I have a three variable multiple regression, where if one of my independent variables is zero the dependent will be zero. In Excel's single regression add-in feature you can set the "constant to zero" to account for this. How do I go about doing this in the multiple regression model?
If the curve is forced through zero, the intercept is set to 0 before the regression is calculated, thereby setting the bias to favor the low end of the calibration range by “pivoting” the function around the origin to find the best fit and resulting in one less degree of freedom. Regards,Rachel Gomez