This preview has intentionally blurred sections. Sign up to view the full version.
View Full DocumentThis preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
Unformatted text preview: Will Landau October 3, 2011 STAT 231 Problem Set 8 Solutions Exercise 8.1. I begin with the following table from homework 7, where X1,...,X5, Xnew are standard normal random variables. If you don’t know how to generate this table, see problem 5 of the posted solutions for homework 7. For each row, we want to use our sample of n = 5 standard normal draws draws (X1, ... X5) to create a tolerance interval that captures 99% of the sampling distribution with 95% confidence. From page 291 in Devore, this interval is of the form, X ± T · σ , where X = X 1 + X 2 + X 3 + X 4 + X 5 5 , σ = q ∑ 5 i =1 ( X i X ) 2 5 1 , and T is the desired tolerance critical value. To find the tolerance critical value, we look at table A.6 and use sample size n = 5, confidence level = 95%,and % of population captured ≥ 99%. We find that T = 6 . 634, which agrees with what Prof. Vardeman wrote in the homework set. With the above figured out, we go back to our JMP table and make two more columns: Ltol, the column containing the lower tolerance limits of all the rows, and Utol, the column containing the upper tolerance limits of all the rows: 1 For Ltol, I use the formula: ”Mean()  6.634*(Std Dev(X1,X2,X3,X4,X5))” For Utol, I use the formula: ”Mean() + 6.634*(Std Dev(X1,X2,X3,X4,X5))” More specifically, I went through these steps for Ltol: And similarly for Utol, yielding the following table: 2 But we’re not done. Next, we need to know what fraction of the standard normal density is covered by each of the tolerance intervals: i.e.,normal density is covered by each of the tolerance intervals: i....
View
Full Document
 Fall '08
 Staff
 Normal Distribution, standard normal distribution, DeVore, Normal probability plot, Utol

Click to edit the document details