Statistics – Computation
Scientific paper
2012-03-28
Statistics
Computation
Under revision to Technometrics
Scientific paper
Variable selection is recognized as one of the most critical steps in statistical modeling. The problems encountered in engineering and social sciences are commonly characterized by over-abundance of explanatory variables, non-linearities and unknown interdependencies between the regressors. An added difficulty is that the analysts may have little or no prior knowledge on the relative importance of the variables. To provide a robust method for model selection, this paper introduces a technique called the Multi-objective Genetic Algorithm for Variable Selection (MOGA-VS) which provides the user with an efficient set of regression models for a given data-set. The algorithm considers the regression problem as a two objective task, where the purpose is to choose those models over the other which have less number of regression coefficients and better goodness of fit. In MOGA-VS, the model selection procedure is implemented in two steps. First, we generate the frontier of all efficient or non-dominated regression models by eliminating the inefficient or dominated models without any user intervention. Second, a decision making process is executed which allows the user to choose the most preferred model using visualizations and simple metrics.
Kuosmanen Timo
Malo Pekka
Sinha Ankur
No associations
LandOfFree
A Multi-objective Procedure for Efficient Regression Modeling does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with A Multi-objective Procedure for Efficient Regression Modeling, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and A Multi-objective Procedure for Efficient Regression Modeling will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-272897