[SciPy-user] Suggestion about algorithm

Daniele Nicolodi daniele@grinta....
Fri Oct 24 05:32:07 CDT 2008


Robert Kern wrote:
> Can you just get the oscillating curve itself rather than extracting
> the peaks? It might be easiest just to fit the decaying oscillator
> function to the curve. Your uncertainly may still be large, but
> probably better than what you currently have.

The point into demodulating the oscillation an taking the derivative of 
the amplitude is that in this way every oscillation becomes an 
independent estimation of the decay constant Beta. I'm convinced that a 
fitting procedure is not statistically correct because each point in my 
time series is strongly correlated with the previous ones (the 
characteristic time of the system is of a couple of years).

In other words an external disturbance acting on the oscillator (think 
to it as a kick) influences only a single data point in my estimation of 
Beta with the derivative. I then average all the independent data 
points. With a fit a kick would instead affect the estimation very badly.

Ciao
-- 
Daniele


More information about the SciPy-user mailing list