Bavo (De Cock) Campo

I got the same error and was able to fix it using: ``` explanation

Hi Reinier, Thank you submitting the issue and sorry for the late reply. It's currently a busy period, so unfortunately I do not have a lot of time the coming...

Hi, One of the reasons could be that the Loess functions results in an error due tot the size of the data set. Can you try setting the smooth argument...

Hi Raphaël, The error you get was due to an error in the previous version of the package. If you update the package, you should no longer see this error...

Hi Reinier, Raphaël, Could you help me with debugging by running the following block of code with your data sets? `y` is the vector with the values for the outcome...

Many thanks Raphaël!! This helps me to pinpoint the problematic parts in the code. As you noticed, the main problem with loess is the calculation of the standard errors which...

One additional remark. In this situation, we cannot estimate the standard errors using loess, but we are able to estimate the flexible calibration curve itself. I would compare the flexible...

Hi Raphaël, Happy to hear that the paper has been helpful in understanding! Harrell's val.prob does indeed use the same logistic calibration framework, but there is a difference in how...

Hi Fred, My apologies for the late response, I was out of office. Where in the code does the issue occur? Is it the glm/lrm.fit function that returns this error...

Hi Federico, This sounds like an interesting idea! I haven't heard of it before, but it definitely sounds useful. I added it to my to-do list. Which references would you...