This preview shows pages 1–3. Sign up to view the full content.
Brandon Lang
December 11, 2007
Mon/Wed 46
BUAD 310 Case Study
1.
a.
The histograms for the cost of an ad and the circulation are skewed to the right
and unimodal.
The histogram for median income appears to be fairly normal with
no skewness.
The histogram for the percent of male readers also appears to have
no skewness and is bimodal making it reasonably symmetric.
b.
The relationship between page cost and circulation appears to have a curved
relationship, not a linear one.
There appear to be two possible outliers but the
overall plot has a slight curve shape.
There appears to be no strong linear
relationship between page cost and the percent of male readers.
The plot is rather
scattered showing no evidence of a strong relationship.
There also appears to be
no strong linear relationship between page cost and median income.
The plot
looks as if it could possibly have a slight curved relationship but there is no strong
relationship apparent.
2.
The regression equation is
pagecost =  8643 + 5.28 circ  11.0 percmale + 1.22
medianincome
Predictor
Coef
SE Coef
T
P
VIF
Constant
8643
12291
0.70
0.486
circ
5.2815
0.5304
9.96
0.000
1.082
percmale
11.00
77.20
0.14
0.887
1.377
medianincome
1.2226
0.5355
2.28
0.027
1.426
S = 13129.3
RSq = 69.4%
RSq(adj) = 67.3%
Analysis of Variance
Source
DF
SS
MS
F
P
Regression
3
17219203510
5739734503
33.30
0.000
Residual Error
44
7584600772
172377290
Total
47
24803804282
a.
The multiple regression model seems to be useful.
The
R²
value is 69.4% which
means that almost 70% of the variation is explained by the model.
Also, the
model is statistically significant at the
α=.05
level based on the Fvalue of 33.30
that has an approximate pvalue of 0.000.
b.
The estimated regression equation is:
Pagecost =  8643 + 5.28 (circulation) – 11.0 (% male) + 1.22 (median income)
c.
Multicollinearity does not appear to be a problem based on the VIF values.
The
VIF values are all less than five which means they are not a concern.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Documentd.
Circulation and median income both contribute significantly to the model at the
α=.05
level.
This is based on the pvalues of 0.000 and 0.027 for circulation and
median income, respectively.
The percent of male readers does not seem to
contribute to the model significantly.
This variable’s pvalue of 0.887 is not
significant at the
α=.05
level and therefore could be eliminated from the model
This is the end of the preview. Sign up
to
access the rest of the document.
 Fall '07
 Lv
 Business

Click to edit the document details