Update termplot.R

[eogoodwin]

The help page for termplot states that it adds (optionally) standard errors around the partial plots for each predictor. However, until now it has multiplied the standard error (returned by predict() function) by 2.0, to generate an approximate 95% confidence interval, rather than a standard error.

[alex7tula]

Hi.
I have question about r-source/src/library/stats/R/optim.R
About parameter control -> factr.
In description i see:

factr - controls the convergence of the "L-BFGS-B" method. Convergence occurs when the reduction in the objective is within this factor of the machine tolerance. Default is 1e7, that is a tolerance of about 1e-8.

If tolerance is 1e-8, why you set default to 1e7?
May be it is mistake? May be 1e-7 - sould be as default?

[SurajGupta]

This is a mirror of the R repo. Please see the R website for directions on how/where to ask questions

On Sat, May 19, 2018 at 4:25 AM alex7tula ***@***.***> wrote: Hi. I have question about r-source/src/library/stats/R/optim.R About parameter control -> factr. In description i see: factr - controls the convergence of the "L-BFGS-B" method. Convergence occurs when the reduction in the objective is within this factor of the machine tolerance. Default is 1e7, that is a tolerance of about 1e-8. If tolerance is 1e-8, why you set default to 1e7? May be it is mistake? May be 1e-7 - sould be as default? — You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub <#3 (comment)>, or mute the thread <https://github.com/notifications/unsubscribe-auth/ABdWoB48WaUyDrwceCr5xt_Wqo8SgHyPks5tz9bigaJpZM4RaOq8> .

-- Best Regards, Suraj http://obeautifulcode.com/