User rep_ho

29 votes

1 answer

3k views

What does it mean that AUC is a semi-proper scoring rule?

asked Apr 11, 2018 at 16:05

27 votes

1 answer

13k views

What are the assumptions of the permutation test?

asked Dec 17, 2014 at 16:44

19 votes

2 answers

4k views

Example when using accuracy as an outcome measure will lead to a wrong conclusion

asked Sep 27, 2018 at 10:57

14 votes

1 answer

7k views

regression for angular/circular data

asked Jul 30, 2014 at 9:13

11 votes

1 answer

3k views

PCA is to CCA as ICA is to?

asked Jun 9, 2017 at 15:47

7 votes

2 answers

8k views

How to threshold multiclass probability prediction to get confusion matrix?

asked Sep 29, 2016 at 9:49

5 votes

3 answers

122 views

Is it valid to do a test only on most extreme subjects, instead of everybody?

asked May 19, 2017 at 17:48

4 votes

1 answer

645 views

Different ROC value for different packages in R, which one is correct?

asked Oct 15, 2015 at 13:45

4 votes

0 answers

87 views

Can SVM leak training data?

asked Jan 30, 2017 at 13:15

4 votes

2 answers

152 views

Can linear SVM classify samples if there is no difference in means of predictors?

asked Jan 24, 2019 at 12:20

3 votes

2 answers

1k views

partial correlation for logistic regression

asked Feb 20, 2020 at 17:05

3 votes

1 answer

375 views

What is null distribution of brier's score or logarithmic score? How to test them properly?

asked Oct 2, 2018 at 13:15

3 votes

1 answer

622 views

Different visualization of AUC than ROC curve

asked Dec 9, 2016 at 13:02

3 votes

1 answer

195 views

Looking for a refference that a cross-validation should be repeated

asked Jan 12, 2017 at 15:20

3 votes

1 answer

200 views

Is there a name for 'heteroskedasticity' but for shape, skewness or kurtosis of the distribution?

asked Jun 18, 2021 at 19:09

2 votes

0 answers

28 views

Which item to administer to improve the standard error of the item difficulty estimate the most?

asked Mar 23, 2022 at 11:26

2 votes

1 answer

694 views

Relative speed of gaussian process classification

asked Aug 3, 2015 at 13:31

2 votes

0 answers

119 views

How can lasso CCA be solved using LARS?

asked Jun 30, 2017 at 17:48

2 votes

1 answer

296 views

Why is SOM not being used? [duplicate]

asked Jul 13, 2015 at 9:20

2 votes

2 answers

6k views

Why is linear regression overestimating small values and underestimating big values?

asked Aug 16, 2018 at 14:35

2 votes

1 answer

518 views

why is calibration of my logistic regression s shaped?

asked Sep 26, 2018 at 13:39

2 votes

2 answers

2k views

How much is ROC biased towards the minority class?

asked May 30, 2016 at 11:44

2 votes

0 answers

58 views

Why does case matching introduce bias?

asked Jun 24, 2020 at 10:59

2 votes

1 answer

217 views

likelihood ratio test for logistic regression with a complete separation

asked Jan 7, 2020 at 9:57

1 vote

1 answer

31 views

Why not accounting for a factor unrelated to treatment makes p-values too conservative?

asked Apr 7, 2021 at 22:24

1 vote

0 answers

24 views

how to test if a bayesian procedure is correct?

asked May 14, 2021 at 13:07

1 vote

0 answers

136 views

What's the connection between Kendall tau and AUC ROC? [duplicate]

asked Jun 29, 2020 at 21:36

1 vote

2 answers

1k views

What is the difference between multiple kernel learning and ensemble learning?

asked Jul 15, 2015 at 14:01

1 vote

0 answers

54 views

Why use clustering + external measure for validation, instead of supervised learning?

asked Jul 13, 2015 at 9:03

1 vote

1 answer

383 views

learning shared weights

asked Oct 29, 2015 at 18:56

Stack Exchange Network

39 Questions

What does it mean that AUC is a semi-proper scoring rule?

What are the assumptions of the permutation test?

Example when using accuracy as an outcome measure will lead to a wrong conclusion

regression for angular/circular data

PCA is to CCA as ICA is to?

How to threshold multiclass probability prediction to get confusion matrix?

Is it valid to do a test only on most extreme subjects, instead of everybody?

Different ROC value for different packages in R, which one is correct?

Can SVM leak training data?

Can linear SVM classify samples if there is no difference in means of predictors?

partial correlation for logistic regression

What is null distribution of brier's score or logarithmic score? How to test them properly?

Different visualization of AUC than ROC curve

Looking for a refference that a cross-validation should be repeated

Is there a name for 'heteroskedasticity' but for shape, skewness or kurtosis of the distribution?

Which item to administer to improve the standard error of the item difficulty estimate the most?

Relative speed of gaussian process classification

How can lasso CCA be solved using LARS?

Why is SOM not being used? [duplicate]

Why is linear regression overestimating small values and underestimating big values?

why is calibration of my logistic regression s shaped?

How much is ROC biased towards the minority class?

Why does case matching introduce bias?

likelihood ratio test for logistic regression with a complete separation

Why not accounting for a factor unrelated to treatment makes p-values too conservative?

how to test if a bayesian procedure is correct?

What's the connection between Kendall tau and AUC ROC? [duplicate]

What is the difference between multiple kernel learning and ensemble learning?

Why use clustering + external measure for validation, instead of supervised learning?

learning shared weights