How to get values of estimators in the SRF?

58 Views Asked by At

I was reading the Econometrics textbook by Damodar Gujarati, and in the book, he develops the sample regression function using the following equations.

$\sum Y_{i} = n \beta_{1} + \beta_{2}\sum X_{i}$

$\sum Y_{i} X_{i} = \beta_{1} \sum X_{i} + \beta_{2}\sum X_{i}^{2}$

I get this. But from these equations, we get something of the form of the following, and I am really confused as to how we get the following from the preceding equations as well as the inner workings of the following equations themselves.

$\beta_{2} = \frac{n\sum X_{i}Y_{i} - \sum X_{i}\sum Y_{i}}{n \sum X_{i}^{2} - (\sum X_{i})^{2}}$

= $\frac{\sum(X_{i}-\bar{X})(Y_{i}-\bar{Y})}{\sum(X_{i}-\bar{X})^{2}}$

Additionally, let me point out that $\bar{X}$ and $\bar{Y}$ are the means of X and Y respectively.

I am really confused as to how we get the second line of this equation from the first.

Finally we have that:

$\beta_{1} = \frac{ \sum X_{i}^2 \sum Y_{i} - \sum X_{i} \sum X_{i}Y_{i} }{n\sum X_{i}^2 - (\sum X_{i})^2}$

= $\bar{Y} - \beta_{2}\bar{X}$

Can someone please tell me how these equations follow from the first two?

1

There are 1 best solutions below

0
On

Multiply the first equation by $\sum X_{i} $ and the latter by $n$ to get

$\sum Y_{i} \sum X_{i} = n \beta_{1} \sum X_{i} + \beta_{2}(\sum X_{i})^2$

$n\sum Y_{i} X_{i} = n\beta_{1} \sum X_{i} + n\beta_{2}\sum X_{i}^{2}$

Substract the 2nd equation from the first

$\sum Y_{i} \sum X_{i} - n\sum Y_{i} X_{i} = \beta_{2}(\sum X_{i})^2-n\beta_{2}\sum X_{i}^{2}$.

You can solve

$\beta_{2} = \frac{n\sum X_{i}Y_{i} - \sum X_{i}\sum Y_{i}}{n \sum X_{i}^{2} - (\sum X_{i})^{2}}$

Now plug in this solution to the first initial equation to solve for $\beta_1$.