Comment on Gauss-Markov-Style meme
montechristo@feddit.org 3 days ago
To the practicing statisticians out there: Is BLUE at all relevant in the field? Even if you can formulate your data/problem as a linear regression, wouldn’t maximum likelihood estimation still be the preferred method in most scenarios?
merari42@lemmy.world 3 days ago
OLS is well used in a lot of domains. If you have a continuous outcome you have a straightforward and very easy way to get a quick reliable estimate of some interesting parameter. The typical use in most social sciences is to implement some sort of difference-in-differences (or DiD event-study) estimate within a simple linear regression.