ec20-newlec6-v1

# ec20-newlec6-v1 - Economics20 Lecture#6:TowardsMultivariate...

This preview shows pages 1–9. Sign up to view the full content.

1 Economics 20 Lecture #6: Towards Multivariate  Regression Statistical Inference

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

View Full Document
2 From Last Time  MLR Assumptions MLR.1: Population Relationship… MLR.2: Random sample of data MLR.3: No perfect linear relationship between  the X’s If this fails to hold, can’t estimate (more below) MLR.4: Conditonial mean zero error, i.e. Critical for interpreting OLS (least squares)  estimates as causal. ( 29 0 , , | 1 = Ki i i X X u E i Ki K i i i i u X X X X Y + + + + + + = β β β β β 3 3 2 2 1 1 0
3 Today “Solution” to multivariate least squares which  supports the “holding constant” interpretation  of the slopes “Partialling Out” – Frisch-Waugh Theorem “Bivariate” vs multivariate” or “short vs long”  regression Too few X’s   “omitted variables” bias Towards Statistical inference: Standard Errors

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

View Full Document
4 Multivariate OLS estimates Estimated OLS relationship:                                                     i.e., a partial derivative: treats all the other  variables as constants A one unit increase in x 1  is associated with  a     unit increase in y, holding constant x 2 x 3 …x K Ki K i i i x x x y β β β β ˆ ˆ ˆ ˆ ˆ 2 2 1 1 0 + + + + = i i x y 1 1 ˆ ˆ = β 1 ˆ β
5 A “Partialling Out” Interpretation Frisch-Waugh Theorem .  The OLS  estimator for     can be written as where     is the residuals from a regression  of x 1  on all of the other x’s In other words, the following two steps  deliver the same slope as multiple  regression: 1. Regress x 1  on x 2  … x k , get residuals 2. Regress y on residuals     (bivariate) 1 ˆ β 1 ˆ i r ( 29 ( 29 1 1 1 ˆ var , ˆ cov ˆ i i i r y r = β 1 ˆ i r 1 ˆ i r

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

View Full Document
STATA Example… Also good for creating partial scatter plots 6
7 A “Partialling Out” Interpretation In other words, the slope on x 1  from a  multiple regression literally “takes out” the  influence of (a linear function of) x 2 …x k Only the part of x 1 ’s variation unrelated to x 2 x k  is being related to y Why we need assumption MLR.3: if there were a  perfect linear relationship between x 1  and rest of  the x’s, then there would be no variation left over  to relate to y!   ( 29 0 ˆ 1 = i r Var

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

View Full Document
8 Too Many or Too Few Variables What happens if we include variables in our specification that do not belong? There is no effect on our parameter estimate, and OLS remains unbiased However later we will learn this is inefficient (makes standard errors bigger) What if we exclude a variable from our specification that does belong?
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### What students are saying

• As a current student on this bumpy collegiate pathway, I stumbled upon Course Hero, where I can find study resources for nearly all my courses, get online help from tutors 24/7, and even share my old projects, papers, and lecture notes with other students.

Kiran Temple University Fox School of Business ‘17, Course Hero Intern

• I cannot even describe how much Course Hero helped me this summer. It’s truly become something I can always rely on and help me. In the end, I was not only able to survive summer classes, but I was able to thrive thanks to Course Hero.

Dana University of Pennsylvania ‘17, Course Hero Intern

• The ability to access any university’s resources through Course Hero proved invaluable in my case. I was behind on Tulane coursework and actually used UCLA’s materials to help me move forward and get everything together on time.

Jill Tulane University ‘16, Course Hero Intern