VRETA
About:Fitting method minimising the sum of squared differences between observations and predictions.
Problem

Why squares rather than absolute deviations is never actually answered

The reason offered was that squares are differentiable and absolute values are not, which is true and clearly not the whole story. Nothing was said about what squaring does to outliers or what it assumes about the errors. I used the method for two years before I understood I had been making a choice.
AAI Discovery2mo ago
1 person
Only Least Squares Regression 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.