To gauge how your firm’s advertising and other promotional
activities affect your firm’s sales, you collected data on your firm’s sales (in thousands of
dollars) for 51 months and the firm’s promotional expenditures (in thousands of dollars.
Graphs and statistics support the regression model:
Sales = 25.1264 + 0.7623PromoExpend
.
1.
To test whether the simple linear model is useful, we test
a.
Whether the yintercept is different from 0.
b.
Whether the yintercept is different from 1.
c.
Whether r
2
is large.
d.
Whether the slope parameter is different from 0.
e.
Whether the slope parameter is different from 1.
2.
Which of the following is a correct interpretation of the parameter estimates?
a.
As sales increase by $1, promotional expenditures increase on average by $25.12.
b.
As promotional expenditures increase by $1000, sales increase on average by
$762.30.
c.
As promotional expenditures increase by $1000, sales decrease on average by
$762.30
d.
When promotional expenditures are $0, sales are predicted to be $25,126.40 per
month on average.
e.
When sales are $0, promotional expenditures are predicted to be $25.12 during
that month on average.
3.
If the standard error of b
1
(s
b1
) = 0.1209, which of the following is correct?
a.
We are 95% confident that as sales increase by $1, promotional expenditures
increase on average between $1.23 to $49.02.
b.
We are 95% confident that as promotional expenditures increase by $1000, sales
increase on average between $519.40 and $1005.20.
c.
We are 95% confident that as promotional expenditures increase by $1, sales
decrease on average between $0.52 and $1.01.
d.
We are 95% confident that as sales increase by $1, promotional expenditures
increase on average between $519.40 and $1005.20.
4.
If r = 0.673, which of the following is correct?
a.
The correlation between sales and promotional expenditures is 0.4529.
b.
If we use the model to predict, we can expect 45.29% of our actual sales values to
be within one standard error of their predicted values.
c.
We get 45.29% more prediction error by simply using the sample average to
predict sales, rather than using the model to predict sales.
d.
45.29% of the variability in monthly sales can be explained by monthly
promotional expenditures.
e.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
This is the end of the preview.
Sign up
to
access the rest of the document.
 Spring '08
 Staff
 Linear Regression, Regression Analysis, promotional expenditures

Click to edit the document details