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

82
Part One
Single-Equation Regression Models
Country
Cellphone
PCs
Per Capita Income ($)
Argentina
17.76
8.2
11410
Australia
71.95
60.18
28780
Belgium
79.28
31.81
28920
Brazil
26.36
7.48
7510
Bulgaria
46.64
5.19
75.4
Canada
41.9
48.7
30040
China
21.48
2.76
4980
Colombia
14.13
4.93
6410
Czech Republic
96.46
17.74
15600
Ecuador
18.92
3.24
3940
Egypt
8.45
2.91
3940
France
69.59
34.71
27640
Germany
78.52
48.47
27610
Greece
90.23
8.17
19900
Guatemala
13.15
1.44
4090
Hungary
76.88
10.84
13840
India
2.47
0.72
2880
Indonesia
8.74
1.19
3210
Italy
101.76
23.07
26,830
Japan
67.9
38.22
28450
Mexico
29.47
8.3
8980
Netherlands
76.76
46.66
28560
Pakistan
1.75
0.42
2040
Poland
45.09
14.2
11210
Russia
24.93
8.87
8950
Saudia Arabia
32.11
13.67
13230
South Africa
36.36
7.26
10130
Spain
91.61
19.6
22150
Sweden
98.05
62.13
26710
Switzerland
84.34
70.87
32220
Thailand
39.42
3.98
7450
U.K.
91.17
40.57
27690
U.S.
54.58
65.98
37750
Venezuela
27.3
6.09
4750
Note:
The data on cell phones and personal computers are per 100 persons.
TABLE 3.3
Number of Cellular
Phone Subscribers
per Hundred
Persons and
Number of Personal
Computers per 100
Persons and Per
Capita Income in
Selected Countries
for 2003
Source: 
Statistical Abstract
of the United States, 
2006,
Table 1364 for data on cell
phones and computers and
Table 1327 for purchasing-
power adjusted per capita
income.
EXAMPLE 3.3
Demand for
Cellular Phones
and Personal
Computers in
Relation to Per
Capita Personal
Income
Table 3.3 gives data on the number of cell phone subscribers and the number of personal
computers (PCs), both per 100 persons, and the purchasing-power adjusted per capita in-
come in dollars for a sample of 34 countries. Thus we have cross-sectional data. These data
are for the year 2003 and are obtained from the 
Statistical Abstract of the United states,
2006.
Although cell phones and personal computers are used extensively in the United
States, that is not the case in many countries. To see if per capita income is a factor in the
use of cell phones and PCs, we regressed each of these means of communication on per
capita income using the sample of 34 countries. The results are as follows:
guj75772_ch03.qxd 23/08/2008 02:34 PM Page 82

---

Chapter 3
Two-Variable Regression Model: The Problem of Estimation
83
3.8
A Note on Monte Carlo Experiments
In this chapter we showed that under the assumptions of CLRM the least-squares estima-
tors have certain desirable statistical features summarized in the BLUE property. In the
appendix to this chapter we prove this property more formally. But in practice how does
one know that the BLUE property holds? For example, how does one find out if the OLS
estimators are unbiased? The answer is provided by the so-called 
Monte Carlo
experi-
ments, which are essentially computer simulation, or sampling, experiments.
To introduce the basic ideas, consider our two-variable PRF:
Y
i
=
β
1
+
β
2
X
i
+
u
i