Frank Harrell

You have too many parameters in the model.

I'm using what I thought was the latest version of R, 3.2.2. How are you using 3.2.3?

I had forgotten to update my package source list for Ubuntu linux. I just did so and installed R 3.2.3. I was able to do library(Hmisc) with no problem using...

I will need help with a code fix for this. It's best to do a Github pull and then have the system send me a merge request.

Please provide a reproducible example that does not throw any errors before `predict()`, i.e., where you properly `require(rms)` or `library(rms)` at the beginning of the code R can find `label

latex.default does not handle this very well. You can get blank column headings by specifying colheads='' but my guess is that is not what you want. I assume that "no...

Please don't fork the package until I get a chance to correct simple errors. I tried running your script but received an error before getting to time-dependent covariates with cph:...

rms was not designed to work with less-than-full-rank models so don't change anything related to how the different terms are recognized. This will likely break something else. Frank On 08/24/2014...

It's too bad that rms needs you to do it that way but that is probably the most expedient solution. On 08/27/2014 10:32 AM, Max Gordon wrote: > Ok, thank...

See the `insert.bottom` argument to `latex.summaryM`