Timeline for Interpretation of a non-canonical Allan Variance plot
Current License: CC BY-SA 4.0
13 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Feb 28 at 5:03 | comment | added | RoninAmibo | Indeed, I'm referring to exactly that. | |
| Feb 28 at 0:27 | comment | added | Dan Boschen | @RoninAmibo no problem, was fun to investigate. As I mentioned in the comments, consider modeling as a leaky integrator of AWGN: y[n] = x[n] + beta y[n-1]. The closer beta is to 1 (but always less than 1!), the higher tau where it transitions from random walk. Maybe that is the same thing you are saying. | |
| Feb 28 at 0:00 | comment | added | RoninAmibo | Hi @Dan, thank you very much for your help, your insights and you time. It is really appreciated. I'll therefore choose to model with an AR process (discrete version of the OU model) of order 1, with a coefficient really close to 1 so that it has a random walk behavior in low taus. The model will be compared with the dataset using the same tools as above. Thank you very, very much. | |
| Feb 27 at 23:30 | vote | accept | RoninAmibo | ||
| Feb 27 at 15:38 | history | edited | Dan Boschen | CC BY-SA 4.0 |
added 466 characters in body
|
| Feb 27 at 13:48 | history | edited | Dan Boschen | CC BY-SA 4.0 |
added 6 characters in body
|
| Feb 27 at 13:33 | history | edited | Dan Boschen | CC BY-SA 4.0 |
added 215 characters in body
|
| Feb 27 at 13:07 | history | edited | Dan Boschen | CC BY-SA 4.0 |
added 2523 characters in body
|
| Feb 26 at 15:17 | history | edited | Dan Boschen | CC BY-SA 4.0 |
added 265 characters in body
|
| Feb 26 at 5:52 | history | edited | Dan Boschen | CC BY-SA 4.0 |
deleted 1189 characters in body
|
| Feb 17 at 20:21 | history | edited | Dan Boschen | CC BY-SA 4.0 |
added 690 characters in body
|
| Feb 16 at 22:48 | history | edited | Dan Boschen | CC BY-SA 4.0 |
added 4 characters in body
|
| Feb 16 at 22:38 | history | answered | Dan Boschen | CC BY-SA 4.0 |