Case Study

Chapter 10 Case Study

ISQS 5345: Business Statistics

Team 4:

Kyle Lock

Jeff Morris

Derrick Plunk

Brian Wilder

10/27/2009

Table of Contents

Chapter 10 Case Study 3

Question 1 3

Question 2 3

Question 3 3

Question 4 4

Chapter 10 Case Study

Question 1

Choose two ads, one that is significant and one that is not. Verify significance based on the average, standard error, and n, to make sure that they are correct. Is it appropriate to use one-sided tests here?

σ=3.54,n=51,xˉ=3.7,S_x=0.104

Write out statements (same as part a)

H_0: μ=3.54

H_1: μ≠3.54

Find Critical Values

Using the t table on page 812, we look for n = 51, two-sided confidence level = 95%.

cv=1.960

Find Confidence Interval

xˉ ±(S_x*cv)

Using the above equation, we find the confidence interval to be:

3.70-(1.96)(.104)=3.49616

3.70+(1.96)(.104)=3.90384

Make decision

We have concluded that the average of the Coffee Break commercial is not significantly different than the average o the shopping commercial. We will accept the null hypothesis. It is necessary to use a two-sided test to determine if the null value falls into the confidence interval or not.

Question 2

If the type I error is supposed to be controlled at 5%, how is it that in the computer simulation model, type I errors occurred 70% of the time?

A type 1 error occurs when a person accepts the research hypothesis, but should have chosen the null hypothesis. It is possible that the error occurred in 70% of tests because the value of the population mean was incorrectly assumed.

Question 3

Could it reasonably be that no ads are worthwhile, in a study for which 2 of 22 are significant?

Not likely. This could possibly be true for each commercial except for the Country Picnic ad, as its p-value is at 0.0001. This tells us that there would be a 1 in 1000 chance that the null hypothesis would be true for this ad.

Question 4

What is your interpretation of the effectiveness of the ads in...