The McGraw-Hill Series Economics essentials of economics brue, McConnell, and Flynn Essentials of Economics

897
E.3
Excel
Using Microsoft Excel we obtained the regression output shown in Table E.2.
Excel first presents summary statistics, such as 
R
2
, multiple 
R
, which is the (positive)
square root of 
R
, adjusted 
R
2
, and the standard error of the estimate. Then it presents the
ANOVA table. After that it presents the estimated coefficients, their standard errors, the 
t
values of the estimated coefficients and their 
p
values. It also gives the actual and estimated
1.0
0.5
0.0
Residual
0.5
1.0
1.5
9
6
7
8
5
Frequency
Histogram of the Residuals
(response is CLFPR)
4
3
2
1
0
Mean
StDev
N
AD
p
-Value
4.479511
0.5569 
23 
0.481
0.210
1.0
0.5
0.0
RESI1
0.5
1.0
1.5
99
80
90
95
70
60
50
Percent
Probability Plot of RESI1
Normal
40
30
20
10
5
1
Predictor
Constant
CUNR
AHE82
Regression Analysis: CLFPR versus CUNR, AHE82
The regression equation is
CLFPR 
81.0 
0.672 CUNR 
1.41 AHE82
Source
Regression
Residual Error
Total
Source
CUNR
AHE82
S
0.584117
R
-Sq 
77.3%
R
-Sq(adj) 
75.0%
Analysis of Variance
T
16.97
8.12
2.31
MS
SE Fit
0.155
0.307
Obs
1
23
CUNR
7.10
5.80
Coef
80.951
0.67163
1.4104
DF
2
20
22
DF
CLFPR
63.800 
66.600
SE Coef
4.770
0.08270
0.6103
SS
Seq SS
21.404
1.822
Fit
65.209
65.575
R
denotes an observation with a large standardized residual.
Durbin–Watson statistic 
0.787065
Unusual Observations
P
0.000
P
0.000
0.000
0.032
St Resid
2.50
R
2.06
R
F
34.04
Residual
1.409
1.025
11.613
0.341
1
1
23.226
6.824
30.050
FIGURE E.2
MINITAB output of civilian labor force participation rate.
guj75772_appE.qxd 05/09/2008 11:10 AM Page 897

---

898
Appendix E
Computer Output of EViews, MINITAB, Excel, and STATA
values of the dependent variable and the residual graph as well as the normal probability
plot.
A unique feature of Excel is that it gives the 95 percent (or any specified percent) confi-
dence interval for the true values of the estimated coefficients. Thus, the estimated value of
the coefficient of CUNR is 
−
0.671631 and the confidence interval for the true value
of CUNR coefficient is (
−
0.84415 to 
−
0.499112). This information is very valuable for
hypothesis testing.