Lecture 15-2007

# Lecture 15-2007 - Limits and the Law of Large Numbers...

This preview shows pages 1–3. Sign up to view the full content.

Limits and the Law of Large Numbers Lecture XV I. Almost Sure Convergence A. White, Halbert. Asymptotic Theory for Econometricians (New York: Academic Press, 1984). Chapter II. B. Let represent the entire random sequence   t Z . As discussed last time, our interest typically centers around the averages of this sequence:   n t t n Z n b 1 1 C. Definition 2.9: Let     n b be a sequence of real-valued random variables. We say that   n b converges almost surely to b , written   b b s a n  . . if and only if there exists a real number b such that     1 : b b P n . 1. The probability measure P describes the distribution of and determines the joint distribution function for the entire sequence   t Z . 2. Other common terminology is that   n b converges to b with probability 1 (w.p.1) or that   n b is strongly consistent for b . 3. Example 2.10: Let n t t n Z n Z 1 1 where   t Z is a sequence of independently and identically distributed (i.i.d.) random variables with   t EZ   . Then . . s a n Z by the Komolgorov strong law of large numbers (Theorem 3.1). 4. Proposition 2.11: Given   :, kl g R R k l   and any sequence   n b such that b b s a n . . where n b and b are 1 k vectors, if g is continuous at b , then

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

View Full Document
AEB 6933 – Mathematical Statistics for Food and Resource Economics Lecture XV Professor Charles B. Moss Fall 2007 2     b g b g s a n  . . . 5. Theorem 2.12: Suppose a) 0 yX   ; b) .. 0 as X n  ; c) XX M n , finite and positive definite. Then n exists a.s. for all n sufficiently large, and 0 n  . d) Proof: Since X X n M , it follows from Proposition 2.11 that     det det X X n M . Because M is positive definite by (c),   det 0 M . It follows that   det 0 X X n a.s. for all n sufficiently large, so   1 X X n exists a.s. for all n sufficiently large. Hence   n y X n X X n ' ' ˆ 1 exists for all n sufficiently large. In addition,   1 0 ˆ ' ' n X nn It follows from Proposition 2.11 that 0 1 0 . . 0 0
This is the end of the preview. Sign up to access the rest of the document.
• Fall '09
• CARRIKER
• Probability theory, Charles B. Moss, Economics Professor Charles, Resource Economics Professor, Lecture XV Fall

{[ snackBarMessage ]}

### Page1 / 6

Lecture 15-2007 - Limits and the Law of Large Numbers...

This preview shows document pages 1 - 3. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online