Timeline for Difficulties reproducing an R-blogger's example of modelling dependency with copulas
Current License: CC BY-SA 4.0
11 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 3 at 22:45 | history | edited | Antoni Parellada | CC BY-SA 4.0 |
deleted 160 characters in body
|
| Jan 3 at 20:28 | answer | added | Lynchian | timeline score: 1 | |
| Jun 22, 2021 at 11:11 | comment | added | Maryam |
Try to change the optim.method and choose a good starting value as mentioned by @ChrisHaug. Also, for pobs it is good to useties.method="random") to handle any problem on ties if present.
|
|
| Jun 17, 2021 at 14:04 | comment | added | Chris Haug |
The data is typical of a t copula with very low degrees of freedom (near 1), and the optimizer is failing because you haven't set good starting parameters and it's using some default ones. If you set decent ones (e.g. start = c(4, 0.35)), you'll get somewhere.
|
|
| Jun 17, 2021 at 13:05 | history | edited | Richard Hardy | CC BY-SA 4.0 |
edited tags
|
| Jun 17, 2021 at 12:42 | comment | added | Antoni Parellada |
@AccidentalStatistician > length(GOOGL) [1] 16626 Is that too long?
|
|
| Jun 17, 2021 at 12:36 | comment | added | Accidental Statistician |
logL will refer to log-likelihoods, so the copula fitting is running into the data having a very small likelihood. Simple examples where that can happen are there being no data (i.e. cree are google is zero-length), or the data being so large that the likelihood has to be so small that R treats it as zero. I can't say anything more specific without knowing more about how fitCopula works, I'm afraid.
|
|
| Jun 17, 2021 at 12:23 | comment | added | Antoni Parellada |
@AccidentalStatistician Does that mean that under fitCopula() there are values too close to zero, and yield - infinity values when log transformed? Do you address that by placing a floor on the values?
|
|
| Jun 17, 2021 at 11:48 | review | Close votes | |||
| Jul 8, 2021 at 3:02 | |||||
| Jun 17, 2021 at 11:14 | comment | added | Accidental Statistician |
fn is the second argument for optim, which here is logL.
|
|
| Jun 17, 2021 at 10:53 | history | asked | Antoni Parellada | CC BY-SA 4.0 |