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

partial regression coefficients,
and their meaning will be explained shortly.
We continue to operate within the framework of the classical linear regression model
(CLRM) first introduced in Chapter 3. As a reminder, we assume the following:
2
This assumption is automatically fulfilled if 
X
2
and 
X
3
are nonstochastic and Eq. (7.1.4) holds.
1. Linear regression model, or 
linear in the parameters.
(7.1.2)
2. Fixed 
X
values or 
X
values independent of the error term. Here, this means 
we require zero covariance between 
u
i
and each 
X
variables. 
cov (
u
i
, 
X
2
i
) 
cov (
u
i
, 
X
3
i
) 
0
(7.1.3)
2
3. Zero mean value of disturbance 
u
i
.
E
(
u
i
|
X
2
i, 
X
3
i
) 
0
for each 
i
(7.1.4)
4. Homoscedasticity or constant variance of 
u
i
.
var (
u
i
) 
σ
2
(7.1.5)
5. No autocorrelation, or serial correlation, between the disturbances.
cov (
u
i
, 
u
j
) 
0
i
=
j
(7.1.6)
6. The number of observations 
n
must be greater than the number of 
parameters to be estimated, which is 3 in our current case.
(7.1.7)
7. There must be variation in the values of the 
X
variables.
(7.1.8)
We will also address two other requirements.
8. No exact collinearity between the 
X
variables.
No