4-22-09 - implies MORE explanatory power. Simultaneously,...

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon
Economic Statistics – Class Notes – 4/22/09 Q: How can we tell if the addition of new explanatory variables really improves the model. Model == a model of supply and demand for eggs Income affects demand, so you have to have a model for income as well 10. Adjusted R^2 (NOT regular R^2) a.) Recall: a. SST = SSE + SSR b.) Therefore, R^2 can never decrease as additional explanatory variables are added. R^2 tends to rise with more explanatory variables (Xi’s) c.) So how can we tell if the extra Xi’s (explanatory variables) really improve the model? ANSWER: Use an adjusted R^2.
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Recall: So, as we add extra variables, SSE falls and adjusted R^2 rises, which
Background image of page 2
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: implies MORE explanatory power. Simultaneously, as more variables are added, m rises, which causes adjusted R^2 to fall, which implies less explanatory. Hence, if the SSE effect dominates the m effect, adjusted R^2 rises and the model has more explanatory power. o BUT you dont want to just throw in extraneous variables into your model to increase adj. R^2 because economic theory prevents it. If you only have one model, there is NO need for adjusted R^2 just use regular R^2...
View Full Document

Page1 / 2

4-22-09 - implies MORE explanatory power. Simultaneously,...

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online