Sachin,
You can use a log periodigram to identify long-wave cycles or the periodicity
of a seasonal waveform.
You can also generate functions of sines and cosines with
x= A*sin(2*pi*freq*time/T + phase shift) + B*cos(2*pi*freq*time/T + phase shift)
where
phase shift is the angular shift in radians.
T = number of obs
time=position on the time axis
freq=frequency of ovariation over a span of a period of observations.
The functions can be added together to model the waveform being considered.
Yet this is just the beginning of spectral analysis. For a more detailed
treatment see Bloomfield on the Fourier Analysis of Time Series published
by Wiley.
Regards,
Bob Yaffee
Robert A. Yaffee, Ph.D.
Research Professor
Silver School of Social Work
New York University
Biosketch: http://homepages.nyu.edu/~ray1/Biosketch2008.pdf
CV: http://homepages.nyu.edu/~ray1/vita.pdf
----- Original Message -----
From: Sachin Chintawar <[email protected]>
Date: Thursday, October 30, 2008 7:50 am
Subject: st: St: Spectral Analysis
To: [email protected]
> Dear All
> I am trying to figure out if we can do spectral analysis in stata.
> Unfortunately I am unable to find the command. I have traditionally
> used SAS
> and remember the 'PROC SPECTRA' method can be used to perform spectral
> and
> cross spectral analysis of time series.
> Any help would be greatly appreciated.
>
> Thanks
> Sachin
>
> Sachin Chintawar
> Research Assistant
> Dept. of Agricultural Economics
> Louisiana State University
>
>
>
>
> *
> * For searches and help try:
> * http://www.stata.com/help.cgi?search
> * http://www.stata.com/support/statalist/faq
> * http://www.ats.ucla.edu/stat/stata/
*
* For searches and help try:
* http://www.stata.com/help.cgi?search
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
