If you only have $y_i = \hat{\beta_0} + \hat{\beta_1} x_i + \hat{\epsilon_i}$ , Then $\hat{\sigma}_{\beta_1} = \sqrt{ \frac{\sum_{i=1}^{n} \hat{\epsilon}_i} {(n-2)(\sum_{i=1}^{n} (x_i-\bar{x}))} }$
Say $y_i = x_i\hat{\beta} + \hat{\epsilon}$, where x is a row vector of features and $\beta$ is a column vector of betas.
How would we calculate standard error for each beta?
