User Noah

57 votes

Accepted

Why do we do matching for causal inference vs regressing on confounders?

answered Sep 17, 2021 at 6:41

49 votes

Accepted

Propensity score matching - What is the problem?

answered Aug 1, 2020 at 19:28

26 votes

Is Propensity Score Matching a "MUST" for Scientific Studies?

answered Jan 7, 2022 at 4:51

25 votes

Raw or orthogonal polynomial regression?

answered Oct 26, 2019 at 0:53

23 votes

Representing interaction effects in directed acyclic graphs

answered Jun 6, 2018 at 19:22

20 votes

Strong ignorability: confusion on the relationship between outcomes and treatment

answered Jun 29, 2020 at 19:29

20 votes

Accepted

If X=Y+Z, Is it ever useful to regress X on Y?

answered Jun 9, 2022 at 14:55

19 votes

Accepted

What are the pros and cons of using mahalanobis distance instead of propensity scores in matching

answered Feb 27, 2021 at 2:50

18 votes

Accepted

Slight inconsistency between probability estimated from logistic regression and manual calculation from cross table

answered Aug 8 at 15:46

17 votes

If p-value is exactly 1 (1.0000000), what should the confidence interval limits be to support null hypothesis being true?

answered Sep 2, 2019 at 23:55

16 votes

Accepted

Should I use a machine learning model to calculate propensity score?

answered Aug 7, 2019 at 19:54

14 votes

Accepted

Do I need to adjust OLS standard errors after matching?

answered Oct 20, 2020 at 18:29

13 votes

Accepted

Why are exponentiated logistic regression coefficients considered "odds ratios"?

answered Aug 9, 2018 at 18:48

13 votes

Accepted

Difference Omitted Variable Bias and Confounding?

answered Nov 13, 2020 at 21:52

13 votes

Accepted

Why is Propensity Score Matching better than just Matching?

answered Feb 11, 2021 at 18:27

12 votes

Accepted

In R, how do I test $H_0: \beta_1+\beta_2=0$

answered Aug 8, 2019 at 21:45

12 votes

Accepted

What are some examples when the Average Treatment Effect on the Treated/Control (ATT,ATC) is more sought after than the ATE?

answered Apr 29, 2021 at 21:19

12 votes

Accepted

Simulated data for logistic regression

answered Sep 29, 2022 at 15:17

11 votes

Correlation is scale invariant but my math doesn't work out

answered Jan 13, 2020 at 3:07

11 votes

Accepted

How exactly to evaluate Treatment effect after Matching?

answered May 3, 2019 at 13:18

11 votes

Accepted

Why doesn't this work as a backdoor?

answered Apr 23, 2021 at 16:29

11 votes

Accepted

Causal Inference When Treatment Assignment is Fully-Known But Not Randomized

answered Nov 12 at 21:39

11 votes

Is it possible to use propensity score matching (or something similar) to create a control group if you do not yet have outcome data?

answered Sep 1, 2022 at 21:25

11 votes

Linear regression's (OLS) coefficient interpretation with heteroscedasticity

answered May 22, 2022 at 19:22

10 votes

Why is the intercept changing in a logistic regression when all predictors are standardized?

answered Oct 2, 2019 at 5:50

10 votes

Accepted

Matching with Multiple Treatments

answered Apr 25, 2019 at 18:06

10 votes

Accepted

Propensity score matching vs non-parametric regression

answered Oct 30, 2020 at 3:46

10 votes

Accepted

Interpretation of coefficients in a poorly performing GLM

answered Jun 16, 2020 at 19:28

10 votes

Choosing $m$ value when using multiple imputation (MI)

answered Feb 7 at 19:11

9 votes

Accepted

Is Coarsened Exact Matching superior to other matching methods in case-control studies?

answered Apr 24, 2020 at 22:47

Stack Exchange Network

875 Answers

Why do we do matching for causal inference vs regressing on confounders?

Propensity score matching - What is the problem?

Is Propensity Score Matching a "MUST" for Scientific Studies?

Raw or orthogonal polynomial regression?

Representing interaction effects in directed acyclic graphs

Strong ignorability: confusion on the relationship between outcomes and treatment

If X=Y+Z, Is it ever useful to regress X on Y?

What are the pros and cons of using mahalanobis distance instead of propensity scores in matching

Slight inconsistency between probability estimated from logistic regression and manual calculation from cross table

If p-value is exactly 1 (1.0000000), what should the confidence interval limits be to support null hypothesis being true?

Should I use a machine learning model to calculate propensity score?

Do I need to adjust OLS standard errors after matching?

Why are exponentiated logistic regression coefficients considered "odds ratios"?

Difference Omitted Variable Bias and Confounding?

Why is Propensity Score Matching better than just Matching?

In R, how do I test $H_0: \beta_1+\beta_2=0$

What are some examples when the Average Treatment Effect on the Treated/Control (ATT,ATC) is more sought after than the ATE?

Simulated data for logistic regression

Correlation is scale invariant but my math doesn't work out

How exactly to evaluate Treatment effect after Matching?

Why doesn't this work as a backdoor?

Causal Inference When Treatment Assignment is Fully-Known But Not Randomized

Is it possible to use propensity score matching (or something similar) to create a control group if you do not yet have outcome data?

Linear regression's (OLS) coefficient interpretation with heteroscedasticity

Why is the intercept changing in a logistic regression when all predictors are standardized?

Matching with Multiple Treatments

Propensity score matching vs non-parametric regression

Interpretation of coefficients in a poorly performing GLM

Choosing $m$ value when using multiple imputation (MI)

Is Coarsened Exact Matching superior to other matching methods in case-control studies?