add ( and )

( )

add ( and )

insert ( before and ) after

to be consistent, insert * before Witten

and after (2010)

suggest to add parens before Hastie and after 2008)

add year and details even tho this is referenced above

I wonder if this subsection should be a section ... mainly so the title shows up in the outline!

I think the title of sec 2.5 should be more general, like "Predictive Modeling" and then make Recursive Partitioning the first subsection. Why? because with Recursive Partitioning the title of the entire section, it seems to hide the real meat of the section, witch I think is the New Directions ...

Is Se supposed to be "Since ... "?

Frank says this should be 0.05

"... are bootstrap ... corrected .. " Is this the start of a question?

or is the intended sentence ... "... boostrap estimates ARE corrected?

Looks like the de Mul citation is not linked, just the doi:

De Mul N, de Jong V, Cremer O ... Practical guidance for validating the predictive performance in the presence of missing data: a guide for the clinical researcher Journal of Clinical Epidemiology, 2026; 192

I must be missing something ... to me it looks like that link is to this RMS course notes ... i.e. linking to itself?

The way

suggest add hyphen, correct spelling of confidence

fast-shifted confidence

change "about" to "amount"

where is code to add data to f??

need to adjust ?font size to avoid overprinting labels in the nomogram

If these are separate steps, consider numbering them to emphasize that ...

there's a typo in the example link:

https://https//fharrell.com/post/impactpo

delete leading https://

log-normal? or log-logistic?

?? section https://hbiostat.org/rmsc/psmcase#sec-psmcase-lognorm-gof refers to log-normal not log-logistic ??

insert "to"

models to be computed

log-normal

delete dup and (unless part of sentence is missing?)

Elaborate on this!!

may "be" inconsistent

Rachel (RMS 2025 attendee) pointed out the new link for Steve Simon:

http://new.pmean.com/cyclical-trends/

eliminate space between >= and 5

CalibratioN ... suggest adding note about when to worry!

"We're going to worry about over-predicting survival when it's high and under-predicting when it's low. Frank Harrell 09:02:47 Uh, and this is the classic kind of regression to the mean. So to really… If you wanted to use this as a prognostic model. Frank Harrell 09:02:55 Predictive model, you probably go back and apply some shrinkage, or really talk to the experts to do more data reduction than I did."

Note Frank says he would not analyze this ds this way now. and there might be an error in the data

?? maybe put a note here for the reader? or maybe link to the video 5-20-2025

this is training

this is test ?

R^2 X_orig, Beta_boot, Y_orig??

R^2 "boot"?

? R^2 apparent

maybe no space before w_i

allow

add ":" after either

to make it clearer that the numbered items relate to those variables

sp: somewhat

discount??

Maybe "with" should be "when"??

as in "adjustments are needed when ..."

maybe subdivide 6.3 with 6.3.1 rms, 6.3.2 rmsb, and ? 6.3.3 the global options, etc. or maybe include that with 6.3.1?

Main point is the toc for section 6 should show a subsection for rmsb explicitly!

BooTstrap

maybe offer option to show this with vars ordered by the R^2?

why is the number 42 shown separately from the lowest interval and the second lowest?

also, wondering how to see the color associated with each interval? True, I can hover over various colors and figure out that yellow represents the highest interval ...

typo: "form" should be "from" (or maybe "using"

should be "have 1 less day"

what happened to the datamethods discussion for this chapter?

? plot title? Predicted Fat Fraction based on Height and Abdominal Circumference given Age = 43 ??

your link went to the desktop version.

Here's link to the server version (Yea Posit!) https://posit.co/products/open-source/rstudio-server/

Can't find this ?personal communication??: gus06per

You've referenced Part II twice. I suspect the first reference in this pair should be to Part I : https://doi.org/10.1002/sim.7993

??

?insert "ed." or "edition" after "second"

typo .. "as" should be "has"

insert ":" Compute by treatment: the mean time unwell

In class, Frank says day should be year,not day

discussion in class very helpful for use of cancore option in transcan

Question: ?truncate? how would that var go in the formula? You said the prediction would be flat for wbc > 40000?

someone in class suggested define effective sample size in glossary!

and m is the sample size (number of observations?

Just to clarify, some ML 'packages' (e.g. AzureML, GoogleML) consider logistic regression to be one of the ML algorithms. FWIW, I've seen (high school) science fair projects use both of those and find that logistic is "the winner" ...

if the cutoff for dichotomizing one variable is unstable, shouldn't be surprised that a tree based on cutoffs by dichotomizing multiple variables is unstable ?

insert period after cutpoints

only appears

effect is present

or better: Do Not Forget ...

?what is not recommended? ?analyses on individual completed datasets?

nonmonotonically

duplicated look

biased

trying to understand this: maybe "the difference between the treatments with the greatest difference is badly biased"

just for readability:

"disease" or "no disease" when severity of disease is actually on a continuum

Pages for Part I are actually 1262--1275

in an object if you want

typo: Some of the functions ...

but also allow for shrinkage

add some simulated post data

When it increases

Suggested edit to emphasize you don't really suggest this approach?!

"Best way" to make model fit data well is to discard much of the data!!

maybe "Change from baseline will"

the idea is to assume

question: after the plan, or after the pivotal analysis, has been completed?

*Avoid * the tendency (or "urge"!)