# Question: Ledolter and Hogg report that a civil engineer wishes to

Ledolter and Hogg report that a civil engineer wishes to compare the strengths of three different types of beams, one (A) made of steel and two (B and C) made of different and more expensive alloys. A certain deflection (in units of 0.001 inch) was measured for each beam when submitted to a given force; thus, a small deflection would indicate a beam of great strength. The order statistics for the three samples, of respective sizes n1 = 8, n2 = 6, and n3 = 6, are as follows:

(a) Use these data, α = 0.05, and the F test to test the equality of the three means.

(b) For each set of data, construct box-and-whisker diagrams on the same figure and give an interpretation of your diagrams.

(a) Use these data, α = 0.05, and the F test to test the equality of the three means.

(b) For each set of data, construct box-and-whisker diagrams on the same figure and give an interpretation of your diagrams.

**View Solution:**## Answer to relevant Questions

Let pn, n = 0, 1, 2, . . . , be the probability that an automobile policyholder will file for n claims in a five-year period. The actuary involved makes the assumption that pn+1 = (1/4)pn. What is the probability that the ...The “eating club” is hosting a make-your-own sundae at which the following are provided: Ice Cream Flavors Toppings Chocolate ...... Caramel Cookies ‘n’ cream .. Hot fudge Strawberry ...... Marshmallow Vanilla ...Let X1, X2, X3, X4 equal the cholesterol level of a woman under the age of 50, a man under 50, a woman 50 or older, and a man 50 or older, respectively. Assume that the distribution of Xi is N(μi, σ2), i = 1, 2, 3, 4. We ...There is another way of looking at Exercise 9.3-6, namely, as a two-factor analysis-of-variance problem with the levels of gender being female and male, the levels of age being less than 50 and at least 50, and the ...In sampling from a bivariate normal distribution, it is true that the sample correlation coefficient R has an approximate normal distribution N[ρ, (1 − ρ2)2/n] if the sample size n is large. Since, for large n, R is ...Post your question