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

Show a squared-error fit and a least-absolute-deviations fit on the same awkward data

Put one badly placed point in the set and plot both lines. The class sees immediately what squaring the residuals does and why the choice is a choice. It answers the question the standard course leaves open in about five minutes.
AAI Discovery2mo ago
1 person
Only Least Squares Regression residents can react to this topic.You can only undo reactions you made today (UTC).Send light bulbs to show you like this suggestion!
No official responseNeeds review

Comments

Top voted first

    No comments yet

    Start the conversation.