search

ahoshiyar / ordPens

Ordinal PCA, Selection and/or Smoothing of Ordinal Predictors
GNU General Public License v2.0
2 stars 2 forks source link

Imprecise statement? #12

Closed osorensen closed 2 years ago

osorensen commented 2 years ago

Here is another comment on the submission. In the Summary, you write

Smoothing only can be done by penalizing the sum of squared differences of adjacent coefficients.

Isn't this only correct if (1) there is only a single only variable in the model, and (2) the indicators for the different levels are properly ordered. I'm not an expert on regression with ordinal variables, but perhaps something like this would be more precise?

Smoothing only can be done by penalizing the sum of squared differences of adjacent coefficients for a given variable, subject to proper ordering.

This issue relates to https://github.com/openjournals/joss-reviews/issues/3828

ahoshiyar commented 2 years ago

Thank you, I've updated the statement :)