# RMS Describing, Resampling, Validating, and Simplifying the Model

**URL:** <https://discourse.datamethods.org/t/rms-describing-resampling-validating-and-simplifying-the-model/4790>\
**Category:** modeling strategy\
**Tags:** graphics, bootstrap, validation\
**Created:** [September 14, 2021, 7:24pm UTC](https://discourse.datamethods.org/t/rms-describing-resampling-validating-and-simplifying-the-model/4790 "2021-09-14T19:24:11Z")\
**Posts on this page:** 2\
**Page:** 10

<div class="post-metadata">

**Author:** ![FurlanLeo](https://discourse.datamethods.org/user_avatar/discourse.datamethods.org/furlanleo/32/3812_2.png) [@FurlanLeo](https://discourse.datamethods.org/u/FurlanLeo)\
**Post date:** [September 12, 2025, 8:26pm UTC](https://discourse.datamethods.org/t/rms-describing-resampling-validating-and-simplifying-the-model/4790/188 "2025-09-12T20:26:19Z")

</div>

Hi @f2harrell, could you kindly help me with the following?

I’m using _rms_ 8.1-0.

`c <- calibrate(m, B = 500, group = data, kint = 10)`

How are the gray confidence lines drawn in `plot(c)`?  
The object `c` has the columns “Lower” and “Upper”. Are these values subtracted from and added to, respectively, the column “calibrated.corrected”?

What’s the level of smoothing applied? I’m having trouble replicating in ggplot the smoothed calibration curve produced by `plot(c)`.

Thank you.

---

<div class="post-metadata">

**Author:** ![f2harrell](https://discourse.datamethods.org/user_avatar/discourse.datamethods.org/f2harrell/32/165_2.png) [@f2harrell](https://discourse.datamethods.org/u/f2harrell)\
**Post date:** [September 13, 2025, 12:01pm UTC](https://discourse.datamethods.org/t/rms-describing-resampling-validating-and-simplifying-the-model/4790/189 "2025-09-13T12:01:55Z")

</div>

Type `?calibrate` to see information about the new confidence intervals or go directly to [Bootstrap Confidence Limits for Bootstrap Overfitting-Corrected Model Performance – Statistical Thinking](https://fharrell.com/post/bootcal) .`Lower` and `Upper` stand on their own. Look at the `plot.calibrate` code to see any smoothing method it uses.

[Previous page](https://discourse.datamethods.org/t/rms-describing-resampling-validating-and-simplifying-the-model/4790.md?page=9)