Hi all, I am receiving the error *Newton failed to find minimum* whilst trying to fit a move persistence model in this package. I think the error is related to the optimiser in the TMB package but it is beyond my statistics/coding knowledge to track down the specific cause and solution. I would appreciate it if anyone knew some resources to assist with fixing this. I have put a MRE and sample data over on Stackoverflow if anyone wants a closer look - https://stackoverflow.com/questions/75253642/how-do-i-fix-newton-failed-to-find-minimum-in-r --
aniMoutm/foiegras Assistance
3 messages · ZAC WARHAM, Roy Mendelssohn - NOAA Federal, Bert Gunter
2 days later
Hi Zac: Two suggestions. In the map statement, set silent = FALSE, hopefully that will give you more info, The second is to try what is suggested in the error message, " Try simplifying the model with the following argument: map = list(rho_o = factor(NA))". I don't know what rho_o does, but it might be a first step to figuring things out/ HTH, -Roy
On Jan 27, 2023, at 12:42 PM, ZAC WARHAM <zac.warham at students.mq.edu.au> wrote: Hi all, I am receiving the error *Newton failed to find minimum* whilst trying to fit a move persistence model in this package. I think the error is related to the optimiser in the TMB package but it is beyond my statistics/coding knowledge to track down the specific cause and solution. I would appreciate it if anyone knew some resources to assist with fixing this. I have put a MRE and sample data over on Stackoverflow if anyone wants a closer look - https://stackoverflow.com/questions/75253642/how-do-i-fix-newton-failed-to-find-minimum-in-r -- [[alternative HTML version deleted]]
______________________________________________ R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.
********************** "The contents of this message do not reflect any position of the U.S. Government or NOAA." ********************** Roy Mendelssohn Supervisory Operations Research Analyst NOAA/NMFS Environmental Research Division Southwest Fisheries Science Center ***Note new street address*** 110 McAllister Way Santa Cruz, CA 95060 Phone: (831)-420-3666 Fax: (831) 420-3980 e-mail: Roy.Mendelssohn at noaa.gov www: https://www.pfeg.noaa.gov/ "Old age and treachery will overcome youth and skill." "From those who have been given much, much will be expected" "the arc of the moral universe is long, but it bends toward justice" -MLK Jr.
The obvious: all optimization procedures can be subject to such errors, and simplifying models and/or weakening the criteria for stopping (increasing step size, increasing the delta of the change in value that signals convergence, trying different starting values for the parameters, etc.) are more or less standard procedures to get convergence. It can be tricky -- numerical optimization is part art as well as science. If you don't get a satisfactory reply here or at SO, you might wish to contact the package maintainer: see ?maintainer. Cheers, Bert On Sun, Jan 29, 2023 at 2:53 PM ZAC WARHAM <zac.warham at students.mq.edu.au> wrote:
Hi all, I am receiving the error *Newton failed to find minimum* whilst trying to fit a move persistence model in this package. I think the error is related to the optimiser in the TMB package but it is beyond my statistics/coding knowledge to track down the specific cause and solution. I would appreciate it if anyone knew some resources to assist with fixing this. I have put a MRE and sample data over on Stackoverflow if anyone wants a closer look - https://stackoverflow.com/questions/75253642/how-do-i-fix-newton-failed-to-find-minimum-in-r -- [[alternative HTML version deleted]]
______________________________________________ R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.