Gretl - calculate the estimated variance of the residuals

Question

I want to learn the statistics package gretl.

My first attempt to do so is to calculate a linear regression model of a set of data:

$$y_i = \alpha + \beta x_i + u_i$$

First I want to create a crossplot of the data and then calculate the variance of the residuals $s^2_u$ and also those of $\alpha$ and $\beta$.

My questions are:

How to get the crossplot, I do not see any option in the menu which says crossplot? Is this possible in gretl?

When I click Summary statistics I think I get the $s^2$ of the data, however is it also possible to get the the variance of the residuals $s^2_u$ and also those of $\alpha$ and $\beta$?

Is it also possible to calculate in gretl a model without $\alpha$, such as: $$y_i = \beta x_i + u_i$$

I appreciate your answers!

UPDATE

My gretl window:

Answer 1

I think this is a stack overflow question and not a Stats question but here goes...

It is possible to get a model without an intercept $\alpha$; simply exclude the const from your X values when you define your model.

To get the variance of the residuals (and a plot of them) try within the model window to go Test > Normality of Residuals.

I don't understand what exactly you mean by crossplot, do you mean fitted against estimated values? (In which case would be Graphs > Fitted, Actual Plots > Actual vs. Fitted.