The error happens after it does the calculation for the point estimates, so it's likely happening when it starts doing the calculations to look at the curvature at the solution (to see if it's a maximum rather than a saddle point and to get an estimate of standard errors). Doing
OU1 <- OUwie(tree, data, model = "OU1", diagn=FALSE) will turn off these extra diagnostics for now. Note there's a dedicated OUwie support list at https://groups.google.com/forum/#!forum/ouwie-discuss , too. People often post to dedicated lists first before R-sig-phylo, but such lists can be hard to find (I think that's true in this case) or are inactive. One other advantage of R-sig-phylo posts for help is that you're more likely to hear about other package alternatives (i.e., "Have you tried mvSLOUCH or OUCH instead?"). Best, Brian _______________________________________ Brian O'Meara Assistant Professor Dept. of Ecology & Evolutionary Biology U. of Tennessee, Knoxville http://www.brianomeara.info Students wanted: Applications due Dec. 15, annually Postdoc collaborators wanted: Check NIMBioS' website Calendar: http://www.brianomeara.info/calendars/omeara On Tue, Oct 29, 2013 at 4:20 PM, Christopher D. Muir < [email protected]> wrote: > All, > > This my first time posting to R-sig-anything, so apologies for any breach > in etiquette. I searched through the mailing list and couldnt find > anything about this problem. A brief description of my data: I am running > OUwie on a 528-taxon megatree generated using phylomatic. I made the tree > dichotomously branching using multi2di, then assigned short branch > lengths to these so that I could estimate ancestral character states > (regimes in the OU model) to each node. OUwie works fine with my dataset > for the BM1 and BMS models, but for all of the OU models, I get the same > error with the singular-value decomposition function: > > OU1 <- OUwie(tree, data, model = "OU1") > Initializing... > Finished. Begin thorough search... > Finished. Summarizing results. > Error in svd(m) : infinite or missing values in 'x' > > Im using R v. 2.15.1 and the latest OUwie v 1.33. > > I think this has something to do with the structure of my tree and/or the > frequency of regime shifts. When I replace my data with Brownian Motion > data simulated with my tree, I generally get the same error. The most > salient feature I can think of is that regime shifts are quite frequent > within the tree and there are many short branches because of resolving > polytomies. There are no NAs or anything unusual in the trait data. > > Chris > > --------------------------------------------------- > Christopher D. Muir, Biodiversity PDF > Office: BioDiv 237 > E-mail: [email protected] > > Biodiversity Research Centre > University of British Columbia > 6270 University Blvd. > Vancouver, BC, Canada > V6T 1Z4 > > > [[alternative HTML version deleted]] > > > _______________________________________________ > R-sig-phylo mailing list - [email protected] > https://stat.ethz.ch/mailman/listinfo/r-sig-phylo > Searchable archive at > http://www.mail-archive.com/[email protected]/ > [[alternative HTML version deleted]]
_______________________________________________ R-sig-phylo mailing list - [email protected] https://stat.ethz.ch/mailman/listinfo/r-sig-phylo Searchable archive at http://www.mail-archive.com/[email protected]/
