Comparative evaluation for alternative variable importance rankings for pedestrian injury severities

Statistical Inference for Variable Importance

Many statistical problems involve the learning of an importance/effect of a variable for predicting an outcome of interest based on observing a sample of n independent and identically distributed observations on a list of input variables and an outcome. For example, though prediction/machine learning is, in principle, concerned with learning the optimal unknown mapping from input variables to a...

Alternative Ordered Response Frameworks for Examining Pedestrian Injury Severity in New York City

This paper focuses on identifying the appropriate ordered response structure for modeling pedestrian injury severity. The alternative ordered response approaches considered for the empirical analysis include: ordered logit model (OL), generalized ordered logit model (GOL) and latent segmentation based ordered logit model (LSOL). The GOL and LSOL models enhance the traditional OL model in differ...

Alternative Methods to Quantify Variable Importance in Ecology

Mesenchymal Stem Cells as an Alternative for Schwann Cells in Rat Spinal Cord Injury

Background: Spinal cord has a limited capacity to repair therefore, medical interventions are necessary for treatment of injuries. Transplantation of Schwann cells has shown a great promising result for spinal cord injury (SCI). However, harvesting Schwann cell has been limited due to donor morbidity and limited expansion capacity. Furthermore, accessible sources such as bone marrow stem cells ...

Evaluation Methods for Rankings of Facetvalues for Faceted Search

We introduce two metrics aimed at evaluating systems that select facetvalues for a faceted search interface. Facetvalues are the values of meta-data fields in semi-structured data and are commonly used to refine queries. It is often the case that there are more facetvalues than can be displayed to a user and thus a selection has to be made. Our metrics evaluate these selections based on binary ...