Search type Search syntax
Tags [tag]
Exact "words here"
Author user:1234
user:me (yours)
Score score:3 (3+)
score:0 (none)
Answers answers:3 (3+)
answers:0 (none)
isaccepted:yes
hasaccepted:no
inquestion:1234
Views views:250
Sections title:apples
body:"apples oranges"
URL url:"*.example.com"
Favorites infavorites:mine
infavorites:1234
Status closed:yes
duplicate:no
migrated:no
wiki:no
Types is:question
is:answer
Exclude -[tag]
-apples
For more details on advanced search visit our help page
Results tagged with Search options answers only user 74500

Predictive models are statistical models whose primary purpose is to predict other observations of a system optimally, as opposed to models whose purpose is to test a particular hypothesis or explain a phenomenon mechanistically. As such, predictive models place less emphasis on interpretability and more emphasis on performance.

3
votes
To answer your overall question, you put multiple features created out of one raw feature into a linear model so that the linear model can capture non-linear relationships between the feature and resp …
answered Feb 6 '17 by Matthew Drury
5
votes
I'm going to offer the dissenting opinion on @Sympa's answer, and go with, No. It's not really well defined what you mean by explanatory power, so I'll offer a definition. A model has explanatory po …
answered Mar 17 '16 by Matthew Drury
1
vote
Consider, instead of encoding missing data by imputing $-999$, instead imputing the mean value of the non-missings in your training data. Of course, this will affect the fit of the spline. You shoul …
answered Aug 7 '15 by Matthew Drury
1
vote
You can see that the $y$-axis is labeled CV-Error, which gives a clue. Using cross validation, we can do the following: for each cross validation fold train[i], test[i]: for each model parameter …
answered Jan 14 '16 by Matthew Drury
4
votes
According to the docs: leaderboard_frame: This argument allows the user to specify a particular data frame to rank the models on the leaderboard. This frame will not be used for anything besides c …
answered Aug 3 '17 by Matthew Drury
17
votes
I think the previous answers do a good job of making important points: Parsimonious models tend to have better generalization characteristics. Parsimony is not truly a gold standard, but just a cons …
answered Jul 28 '15 by Matthew Drury
2
votes
Specification of a loss function is not sufficient to describe a machine learning algorithm, you also must describe the allowable shapes of the prediction surface. By prediction surface, I mean the g …
answered Dec 6 '18 by Matthew Drury
7
votes
This is a nice and thoughtful post, and in my working life I have observed the things you outline to be correct - the successful statisticians and scientists at my workplace are those that can step ba …
answered Jun 13 '15 by Matthew Drury
54
votes
I'll use the sklearn code, as it is generally much cleaner than the R code. Here's the implementation of the feature_importances property of the GradientBoostingClassifier (I removed some lines of co …
answered Jul 29 '15 by Matthew Drury
4
votes
It is a common misconception that a model is overfit when the training and hold out error metrics are divergent. This does tend to happen when models become overfit, but it is not a sufficient condit …
answered May 16 '16 by Matthew Drury
1
vote
The concept of residuals makes sense on any set of data for which: You can use your model to make predictions and You have a true response value on each record So, if you, for example, split your …
answered Oct 7 '15 by Matthew Drury