As before for the n-nearest-neigbors method, I think the first use of logistic regression requires a short explanation, in particular because the name is not at all self-explanatory.
Just above, we added a note:
In short, these models find a set of weights to combine each column in the data matrix to predict the target. For instance, the model can come up with rules such as 0.1 * age + 3.3 * hours-per-week - 15.1 > 0.5 means that high-income is predicted.
We did not wanted to go more into details regarding the model. Do you think that the explanation is not enough?
That note explains “linear” but not “logistic”. To anyone unfamiliar with the technical meaning of the term, it suggests a relation to logistics.
We had an exercice in the Reproducible Research MOOC that used logistic regression. Many students didn’t even attempt to do it because they didn’t know what logistic regression is. Unfamiliar terms can be very scary when they come from mathematics.
I added a few words explaining that the logistic regression will be covered in more details in the Linear Models module and that for now the focus is to use it rather than understand its internals.
I did some related rewording as well which hopefully makes the introduction of the logistic regression a bit less scary.
1 Like