CHAPTER 13 Simple Linear Regression
CHAPTER 13 Simple Linear Regression
CHAPTER 13 Simple Linear Regression
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
544 <strong>CHAPTER</strong> THIRTEEN <strong>Simple</strong> <strong>Linear</strong> <strong>Regression</strong><br />
<strong>13</strong>.45 In Problem <strong>13</strong>.7 on page 523, you used<br />
PH Grade <strong>13</strong>.40 You are testing the null hypothesis that PH Grade<br />
Test ing manager used shelf space for pet food to predict<br />
weekly sales. The data are stored in the file<br />
<strong>13</strong>.48 In Problem <strong>13</strong>.10 on page 523, you used hardness<br />
to predict the tensile strength of die-cast aluminum. The<br />
petfood.xls. From the results of that problem, b 1<br />
= 7.4 and<br />
data are stored in the file hardness.xls. Using the results of<br />
S b1<br />
= 1.59.<br />
that problem,<br />
a. At the 0.05 level of significance, is there evidence of a<br />
a. at the 0.05 level of significance, is there evidence of a<br />
linear relationship between shelf space and sales?<br />
linear relationship between hardness and tensile<br />
b. Construct a 95% confidence interval estimate of the<br />
strength?<br />
population slope, β 1<br />
.<br />
b. construct a 95% confidence interval estimate of the population<br />
mine that b 1<br />
= +4.5 and S b1<br />
= 1.5.<br />
Using the results of that problem,<br />
a. What is the value of the t test statistic?<br />
a. at the 0.05 level of significance, is there evidence of a<br />
ASSIST there is no relationship between two variables, X<br />
and Y. From your sample of n = 18, you deter-<br />
ASSIST the weight of mail to predict the number of orders<br />
received. The data are stored in the file mail.xls.<br />
b. At the α = 0.05 level of significance, what are the critical<br />
values?<br />
c. Based on your answers to (a) and (b), what statistical<br />
decision should you make?<br />
linear relationship between the weight of mail and the<br />
number of orders received?<br />
b. construct a 95% confidence interval estimate of the population<br />
slope, β 1<br />
.<br />
d. Construct a 95% confidence interval estimate of the<br />
<strong>13</strong>.46 In Problem <strong>13</strong>.8 on page 523, you used annual revenues<br />
to predict the value of a baseball franchise. The data<br />
population slope, β 1<br />
.<br />
PH Grade<br />
ASSIST<br />
<strong>13</strong>.41 You are testing the null hypothesis that<br />
there is no relationship between two variables, X<br />
and Y. From your sample of n = 20, you determine<br />
are stored in the file bbrevenue.xls. Using the results of that<br />
problem,<br />
a. at the 0.05 level of significance, is there evidence of a<br />
that SSR =60andSSE = 40.<br />
a. What is the value of the F test statistic?<br />
b. At the α = 0.05 level of significance, what is the critical<br />
value?<br />
linear relationship between annual revenue and franchise<br />
value?<br />
b. construct a 95% confidence interval estimate of the population<br />
slope, β 1<br />
.<br />
c. Based on your answers to (a) and (b), what statistical<br />
<strong>13</strong>.47 In Problem <strong>13</strong>.9 on page 523, an agent for a real<br />
decision should you make?<br />
estate company wanted to predict the monthly rent for apartments,<br />
based on the size of the apartment. The data are stored<br />
d. Compute the correlation coefficient by first computing<br />
r 2 and assuming that b 1<br />
is negative.<br />
in the file rent.xls. Using the results of that problem,<br />
e. At the 0.05 level of significance, is there a significant<br />
a. at the 0.05 level of significance, is there evidence of a<br />
correlation between X and Y?<br />
linear relationship between the size of the apartment and<br />
Applying the Concepts<br />
the monthly rent?<br />
b. construct a 95% confidence interval estimate of the population<br />
SELF <strong>13</strong>.42 In Problem <strong>13</strong>.4 on page 522, the market-<br />
slope, β 1<br />
.<br />
slope, β 1<br />
.<br />
<strong>13</strong>.43 In Problem <strong>13</strong>.5 on page 522, you used reported<br />
magazine newsstand sales to predict audited sales. The data<br />
are stored in the file circulation.xls. Using the results of that<br />
problem, b 1<br />
= 0.5719 and S b1<br />
= 0.0668.<br />
a. At the 0.05 level of significance, is there evidence of a<br />
linear relationship between reported sales and audited<br />
sales?<br />
b. Construct a 95% confidence interval estimate of the<br />
population slope, β 1<br />
.<br />
<strong>13</strong>.44 In Problem <strong>13</strong>.6 on pages 522–523, the owner of a<br />
moving company wanted to predict labor hours, based on<br />
the number of cubic feet moved. The data are stored in the<br />
file moving.xls. Using the results of that problem,<br />
a. at the 0.05 level of significance, is there evidence of a<br />
linear relationship between the number of cubic feet<br />
moved and labor hours?<br />
b. construct a 95% confidence interval estimate of the population<br />
slope, β 1<br />
.<br />
<strong>13</strong>.49 The volatility of a stock is often measured by its<br />
beta value. You can estimate the beta value of a stock by<br />
developing a simple linear regression model, using the percentage<br />
weekly change in the stock as the dependent variable<br />
and the percentage weekly change in a market index as<br />
the independent variable. The S&P 500 Index is a common<br />
index to use. For example, if you wanted to estimate the<br />
beta for IBM, you could use the following model, which is<br />
sometimes referred to as a market model:<br />
(% weekly change in IBM) = β 0<br />
+ β 1<br />
(% weekly change in<br />
S & P 500 index) + ε<br />
The least-squares regression estimate of the slope b 1<br />
is the<br />
estimate of the beta value for IBM. A stock with a beta<br />
value of 1.0 tends to move the same as the overall market.<br />
A stock with a beta value of 1.5 tends to move 50% more<br />
than the overall market, and a stock with a beta value of 0.6