Selection of Ordinally Scaled Independent Variables
نویسندگان
چکیده
Ordinal categorial variables are a common case in regression modeling. Although the case of ordinal response variables has been well investigated, less work has been done concerning ordinal predictors. This article deals with the selection of ordinally scaled independent variables in the classical linear model, where the ordinal structure is taken into account by use of a difference penalty on adjacent dummy coefficients. It is shown how the Group Lasso can be used for the selection of ordinal predictors, and an alternative blockwise Boosting procedure is proposed. Emphasis is placed on the application of the presented methods to the (Comprehensive) ICF Core Set for chronic widespread pain.
منابع مشابه
Comparing Multiple Attribute System Selection and Social Choice Preference Aggregation
Comparison of information systems by evaluation of several specified criteria is a critical and often arduous process in organizational IT. The process is often done by compilation and consolidation of utility values using weights for the criteria. There is ample room for manipulation and misrepresentation of system aspects via the use of utility values and weights. In this work simulation resu...
متن کاملAxisymmetric Scaled Boundary Finite Element Formulation for Wave Propagation in Unbounded Layered Media
Wave propagation in unbounded layered media with a new formulation of Axisymmetric Scaled Boundary Finite Element Method (AXI-SBFEM) is derived. Dividing the general three-dimensional unbounded domain into a number of independent two-dimensional ones, the problem could be solved by a significant reduction in required storage and computational time. The equations of the corresponding Axisymmetri...
متن کاملThe Data Analytic Implications of Human Psychology’s Dimensions Being Ordinally Scaled
Scientific findings involve description, and description requires measurements on the dimensions descriptive of the phenomena described. The richer a description the more multidimensional is the abstract space in which that description in effect locates what is described. Many of the dimensions of human psychological phenomena, including those of psychotherapy, are naturally gradated only ordin...
متن کاملLimit distribution of the degrees in scaled attachment random recursive trees
We study the limiting distribution of the degree of a given node in a scaled attachment random recursive tree, a generalized random recursive tree, which is introduced by Devroye et. al (2011). In a scaled attachment random recursive tree, every node $i$ is attached to the node labeled $lfloor iX_i floor$ where $X_0$, $ldots$ , $X_n$ is a sequence of i.i.d. random variables, with support in [0,...
متن کاملRandom assignment of multiple indivisible objects
We consider random assignment of multiple indivisible objects. When each agent receives one object, Bogomolnaia and Moulin (2001) show that the probabilistic serial mechanism is ordinally efficient, envy-free and weakly strategy-proof. When each agent receives more than one object, we propose a generalized probabilistic serial mechanism that is ordinally efficient and envy-free but not weakly s...
متن کامل