Ch3 Woolridge: Multiple Regression Analysis: estimation Flashcards
What is multicollinearity?
two or more independent variables are strongly correlated to one another
Why is it a problem?
When predictors are too similar:
It confuses the model because it can’t decide which variable is really doing the work.
The results become less reliable.
It’s like asking two friends for advice, but they both tell you the same thing. You’re not getting extra help—you’re just hearing the same idea twice!
A way to tell if this is a problem is with the help of variance inflation factor.
What is the omitted variable bias?
Omitted variable bias happens when you leave out an important variable in your regression model, and that missing variable is related to both your predictor (independent variable) and your outcome (dependent variable). This makes your results incorrect or biased
What is the variance inflation factor?
The Variance Inflation Factor (VIF) measures how much a predictor (independent variable) in a regression model is “overlapping” or correlated with other predictors. It tells you if multicollinearity (predictors being too similar) is a problem.
VIF < 10: The predictors are not stepping on each other’s toes too much, so your model is fine.
VIF > 10: Your predictors are too similar, and it’s hard for the model to figure out which one is doing the work.
