Multivariate Adaptive Regression Splines (MARS) is a supervised learning model in machine learning, not obtained by an ensemble method. Ensemble methods are gathered from samples comprising hundreds or thousands of learners that serve the common purpose improving stability and accuracy algorithms. This study presented REMARS (Random MARS), new MARS selection approach using Random Forest (RF) al...

Generalized additive models are useful in finding predictor-response relationships in many kinds of data without using a specific model. They combine the ability to explore many nonparametric relationships simultaneously with the distributional flexibility of generalized linear models. The approach often brings to light nonlinear dependency structures in your data. This paper discusses an examp...

Multimodal therapy is generally more effective than single-agent treatment for cancer. rRp450 is an engineered herpes simplex viral mutant that replicates in and kills tumor cells in a relatively selective fashion. It also expresses, in infected cells, the cyclophosphamide (CPA)-sensitive rat cytochrome P450 2B1 (CYP2B1) and the ganciclovir (GCV)-sensitive herpes simplex virus thymidine kinase ...

The primary aim of this study was to evaluate the psychometric properties of the Steinke Sexual Concerns Inventory-General Cardiac Version (SSCI-GCV) and to examine its use across multiple cardiac diagnoses. A sub-analysis of a cross-sectional sample of 205 cardiac patients from the central USA was completed. Our analyses yielded promising evidence that the SSCI-GCV is a reliable (Cronbach's al...

In many ill-posed problems it can be assumed that the error in the data is dominated by noise which is independent identically normally distributed. Given this assumption the residual should also be normally distributed with similar mean and variance. This idea has been used to develop three statistical diagnostic tests to constrain the region of plausible solutions. This project aims to develo...

In the paper we consider new estimators of expected values E w(X) of functions of a random variable X. The new estimators are based on Gauss quadrature, a numerical method frequently used to approximate integrals over finite intervals. We apply the new estimators in Partial Cross Validation, a numerical method for finding optimal smoothing parameters in nonparametric curve estimation. We show t...