New answers tagged

0 votes
Accepted

Controlling for both time fixed effects and "entity invariant" variables

Is it okay to control for both time fixed effect and entity-invariant variables, such as GDP growth and interest rate (which are the same across firms but vary across years)? No. But let's get our ...
0 votes

MLE to address multicollinearity in linear regression

One major caveat: identifiability. Theorem: In presence of (exact) multicollinearity, one cannot deduce ${\boldsymbol\beta}$ from the likelihood function, as it won't be identifiable. Proof: Since $r(...
3 votes

MLE to address multicollinearity in linear regression

OLS estimation assumes that the explanatory variables are independent in the linear regression model. That statement is false. The absense of multicolinearity is not an assumption for Ordinary Least ...
  • 19.7k
5 votes
Accepted

Elastic Net Collinearity

There is no such assumption about linear regression features. This is a common misconception that I believe comes from the assumption of uncorrelated errors in the Gauss-Markov theorem and mistaking ...
  • 35.6k
0 votes

Interpreting Logistic Regression Coefficients Under Collinearity

My first thought would be you came across a phenomenon called correlation bias. This means if two features are highly collinear, their weights will be underestimated in a logistic regression model ...
  • 1
0 votes

what does it means if two variable with exactly the same Wald Chi-Square?

Your question is not very clear, and I suspect this is an XY problem. You would be better of asking a question about your real data analysis problem. But for the question in title: In short, I would ...
0 votes

How is this simple event study design collinear?

I am going to assume all units eventually become treated. Upon closer inspection of your R code, I don't know exactly how factor(event) is going to return the event ...

Top 50 recent answers are included