This preview shows pages 1–2. Sign up to view the full content.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: contain one so it is not reasonable to suppose the standard deviations are the same. 9. (a) ˆ p = 24 / 642 = 0 . 0374. (b) ˆ p ± 1 . 96 p ˆ p (1ˆ p ) /n = [0 . 0227 , . 0521] (c) ˆ p + 1 . 96 2 / (2 n ) ± 1 . 96 p (ˆ p (1ˆ p ) /n + 1 . 96 2 / (4 n 2 )) 1 + 1 . 96 2 /n = [0 . 0252 , . 0550] (d) ˆ p + 1 . 645 p ˆ p (1ˆ p ) /n = 0 . 0497 10. see output 11. see output 12. The conﬁdence interval for the ratio of the variances includes one so there is no reason to suppose they diﬀer. 13. R computes the quadratic interval. It is quite close to the exact interval for the data of Question 9. 14. The upper line in the plot represents the upper ends of the intervals and the lower line the lower end. The straight line is the true value (zero).You should have noticed about 95% of the intervals contain zero. 2...
View
Full
Document
This note was uploaded on 10/05/2009 for the course STATS 620202 taught by Professor R during the One '09 term at University of Melbourne.
 One '09
 R
 Statistics

Click to edit the document details