Since variable selection is important in quantitative structure property/activity studies, in this paper comparison between the genetic algorithm and several common methods such as forward method, backward elimination and stepwise regression is performed.

First the stepwise regression was applied to screen the habitat factors,then analytic hierarchy(AHP) process was applied to determined the weights of the factors.

The temperature compensating model is gained in the help of the method of stepwise regression by temperature experiment repeated, and its applicability is validated.

The relation of RLG s bias and temperature was analyzed in the help of the method of stepwise regression by temperature experiment repeated.

The new kind of temperature compensating model is established in the help of the method of stepwise regression by lots of high-low temperature experiment repeated.

Establishment of TA15 titanium alloy constitutive model based on stepwise regression method;

Application of stepwise regression method in flood level forecast of the lower Yellow River;

The“optimum”independent variable subsets of macro-variables testable(deformation temperature、strain rate and strain)influencing the flow stress have been determined by using stepwise regression method.

05,using Pettengill s excess market return model and Fama s two pass regression method.

Based on the capacitance distributions from 12-electrod capacitance sensor,using stepwise regression method,the capacitance relation of oil-gas two phase flow based on flow pattern is developed.

Based on D-S evidence theory and stepwise regression method,combining the power spectrum density function characteristics of differential pressure fluctuation signals and capacitance information from capacitance sensor,a new flow pattern identification method of oil-gas two phase flow was proposed.