# hw4vqn - Vinh Nguyen Stat 120A(Fall 2007 HW4 Solutions...

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

Vinh Nguyen Stat 120A(Fall 2007): HW4 Solutions November 7, 2007 Text: Probabilty and Statistics , by Degroot and Schervish (3 rd ed) Problems: 4.5.6, 4.5.11, 4.8.5, 5.6.3, 5.6.13, 5.7.2, and 5.7.11 4.5.6 Suppose X has the following pdf: f ( x ) = ± 2 x for 0 < x < 1, 0 otherwise. (a) We know from section 4.5 that E [( X - d ) 2 ] is minimized at d = E ( X ) = μ . E ( X ) = Z 1 0 x 2 xdx = ² 2 x 3 3 ³ 1 0 = 2 3 (b) We know from section 4.5 that E [ | X - d | 2 ] is minimized at d = F - 1 X (1 / 2) = median ( X ). F X ( x ) = Z x 0 2 tdt = t 2 | x 0 = x 2 which implies F - 1 X ( q ) = q so that F - 1 X (1 / 2) = r 1 2 . 4.5.11 Suppose X Bin ( n = 7 ,p = 1 / 4) and Y Bin ( n = 5 ,p = 1 / 2). Recall that the M.S.E. for a r.v. X is deﬁned as E [( X - μ ) 2 ] = σ 2 . For a Bin ( n,p ) distribution, we know that μ = p and σ 2 = np (1 - p ). Applying this, we have σ 2 X = 7(1 / 4)(3 / 4) = 21 / 16 and σ 2 Y = 5(1 / 2)(1 / 2) = 5 / 4. Since σ X > σ Y , Y can be predicted with a smaller M.S.E.

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 / 3

hw4vqn - Vinh Nguyen Stat 120A(Fall 2007 HW4 Solutions...

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

View Full Document
Ask a homework question - tutors are online