Aja Carter
2017-11-28 20:26:10 UTC
I am using the ancThresh model in the phytools package for 172 taxa. The
model finished running: I have the liabilities, parameters, MCMC and alpha
values output. The alpha value shows convergence of the model. However when
I tried getting DIC values from the threshDIC function I got Infs for both
the OU model and the Lambda model.The error output I have been receiving is
**** NOTE: no sequence provided, column order in x
Error in start:nrow(mcmc$par) : argument of length 0
2109.678 Inf -Inf -Inf
Any help or guidance you could provide would be greatly appreciated.
Thank you
--
Aja Carter
PhD Candidate
Department of Earth and Environmental Sciences
University of Pennsylvania
[[alternative HTML version deleted]]
_______________________________________________
R-sig-phylo mailing list - R-sig-***@r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-phylo
Searchable archive at http://www.mail-archive.com/r-sig-***@r-project.org/
model finished running: I have the liabilities, parameters, MCMC and alpha
values output. The alpha value shows convergence of the model. However when
I tried getting DIC values from the threshDIC function I got Infs for both
the OU model and the Lambda model.The error output I have been receiving is
BMThreshDIC <-threshDIC(scaled.tree, AT.data, ancestralBM,
burnin=20000000)**** NOTE: no sequence provided, column order in x
Error in start:nrow(mcmc$par) : argument of length 0
BMThreshDIC <-threshDIC(scaled.tree, AT.data, ancestralBM, burnin=2000000)
**** NOTE: no sequence provided, column order in xOUThreshDIC
Dbar Dhat pD DIC2109.678 Inf -Inf -Inf
Any help or guidance you could provide would be greatly appreciated.
Thank you
--
Aja Carter
PhD Candidate
Department of Earth and Environmental Sciences
University of Pennsylvania
[[alternative HTML version deleted]]
_______________________________________________
R-sig-phylo mailing list - R-sig-***@r-project.org
https://stat.ethz.ch/mailman/listinfo/r-sig-phylo
Searchable archive at http://www.mail-archive.com/r-sig-***@r-project.org/