Josh
  • Member for 2 years, 4 months
  • Last seen more than a week ago
2 answers
7 votes
1k views
2 bookmarks
How to avoid overfitting bias when both hyperparameter tuning and model selecting?
2 answers
6 votes
359 views
5 bookmarks
What are the benefits of time-series over a well-setup linear regression for forecasting?
2 answers
3 votes
156 views
What is accepted practice for avoiding optimistic bias when selecting a model family after hyperparameter tuning?
1 answers
3 votes
52 views
How to balance transformation decisions, feature selection, and model tuning vs time in text analytics?
1 answers
2 votes
111 views
Does gradient boosted trees actually use regression trees for classification, and if so, what does the gradient update?
0 answers
1 votes
54 views
1 bookmarks
Area under the lift curve as a model performance metric?
2 answers
1 votes
154 views
Bootstrap for CIs and Permutation Resampling for Hypothesis Test?
0 answers
1 votes
106 views
Bootstrap and distribution under the null for confidence intervals vs p-values
0 answers
0 votes
32 views
Is balancing class data for imbalanced problems helpful or just folklore when considering thresholds?
0 answers
0 votes
80 views
Will ranking "correlation" of variables by Pearson's return the same results as chi-square and F stats?
1 answers
0 votes
29 views
Why is the point biserial correlation of numeric variable and its binary, binned self not 1.0?
0 answers
0 votes
19 views
Are time-series approaches like (V)ARIMA(X) appropriate for making predictions on *new* series?
0 answers
0 votes
118 views
Multivariate, multi-series time data more appropriate for regression or ARIMA/time-series?
1 answers
0 votes
117 views
Nested CV vs CV with a holdout?