New answers tagged model-selection
2
votes
Build a neural network to diagnose my digestive disorders
If it seems more complex than "you eat this, you feel bad 2 hours later", how will a model that predicts 'symptoms from foods' be useful?
Think carefully about what useful model predictions ...
- 3,029
0
votes
How compute a BIC for multivariate regression?
I implemented this formula in my R package StepReg based on this paper.
"Al-Subaihi, A.A. 2002. Variable Selection in Multivariable Regression Using SAS/IML. Journal of Statistical Software. 7, ...
- 21
0
votes
Repeated Nested Cross validation
I would correct your first sentence as follows:
Nested cross-validation is used to estimate the out-of-sample performance of the prediction algorithm (true prediction error)
Repeated k-fold cross-...
- 47
0
votes
How to determine whether difference in RMSE is meaningful
To add to what the others have said, apart from the "philosophical" aspect of choosing the statistical and/or practical significance of any metric and thereby its relation with the model, if ...
- 109
1
vote
How to determine whether difference in RMSE is meaningful
In one sense, this is akin to the distinction between statistical vs. practical significance. There's no way to come up with a difference that is meaningful without taking into account the important ...
- 19.8k
4
votes
Effect of sample size on BIC
Remember that what matters is not the absolute value of BIC for one model, but the difference between two models.
Suppose you have two Gaussian models where one of them contains $p$ important ...
- 43.6k
Top 50 recent answers are included