Timeline for Exponential fit for time series
Current License: CC BY-SA 3.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 8, 2017 at 22:49 | comment | added | JimB |
One gets more stable results (i.e., less dependent on starting values) if Exp[a + b t] is used rather than a Exp[b t].
|
|
| Sep 8, 2017 at 15:02 | comment | added | Daniel Lichtblau | The error message would suggest that a variable was mistakenly assigned to the actual data. As others have noted, there are perhaps other issues with this. | |
| Sep 7, 2017 at 22:07 | comment | added | Hugh | I think we need to see a plot of your complete data set so that we can see what you are trying to do. Can you add this to your question. I feel I am working in the dark at the moment. | |
| Sep 7, 2017 at 22:04 | comment | added | Marta Greselin | Hi Hugh, I really appreciate your help. Indeed it is an oscillating function with an exponential envelop. I'm exactly looking for this envelop, when the oscillation amplitude stop growing and start decreasing. | |
| Sep 7, 2017 at 21:42 | history | edited | Hugh | CC BY-SA 3.0 |
More information provided gives a different perspective.
|
| Sep 7, 2017 at 20:52 | comment | added | Marta Greselin | I provided data corresponding to a 20s recording, which is very short. But anyway the problem I face is very basic. Mathematica FindFit or NonlinearFit complains about the kind of data I provide. As an example this is the error I get: General::ivar: {1/120,1/60,1/40,1/30,1/24,1/20,7/120,1/15,3/40,1/12,11/120,1/10,13/120,7/60,1/8,2/15,17/120,3/20,19/120,1/6,7/40,11/60,23/120,1/5,5/24,13/60,9/40,7/30,29/120,1/4,31/120,4/15,11/40,17/60,7/24,3/10,37/120,19/60,13/40,1/3,41/120,7/20,43/120,11/30,3/8,23/60,47/120,2/5,49/120,5/12,<<765191>>} is not a valid variable. | |
| Sep 7, 2017 at 20:47 | comment | added | Marta Greselin | pastebin.com/M03RMCJk | |
| Sep 7, 2017 at 20:28 | comment | added | Hugh | I think it is too short to be any use. Can you see an exponential in this? You need to give us much more data. Consider using pastebin and giving us the link. | |
| Sep 7, 2017 at 20:19 | comment | added | Marta Greselin | It is the output of a video tracking of a pendulum in a chain. And I've extracted a very short part of the motion. | |
| Sep 7, 2017 at 19:59 | history | answered | Hugh | CC BY-SA 3.0 |