improve this question
1  
This material is covered quite well in the book Econometric Modelling with Time Series by Martin, Hurn, and Harris. Specifically, see Chapter 15 and pages 567-571. I may provide a full answer later. –  Graeme Walsh Feb 20 at 2:03
add comment

1 Answer

up vote 3 down vote accepted

A) Actually, your reference says "a stationary residual or cyclical component, $c_t$", while this calls $c_t$ a 'cyclical component'.

Maravall and del Rio (2001) say "a residual, $c_t$, to be called “cycle”."

B) This formulation follows from the form of $A$; the second difference of $\tau$ is the error term.

C)

http://www.reservebank.govt.nz/research/discusspapers/dp03_02.pdf

http://www.stat.itam.mx/seminarios/Resumens/p136.pdf (see p6 which is relevant to your B, but they appear to have a sign in the A-matrix wrong (c.f. your link, p13)

http://www3.istat.it/dati/pubbsci/contributi/Contributi/contr_2005/2005_07.pdf

http://www.terrapub.co.jp/journals/jjss/pdf/3801/38010041.pdf

share|improve this answer
    
Thanks for your answer! Some remarks: ad A) No matter how we all it. $c_t$ in the classical formulation of HP an have any distribution as far as I know. In the Kalman filter setting it has to be normal. This is a strong assmption, isn't it? ad B) Now I see: this is the smoothness condition ... great! Thanks for C)! –  Richard Jan 23 '13 at 13:18
add comment

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.

Not the answer you're looking for? Browse other questions tagged or ask your own question.