Key - Problem Set 4 2011

# Key - Problem Set 4 2011 - Problem Set 4 Due Econometrics I...

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

Problem Due 3/3/ 1. Suppo Unfortun conseque variabilit Some equ a. How w explanati Let’s che and subs 1 a Now, tak E Well hec absolute variable, average, populati distribut amount the para coefficie b. The ap is the est Start wit either a numerat The num Var(a 1 ) < Set 4 /11 ose you estim nately, the tru ences for our ty of a 1 ? uations: 1 a will the estim ion. eck, by dete stitute the t 1 2 1 ii i x Y x ke the expec 11 [] E a ck, that does ely no correl , so our SLM we will find on paramet tion is not o and directio meter β 1 an nts” of X 2 on ppropriate es imator b 1 . C th the two fo common de tor, just mul 1 2 2 2 1 a i x erators are < Var(b 1 ). W mate the foll ue model is: r simple line 1 2 1 i x Y x , mator do on a rmining the rue model f 10 1 i x  ctation, and 1 2 i x x sn’t equal β lation betw M estimator d that we do ter. The cen over the true on of the bia nd the “regr n X 1 . stimator for t Compare the ormulas abo enominator ltiply Var(a 2 2 2 2 i i x x    e the same, b hile biased, owing simp 0 i Y ear model es 1 2 a average? Ex e expected v for Y: 12 2 1 i i X X x using CRM 2 2 1 i i X 1 , unless th een indepen is biased. T o not get th nter of our s e value. The as depends ression the effect of variance fo ove and ask or numerat 1 ) by “1.” 2 1 i x  but clearly t , it appears le linear mod i X  timator, a 1 ? 2 2 1 i x , 1 2 b plain – prov value of the 2 v A 2 and 3, w ere is ndent Thus, on e true ampling e exact upon f X 1 on Y r b 1 to the va k: Is Var(a 1 ) tor. It’s a bit 22 2 2 21 i x x x x

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

View Full Document
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### Page1 / 4

Key - Problem Set 4 2011 - Problem Set 4 Due Econometrics I...

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

View Full Document
Ask a homework question - tutors are online