This preview shows pages 1–3. 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: Solutions to Homework #6, 36220 Due 12 October 2005 NonDevore Problem The rule for variances which says Var ( X + Y ) = Var ( X )+Var ( Y ) only applies if X and Y are uncorrelated random variables, for instance, if X and Y are independent. But here the variables were adding are perfectly correlated theyre functions of one another and we cant use that rule. (Notice that the book gives a more general rule, for correlated variables, as Equation 5.11 on page 244. You can check that this rule gives the right answer, once you calculate the covariance of X and Y .) 46 a E X = E [ X ] = 12cm X = X / n = 0 . 04cm / 16 = 0 . 01cm b E X = 12cm, again X = X / 64 = 0 . 04cm / 8 = 0 . 005cm c The larger sample is more likely to be close to 12 cm, because 12 cm is the mean, in both cases, but the standard deviation is smaller for the large sample. A smaller standard deviation implies a higher probability of being near the mean. 48 Notice that X = X / 100 = 1 / 10 = 0 . 1. a E X = 50, so Pr 49 . 75 50 . 1 X 50 . 1 50 . 25 50 . 1 1 = Pr (( . 25)(10) Z (0 . 25)(10)) = (2 . 5) ( 2 . 5) = . 988 b We repeat the same calculation, only substituting 49 . 8 for 50. Pr 49 . 75 49 . 8 . 1 X 49 . 8 . 1 50 . 25 49 . 8 . 1 = Pr (( . 05)(10) Z (0 . 45)(10)) = (4 . 5) ( . 5) = . 691 49 Lets use T for the total time it takes to grade. T =...
View Full
Document
 Fall '05
 Shalizi
 Statistics, Variance

Click to edit the document details