Regression

Display:

Description:
The first data input is the abscissa (X), and the second is the ordinate (Y). Y is explained, and X est explanatory.
Example:     The GNP of a Country (Y) is a variable explained by the number of active persons (X).

The module calculates a and b to place the line closest to the data, i.e.:

      Sum total ( ( Y - Y' )* ( Y - Y') ) is a minimum.

where Y' = ordinate of the point on the line having the same abscissa as the data.
Y-Y' represents the residue supplied as the module output.

In the graphic area, the regression line is drawn with the points corresponding to the data input. When the mouse pointer moves through a point (shown as a red square), the coordinates of the point are displayed in the lower right-hand corner of the graph (under the Center button).
If the window size is changed, the drawing is automatically adjusted to suit the new size.

The text area contains information on the X and Y data (their average and their variance), together with the values of the coefficients a and b of the regression line, and the correlation coefficient between X and Y.

You can switch the two data inputs round by moving their name vertically; the graph and the data are modified accordingly.

The output is a continuous data output that is the residue of the regression.

Graphics :
Under the graphic, you will find a button : that creates a "graphical window" from current drawing. This window let you compare graphics, export them, or print them.

Script

2      module untyped_list ""
3        mod_type integer "103"
3        mod_subtype integer "503"
3        mod_name string "Regression"
3        mod_dads integer_list ""
4          ? integer "4"
4          ? integer "5"
3        coeff_a double "1.54481"
3        coeff_b double "-6412.2176"
3        average_x double "40176.01"
3        average_y double "55652.083"
3        variance_x double "8.9001439e+8"
3        variance_y double "2.3708507e+9"
3        correlation double "0.94650186"