INTRODUCTION TO ECONOMETRICS II
ECO 306
NOUN
55 how the OLS, using sample data, can estimate unknown parameters of a regression equation. Furthermore, it makes available opportunity to ask whether statements about the true unknown parameters of the model, based on our estimated values can be made. In doing this, there is need to make a number of assumptions. These assumptions, if satisfied, ensure that the estimators being used are accurate and efficient. Precise predictions about the unknown model parameters can also be make through satisfactory assumptions. Here is a summary of the 10 assumptions in CLRM:
Assumption 1: Linear regression model. The regression model is linear in the parameters,as shown in
1 2
i
i
i
Y
X
where,
Y is the regressandY and the regressorX may be nonlinear.
Assumption 2: X values are fixed in repeated sampling.
Values taken by the regressorXare considered fixed in repeated samples. More precisely, X is assumed to be nonstochastic.
Assumption 3: Zero means value of disturbance
i
. That is, given the value of X, the mean value of the random disturbance term
i
is zero. This shows that the uncertain mean value of
i
is zero, as shown in
(
|
)
0
i
i
E
X
…[02]
Assumption 4: Equal variance of
i
. If given the value of X, the variance of
i
is the same for all observations. Which means that the uncertain variances of
i
are alike, as shown in.
|
