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

(3.8.1)
Demand for Cell Phones.
Letting 
Y
=
number of cell phone subscribers and 
X
=
purchasing-power-adjusted per capita income, we obtained the following regression.
ˆ
Y
i
=
14.4773 
+
0.0022
X
i
(3.7.3)
se ( ˆ
β
1
) 
=
6.1523;
se ( ˆ
β
2
) 
=
0.00032
r
2
=
0.6023
The slope coefficient suggests that if per capita income goes up by, say, $1,000, on
average, the number of cell phone subscribers goes up by about 2.2 per 100 persons.
The intercept value of about 14.47 suggests that even if the per capita income is zero, the
average number of cell phone subscribers is about 14 per 100 subscribers. Again, this
interpretation may not have much meaning, for in our sample we do not have any coun-
try with zero per capita income. The 
r
2
value is moderately high. But notice that our
sample includes a variety of countries with varying levels of income. In such a diverse
sample we would not expect a very high 
r
2
value.
After we study Chapter 5, we will show how the estimated standard errors reported
in Equation 3.7.3 can be used to assess the statistical significance of the estimated
coefficients.
Demand for Personal Computers.
Although the prices of personal computers have come
down substantially over the years, PCs are still not ubiquitous. An important determinant
of the demand for personal computers is personal income. Another determinant is price,
but we do not have comparative data on PC prices for the countries in our sample.
Letting 
Y
denote the number of PCs and 
X
the per capita income, we have the follow-
ing “partial” demand for the PCs (partial because we do not have comparative price data
or data on other variables that might affect the demand for the PCs).
ˆ
Y
i
= −
6.5833 
+
0.0018
X
i
(3.7.4)
se ( ˆ
β
1
) 
=
2.7437;
se ( ˆ
β
2
) 
=
0.00014
r
2
=
0.8290
As these results suggest, per capita personal income has a positive relationship to the
demand for PCs. After we study Chapter 5, you will see that, statistically, per capita
personal income is an important determinant of the demand for PCs. The negative value
of the intercept in the present instance has no practical significance. Despite the diversity
of our sample, the estimated 
r
2
value is quite high. The interpretation of the slope coeffi-
cient is that if per capita income increases by, say, $1,000, on average, the demand for
personal computers goes up by about 2 units per 100 persons.
Even though the use of personal computers is spreading quickly, there are many
countries which still use main-frame computers. Therefore, the total usage of computers
in those countries may be much higher than that indicated by the sale of PCs.
EXAMPLE 3.3
(
Continued
)
guj75772_ch03.qxd 23/08/2008 05:28 PM Page 83

---

84