Accounting 3334
Assignment 3
Solution
1030
(3040 min.)
Highlow versus regression method.
1.
The first step is the specification analysis to assure the quality of the input data sets. The plot of the residuals does not
illustrate any pattern and this means the residual values are random and normally distributed. The OLS regression line
provides evidence that the relationship between advertising expense and revenue is linear and it is economically plausible
that increased advertising expense would stimulate purchases/sales of the product. The
r
2
of 0.643 assures the managerial
accountant that in fact change in advertising expense explains slightly over 64% of the change in revenue. The critical
value of the
t
statistic for 99% confidence level and d.f. of 9 is 3.250. The calculated
t
values for both the intercept
a
of
6.831 and slope coefficient
b
of 8.723 both exceed the critical value, therefore the managerial accountant can be
confident that these are not random values. The pstatistic tells the managerial accountant that there is a probability of
0.0001 or 1 in 10,000 that it is incorrect to reject the null hypothesis H
0
for the intercept
a
, and probability of 0.005 or 5
in 1,000 it is incorrect to reject the null hypothesis H
0
for the slope coefficient
b
. These results not only meet the criteria
of the specification analysis but provide strong evidence that by controlling advertising expense, managers can control
revenue.
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 '11
 Don
 Accounting, Linear Regression, Regression Analysis, Accountant, regression line, Advertising expense

Click to edit the document details