Post Reply 
 
Thread Rating:
  • 0 Votes - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Best fit for a xy data set
09-11-2009, 07:32 PM
Post: #1
Best fit for a xy data set
Hi,

I\'m trying to model some xy data, and the only obvious best fit options are polynomials, is there a way to use an exponential?
Quote this message in a reply
10-11-2009, 04:51 PM
Post: #2
Re: Best fit for a xy data set
Hi reg,

Once you have entered your data, enter the model you would like to use for your data. In your case maybe:

y = aexp(bx + c) + d

Use the Constant Controller to find the values of a, b, c and d which lead to a good fit. Select the curve and the data, right-click and choose Best Fit. Then Autograph will calculate the values of a, b, c and d that it thinks would be best.

I hope this helps,

Simon
Quote this message in a reply
10-11-2009, 06:14 PM
Post: #3
Re: Best fit for a xy data set
Thank you, that works well. Although it gives a different (and seemingly less accurate) solution than Excel. Is there a way of overcoming this?

Thanks
Rachel
Quote this message in a reply
12-11-2009, 07:32 PM
Post: #4
Re: Best fit for a xy data set
Dear Rachel,

Glad this is now working for you. I am not sure what method Excel uses to fit functions to data. The success of our algorithm depends on the start values of the parameters so you might find it fits better if you tweak the initial values.

Best regards,

Simon
Quote this message in a reply
Post Reply 


Forum Jump:


User(s) browsing this thread: 1 Guest(s)