In multivariate analysis, we used the method of stepwise multivariate linear regression for each subgroup.
Then, a heuristic method of stepwise regression was implemented for further feature selection.
The method of stepwise regression used in the analysis of these data is controversial in some contexts, but generally remains an accepted method of hypothesis testing and generation.
Multivariate logistic regression, using the method of stepwise selection, was subsequently applied to identify independent predictors of clinically significant emotional distress.
The general linear start model includes all independent variables, whereas the final model contains only predictive factors after using the automatic method of stepwise backward selection.
A multiple linear regression model for the transformed acrylamide data was then fitted, using the method of stepwise forward selection of most significant (P < 0.05, F-test) explanatory variables, then factors and finally interactions between terms already in the model.
In the multiple regression analysis, when a parameter is a dependent variable and the others are all the variables, regression analysis was performed with SPSS 20.0 software, and we use the method of "stepwise" to bring in variables (stepping method criteria: Entry 0.05, Removal 0.10).
The method of backward stepwise elimination was used as the model fitting strategy.
In this research for associations between blood lead levels and blood pressure in NHANES II, the method of forward stepwise regression was used.
While it is not unlikely to observe agreement in subset selection methods in the situation of relatively few potentially weakly correlated variables, the deficiencies of stepwise methods become more apparent when number of candidate variables increase and issues of multicollinearity come into play.
