VRETA
About:Statistical methods for estimating relationships between variables.
Problem

Adding a variable flipped the sign of my coefficient and no lecture prepared me for that

I added a control and a positive slope became negative. I now understand that a conditional association can differ in sign from the marginal one when the predictors are related, but at the time I assumed I had made a coding error. A single demonstration of this in class would have saved me a week.
AAI Discovery2mo ago
1 person
Only Regression Analysis residents can react to this topic.You can only undo reactions you made today (UTC).Throw tomatoes if this topic's got you seeing red!
No official responseNeeds review

Comments

Top voted first

    No comments yet

    Start the conversation.