User Demetri Pananos

74 votes

When to remove insignificant variables?

answered Jun 18, 2019 at 16:29

58 votes

What are the worst (commonly adopted) ideas/principles in statistics?

answered Jul 10, 2020 at 4:00

35 votes

How can I determine which of two sequences of coin flips is real and which is fake?

answered May 7, 2022 at 2:45

33 votes

Accepted

Why do we care more about test error than expected test error in Machine Learning?

answered Jul 28, 2021 at 12:20

33 votes

What percentage of a population needs a test in order to estimate prevalence of a disease? Say, COVID-19

answered Apr 16, 2020 at 4:48

32 votes

Accepted

In regression, why not use regularization by default?

answered Jan 2, 2020 at 21:08

32 votes

Accepted

How to choose "family" in Generalized Additive Model (GAM)

answered Mar 20, 2019 at 15:51

28 votes

Accepted

Significance test for two groups with dichotomous variable

answered Mar 26, 2021 at 2:52

24 votes

What are the worst (commonly adopted) ideas/principles in statistics?

answered Jul 10, 2020 at 4:11

24 votes

Accepted

Can an irrelevant variable be significant in a regression model?

answered Jun 20, 2022 at 4:10

24 votes

Accepted

Does every variable need to be statistically significant in a regression model?

answered Oct 18 at 3:35

22 votes

Why does Machine Learning need a lot of data while one can do statistical inference with a small set of data?

answered Apr 20, 2022 at 16:21

22 votes

What if my linear regression data contains several co-mingled linear relationships?

answered Jan 28, 2019 at 14:41

21 votes

Accepted

Do test scores really follow a normal distribution?

answered Nov 12, 2018 at 1:27

20 votes

Accepted

Stepwise binary logistic regression, Forward or Backward?

answered Feb 23, 2023 at 3:49

19 votes

Why do we never learn cross validation in regular statistical textbooks?

answered Sep 27, 2021 at 22:21

19 votes

Are linear regression and least squares regression necessarily the same thing?

answered May 11, 2021 at 12:29

18 votes

Accepted

Statsmodels Logistic Regression: Adding Intercept?

answered Dec 10, 2019 at 19:17

18 votes

Why do you take the sqrt of 1/n for RMSE?

answered Jun 1, 2022 at 20:54

18 votes

Accepted

Causal diagrams necessary in randomized controlled trials?

answered Dec 22, 2023 at 5:21

17 votes

Why does Harrell Argue for "Ignoring Y during data reduction"?

answered Jan 25 at 22:24

17 votes

Is linear regression still relevant in a mid-level DS interview?

answered Mar 12 at 1:30

17 votes

Accepted

What can be done about assumption violations in logistic regression?

answered May 3, 2022 at 2:27

17 votes

How to learn statistics for medical research?

answered Jan 12, 2022 at 21:39

17 votes

Accepted

What are the best ways to generate Bayesian prior estimates using beliefs of non-statisticians?

answered Dec 4, 2019 at 0:13

17 votes

Accepted

Dichotomizing continuous variables at their optimal cut-off for clinical interpretation

answered Jan 13, 2020 at 23:51

17 votes

Accepted

Feature selection for Logistic Regression

answered Feb 27, 2020 at 5:41

17 votes

Accepted

ANOVA vs pairwise t-tests with multiple test correction

answered Nov 11, 2018 at 21:12

17 votes

Accepted

Why do parameters go untested in Machine Learning?

answered Apr 12, 2021 at 0:59

16 votes

Accepted

Unable to get correct coefficients for logistic regression in simulated dataset

answered Apr 11, 2021 at 23:12

Stack Exchange Network

1,043 Answers

When to remove insignificant variables?

What are the worst (commonly adopted) ideas/principles in statistics?

How can I determine which of two sequences of coin flips is real and which is fake?

Why do we care more about test error than expected test error in Machine Learning?

What percentage of a population needs a test in order to estimate prevalence of a disease? Say, COVID-19

In regression, why not use regularization by default?

How to choose "family" in Generalized Additive Model (GAM)

Significance test for two groups with dichotomous variable

What are the worst (commonly adopted) ideas/principles in statistics?

Can an irrelevant variable be significant in a regression model?

Does every variable need to be statistically significant in a regression model?

Why does Machine Learning need a lot of data while one can do statistical inference with a small set of data?

What if my linear regression data contains several co-mingled linear relationships?

Do test scores really follow a normal distribution?

Stepwise binary logistic regression, Forward or Backward?

Why do we never learn cross validation in regular statistical textbooks?

Are linear regression and least squares regression necessarily the same thing?

Statsmodels Logistic Regression: Adding Intercept?

Why do you take the sqrt of 1/n for RMSE?

Causal diagrams necessary in randomized controlled trials?

Why does Harrell Argue for "Ignoring Y during data reduction"?

Is linear regression still relevant in a mid-level DS interview?

What can be done about assumption violations in logistic regression?

How to learn statistics for medical research?

What are the best ways to generate Bayesian prior estimates using beliefs of non-statisticians?

Dichotomizing continuous variables at their optimal cut-off for clinical interpretation

Feature selection for Logistic Regression

ANOVA vs pairwise t-tests with multiple test correction

Why do parameters go untested in Machine Learning?

Unable to get correct coefficients for logistic regression in simulated dataset