For the simple linear regression model

$$y_i=\beta_0 +\beta_1 x_i$$

I have derived the estimates of $\beta_0=\bar y -\beta_1\bar x$ and $\beta_1=\frac{\Sigma (y_i-\bar y)(x_i-\bar x)}{\Sigma (x_i-\bar x)^2}$ but my book says that it is possible to express $\beta_0=\Sigma a_i Y_i$ and $\beta_1 =\Sigma c_i Y_i$.

How ever I can't seem to factor out $Y_i$ from either expression. For $\beta_0$ all I can get is $\beta_0=\Sigma \frac{y_i}{n}-\beta_1\bar x$ but this has constant term $\beta_1 \bar x$.

For $\beta_1$ I get $\beta_1=\Sigma y_i\frac{x_i-\bar x}{\Sigma (x_i-\bar x)^2}-\frac{\bar y(x_i-\bar x)}{\Sigma(x_i- \bar x)^2}$ again with constant term that I can't get rid of. Does anyone know how to solve it, why these constants should go or how to get rid of them?

  • $\begingroup$ What is $\bar{x}_0$ in the expression of $\beta_1$? $\endgroup$ – Shanks May 20 '18 at 13:01
  • $\begingroup$ Should be written $\hat{\beta}_0$ and $\hat{\beta}_1$ instead of just $\beta_0$ and $\beta_1$ while writing the estimates. $\endgroup$ – Shanks May 20 '18 at 13:03


\begin{align} \hat{\beta}_0 &= \bar{y} - \hat{\beta}_1 .\bar{x}\\ & = \left(\frac{1}{n} \sum \limits_{i=1}^n y_i\right) - \frac{\sum \limits_{i=1}^n (y_i-\bar y)(x_i-\bar x)}{\sum \limits_{i=1}^n (x_i-\bar x)^2} \bar{x}\\ &= \left(\frac{1}{n} \sum \limits_{i=1}^n y_i\right) - \frac{\sum \limits_{i=1}^n (y_i-\bar y)x_i}{\sum \limits_{i=1}^n (x_i-\bar x)^2} \bar{x}\\ &= \left(\frac{1}{n} \sum \limits_{i=1}^n y_i\right) - \sum \limits_{i=1}^n \left(\frac{x_i\cdot \bar{x}}{\sum \limits_{i=1}^n (x_i-\bar x)^2}\right)y_i + \bar{y} \frac{\bar{x}\sum\limits _{i=1}^n x_i}{\sum \limits_{i=1}^n (x_i-\bar x)^2}\\ &= \sum \limits_{i=1}^n \left(\frac{1}{n}\right) y_i - \sum \limits_{i=1}^n \left(\frac{x_i\cdot \bar{x}}{\sum \limits_{i=1}^n (x_i-\bar x)^2}\right)y_i + \sum \limits_{i=1}^n \left(\frac{\bar{x}\sum\limits _{i=1}^n x_i}{n\sum \limits_{i=1}^n (x_i-\bar x)^2}\right)y_i \end{align}

Now the rest should be done easily.

| cite | improve this answer | |

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.