The GLMSELECT Procedure
-
Overview
- Getting Started
-
Syntax
-
DetailsModel-Selection MethodsModel Selection IssuesCriteria Used in Model Selection MethodsCLASS Variable Parameterization and the SPLIT OptionMacro Variables Containing Selected ModelsUsing the STORE StatementBuilding the SSCP MatrixModel AveragingUsing Validation and Test DataCross ValidationExternal Cross ValidationScreeningDisplayed OutputODS Table NamesODS Graphics
-
Examples
- References
Lasso Selection (LASSO)
LASSO (least absolute shrinkage and selection operator) selection arises from a constrained form of ordinary least squares
regression where the sum of the absolute values of the regression coefficients is constrained to be smaller than a specified
parameter. More precisely let 
denote the matrix of covariates and let 
denote the response, where the 
s have been centered and scaled to have unit standard deviation and mean zero, and has mean zero. Then for a given parameter t, the LASSO regression coefficients 
are the solution to the constrained optimization problem
![\[ \min ||\mb{y}-\bX \bbeta ||^2 \qquad \mbox{subject to} \quad \sum _{j=1}^{m} | \beta _ j | \leq t \]](images/statug_glmselect0031.png)
Provided that the LASSO parameter t is small enough, some of the regression coefficients will be exactly zero. Hence, you can view the LASSO as selecting a subset of the regression coefficients for each LASSO parameter. By increasing the LASSO parameter in discrete steps, you obtain a sequence of regression coefficients where the nonzero coefficients at each step correspond to selected parameters.
Early implementations (Tibshirani 1996) of LASSO selection used quadratic programming techniques to solve the constrained least squares problem for each LASSO parameter of interest. Later Osborne, Presnell, and Turlach (2000) developed a "homotopy method" that generates the LASSO solutions for all values of t. Efron et al. (2004) derived a variant of their algorithm for least angle regression that can be used to obtain a sequence of LASSO solutions from which all other LASSO solutions can be obtained by linear interpolation. This algorithm for SELECTION= LASSO is used in PROC GLMSELECT. It can be viewed as a stepwise procedure with a single addition to or deletion from the set of nonzero regression coefficients at any step.
As with the other selection methods that PROC GLMSELECT supports, you can specify a criterion to choose among the models at each step of the LASSO algorithm by using the CHOOSE= option. You can also specify a stopping criterion by using the STOP= option. For more information, see the discussion in the section Forward Selection (FORWARD). The model degrees of freedom that PROC GLMSELECT uses at any step of the LASSO are simply the number of nonzero regression coefficients in the model at that step. Efron et al. (2004) cite empirical evidence for doing this but do not give any mathematical justification for this choice.
A modification of LASSO selection that is suggested in Efron et al. (2004) uses the LASSO algorithm to select the set of covariates in the model at any step, but it uses ordinary least squares regression with just these covariates to obtain the regression coefficients. You can request this hybrid method by specifying the LSCOEFFS suboption of the SELECTION= LASSO option.