VariableSelection Procedures:
In regression analysis, variableselection procedures are aimed at selecting a reduced set of the independent variables  the ones providing the best fit to the model.
The criterion for selecting is usually the following Fstatistic:

where n is the total number of data points, SSE is the sum squares due to error  that is, the sum of squares minimized by the least squares method. If adding the variable x_{p+1} to variables x_{1},...,x_{p} does not improve (or deletion of the variable x_{p+1} does not worsen) the fit significantly, this statistic follows an Fdistribution; otherwise, the statistic tends to take on larger values.
There are several methods for variableselection procedures. Some of them are stepwise regression, forward selection, backward elimination.
If the symbols do not display properly, try
the graphic version of this page