HWK 13 - Is there any difference between the recall...

Info iconThis preview shows page 1. Sign up to view the full content.

View Full Document Right Arrow Icon
Homework #12 Problem #35 Page 439 Business Issue: TV Comercial messages seen and recalled by viewers. Business Question: Data: Commercial A Commercial B # who Saw 150 200 # who Remembered 63 60 Analysis: 1) Ho: Ha: 2) and std err = stdev (p-bar1 - p-bar2) p-bar A =  0.42 nA =  150 p-bar B = 0.3 nB = 200 p-bar = (n1*p-bar1 + n2*p-bar2) / (n1 + n2) = 0.35 StdError= 0.05 3) Alpha = .05 4) Norminv (.025, 0,.035)= -0.1 > pbar 0.1 < pbar 5) p-bar1 - p-bar2 = 0.12 p-value = 0.99 = 2*(1-.999665) 0.02 6) Reject Ho Business Answer According to the samples of the two commercials there is sufficent or strong evidence to be able to conclude that the recall proportions are different.  The sample recall proportions of commercial A are different enough from those of commercial B to safely be able to make the conclusion that the two are different with commercial A being higher.
Background image of page 1
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Is there any difference between the recall proportions for the two commercials. If so, what is the difference? Ho: p 1 - p 2 = D =0 Ha: p 1 - p 2 <> D =0 (p-bar 1- p-bar 2 ), the difference found in the two sample proportions Because when Ho is true (p 1 = p 2 ) and the sample sizes are large (n*p & n*(1-p) for both >=5) this test stat is NORMAL with mean (p-bar1 - pbar2) = D = 0 (the difference stated in Ho). = [ p-bar 1 *(1-p-bar 1 )/n 1 + p-bar 2 *(1-p-bar 2 )/n 2 ]^.5 Reject Ho if (p-bar 1 - p-bar 2 ) < "value of the normal distribution with cum prob = .025" or if (p-hat 1 - p-hat 2 ) > "value of the normal distribution with cum prob = .975"...
View Full Document

This note was uploaded on 03/31/2011 for the course STATS 211 taught by Professor Dunne during the Spring '07 term at University of Dayton.

Ask a homework question - tutors are online