User Adrian

20 votes

2 answers

545 views

Can regularization be helpful if we are interested only in modeling, not in forecasting?

asked Mar 29, 2016 at 16:44

18 votes

2 answers

6k views

Are SHAP values potentially misleading when predictors are highly correlated?

asked Jul 22, 2021 at 23:43

15 votes

2 answers

3k views

You observe k heads out of n tosses. Is the coin fair?

asked Apr 29, 2014 at 13:53

8 votes

2 answers

7k views

Number of distinct bootstrap samples

asked Jul 11, 2014 at 19:34

8 votes

1 answer

255 views

Autocorrelation of concatenated independent AR(1) processes

asked Mar 26, 2016 at 12:08

8 votes

1 answer

798 views

Is there a parametric joint distribution such that $X$ and $Y$ are both uniform and $\mathbb{E}[Y \;|\; X]$ is linear?

asked Jan 23, 2017 at 19:47

8 votes

1 answer

13k views

References on number of features to use in Random Forest Regression

asked Jan 22, 2018 at 5:09

8 votes

3 answers

439 views

Using regression weights when $Y$ might be measured with nonzero-mean measurement error

asked Jan 30, 2019 at 23:14

8 votes

1 answer

359 views

References on data partitioning (cross-validation, train/val/test set construction) when data are non-IID

asked Feb 11, 2022 at 22:54

7 votes

1 answer

364 views

Tversky and Kahneman eye color problem

asked Oct 24, 2016 at 20:22

7 votes

1 answer

3k views

Is is possible for a gradient boosting regression to predict values outside of the range seen in its training data?

asked Sep 26, 2017 at 2:49

6 votes

2 answers

2k views

What is the population minimizer for Huber loss

asked Aug 17, 2017 at 0:27

6 votes

1 answer

230 views

"Only if" and "if" direction in Kolmogorov's Existence Theorem

asked Feb 12, 2015 at 18:21

6 votes

2 answers

449 views

Simple constant-width prediction interval for a regression model

asked May 18, 2021 at 21:05

5 votes

1 answer

324 views

Is the likelihood for Gaussian mixture models still multimodal when Y is partially observed?

asked Mar 31, 2022 at 23:35

5 votes

2 answers

895 views

Non-informative prior for regression model

asked Jul 12, 2014 at 15:48

5 votes

1 answer

1k views

What is the M-step for Expectation Maximization for a multivariate Gaussian hidden Markov model with missing observations?

asked Aug 12, 2016 at 17:34

5 votes

0 answers

113 views

Trading signals example from Marginal Revolution blog

asked Sep 24, 2016 at 16:59

5 votes

1 answer

480 views

Derivation of Procrustes transformation

asked Aug 13, 2018 at 2:43

4 votes

2 answers

3k views

Expected value of latent utility in logistic regression [duplicate]

asked Apr 28, 2013 at 16:00

4 votes

0 answers

314 views

Catalan numbers and gambler's ruin paths

asked Nov 9, 2015 at 14:39

4 votes

1 answer

406 views

How could this NYT graphic be improved?

asked Feb 16, 2020 at 1:14

4 votes

1 answer

70 views

Martingale property & limiting distribution for frequency of last names

asked Mar 17, 2021 at 22:37

2 votes

1 answer

99 views

Probability that two specific people are selected for IRS audit within 4 year period

asked Jul 7, 2022 at 0:43

2 votes

1 answer

311 views

How to distinguish two versions of R-squared calculated on test set?

asked Mar 30, 2022 at 20:33

1 vote

0 answers

27 views

When fitting a Cox proportional hazards model, should we drop any observations that are right-censored at zero?

asked Jul 25 at 22:55

1 vote

0 answers

60 views

Maximum likelihood estimation when the model is misspecified (and the true data generating process is a mixture model)

asked Oct 27, 2021 at 6:50

1 vote

0 answers

45 views

References on simulating a raster with spatial dependence

asked Jan 27, 2018 at 6:22

1 vote

0 answers

1k views

Ridge regression / regularization approach to hierarchical model

asked Mar 1, 2018 at 1:47

1 vote

0 answers

562 views

Power calculation for t-test for difference in binomial proportions

asked Nov 2, 2017 at 23:49

Stack Exchange Network

30 Questions

Can regularization be helpful if we are interested only in modeling, not in forecasting?

Are SHAP values potentially misleading when predictors are highly correlated?

You observe k heads out of n tosses. Is the coin fair?

Number of distinct bootstrap samples

Autocorrelation of concatenated independent AR(1) processes

Is there a parametric joint distribution such that $X$ and $Y$ are both uniform and $\mathbb{E}[Y \;|\; X]$ is linear?

References on number of features to use in Random Forest Regression

Using regression weights when $Y$ might be measured with nonzero-mean measurement error

References on data partitioning (cross-validation, train/val/test set construction) when data are non-IID

Tversky and Kahneman eye color problem

Is is possible for a gradient boosting regression to predict values outside of the range seen in its training data?

What is the population minimizer for Huber loss

"Only if" and "if" direction in Kolmogorov's Existence Theorem

Simple constant-width prediction interval for a regression model

Is the likelihood for Gaussian mixture models still multimodal when Y is partially observed?

Non-informative prior for regression model

What is the M-step for Expectation Maximization for a multivariate Gaussian hidden Markov model with missing observations?

Trading signals example from Marginal Revolution blog

Derivation of Procrustes transformation

Expected value of latent utility in logistic regression [duplicate]

Catalan numbers and gambler's ruin paths

How could this NYT graphic be improved?

Martingale property & limiting distribution for frequency of last names

Probability that two specific people are selected for IRS audit within 4 year period

How to distinguish two versions of R-squared calculated on test set?

When fitting a Cox proportional hazards model, should we drop any observations that are right-censored at zero?

Maximum likelihood estimation when the model is misspecified (and the true data generating process is a mixture model)

References on simulating a raster with spatial dependence

Ridge regression / regularization approach to hierarchical model

Power calculation for t-test for difference in binomial proportions