Closed smjenness closed 9 years ago
I'm also not seeing what the problem is in the latticeplot MCMC diagnostic screenshot you uploaded. (sorry if i'm missing something obvious)
On Tue, 8 Sep 2015, Samuel Jenness wrote:
screen shot 2015-09-08 at 10 35 32 am
— Reply to this email directly or view it on GitHub.[AH0J4k6G0dT4o2yLXPuNgBFpkzVbrX4Vks5ovpV-gaJpZM4F5VUS.gif]
Professor of Sociology and Statistics Director, UWCFAR Sociobehavioral and Prevention Research Core Box 354322 University of Washington Seattle, WA 98195-4322
Office: (206) 685-3402 Dept Office: (206) 543-5882, 543-7237 Fax: (206) 685-7419
morrism@u.washington.edu http://faculty.washington.edu/morrism/
Compare to Slide 34 here: http://statnet.github.io/nme/d2-s1.pdf
so, missing the blue color, and using a histogram instead of the continuous distn for the edges?
On Tue, 8 Sep 2015, Samuel Jenness wrote:
Compare to Slide 34 here: http://statnet.github.io/nme/d2-s1.pdf
— Reply to this email directly or view it on GitHub.[AH0J4q-rsIA3XFdIU2HS8LVbbzul-YBwks5ovtXngaJpZM4F5VUS.gif]
Professor of Sociology and Statistics Director, UWCFAR Sociobehavioral and Prevention Research Core Box 354322 University of Washington Seattle, WA 98195-4322
Office: (206) 685-3402 Dept Office: (206) 543-5882, 543-7237 Fax: (206) 685-7419
morrism@u.washington.edu http://faculty.washington.edu/morrism/
Sorry, let me be more precise: ergm has the suggested package lattice, which is used by mcmc.diagnostics to generate the two panel plots of MCMC mixing and the final distribution shape. When that package is not loaded correctly, ergm defaults to use the base plotting methods (screen shot from above); the difference is mainly cosmetic but did raise some confusion about differences between the slides in the workshop.
Thanks. Moving the lattice packages to Imports so that they will be installed with the statnetWeb package. This will take effect with the next CRAN release.