A new contribution to nonlinear robust regression and classification with mars and its applications to data mining for quality control in manufacturing

Download

index.pdf

Date

2008

Author

Yerlikaya, Fatma

Metadata

Show full item record

Item Usage Stats

445
views

173
downloads

Multivariate adaptive regression spline (MARS) denotes a modern methodology from statistical learning which is very important in both classification and regression, with an increasing number of applications in many areas of science, economy and technology. MARS is very useful for high dimensional problems and shows a great promise for fitting nonlinear multivariate functions. MARS technique does not impose any particular class of relationship between the predictor variables and outcome variable of interest. In other words, a special advantage of MARS lies in its ability to estimate the contribution of the basis functions so that both the additive and interaction effects of the predictors are allowed to determine the response variable. The function fitted by MARS is continuous, whereas the one fitted by classical classification methods (CART) is not. Herewith, MARS becomes an alternative to CART. The MARS algorithm for estimating the model function consists of two complementary algorithms: the forward and backward stepwise algorithms. In the first step, the model is built by adding basis functions until a maximum level of complexity is reached. On the other hand, the backward stepwise algorithm is began by removing the least significant basis functions from the model. In this study, we propose not to use the backward stepwise algorithm. Instead, we construct a penalized residual sum of squares (PRSS) for MARS as a Tikhonov regularization problem, which is also known as ridge regression. We treat this problem using continuous optimization techniques which we consider to become an important complementary technology and alternative to the concept of the backward stepwise algorithm. In particular, we apply the elegant framework of conic quadratic programming which is an area of convex optimization that is very well-structured, herewith, resembling linear programming and, hence, permitting the use of interior point methods. The boundaries of this optimization problem are determined by the multiobjective optimization approach which provides us many alternative solutions. Based on these theoretical and algorithmical studies, this MSc thesis work also contains applications on the data investigated in a TÜBİTAK project on quality control. By these applications, MARS and our new method are compared.

Subject Keywords

Mathematics., Statistical learning.

URI

http://etd.lib.metu.edu.tr/upload/3/12610037/index.pdf
https://hdl.handle.net/11511/18008

Collections

Graduate School of Applied Mathematics, Thesis

Suggestions

OpenMETU
Core

Continuous optimization applied in MARS for modern applications in finance, science and technology Taylan, Pakize; Weber, Gerhard Wilhelm; Yerlikaya, Fatma (2008-05-23) Multivariate adaptive regression spline (MARS) denotes a tool from statistics, important in classification and regression, with applicability in many areas of finance, science and technology. It is very useful in high dimensions and shows a great promise for fitting nonlinear multivariate functions. The MARS algorithm for estimating the model function consists of two subalgorithms. We propose not to use the second one (backward stepwise algorithm), but we construct a penalized residual sum of squares for a ...
On the foundations of parameter estimation for generalized partial linear models with B-splines and continuous optimization TAYLAN, PAKİZE; Weber, Gerhard Wilhelm; Liu, Lian; Yerlikaya-Ozkurt, Fatma (Elsevier BV, 2010-07-01) Generalized linear models are widely used in statistical techniques. As an extension, generalized partial linear models utilize semiparametric methods and augment the usual parametric terms with a single nonparametric component of a continuous covariate. In this paper, after a short introduction, we present our model in the generalized additive context with a focus on the penalized maximum likelihood and the penalized iteratively reweighted least squares (P-IRLS) problem based on B-splines, which is attract...
Mathematical contributions to dynamics and optimization of gene-environment networks Weber, Gerhard Wilhelm; Tezel, Aysun; TAYLAN, PAKİZE; Soyler, Alper; Cetin, Mehmet (Informa UK Limited, 2008-01-01) This article contributes to a further introduction of continuous optimization in the field of computational biology which is one of the most challenging and emerging areas of science, in addition to foundations presented and the state-of-the-art displayed in [C.A. Floudas and P.M. Pardalos, eds., Optimization in Computational Chemistry and Molecular Biology: Local and Global Approaches, Kluwer Academic Publishers, Boston, 2000]. Based on a summary of earlier works by the coauthors and their colleagues, it r...
Uncertainty models for vector based functional curves and assessing the reliability of G-Band Kurtar, Ahmet Kürşat; Düzgün, H. Şebnem; Department of Geodetic and Geographical Information Technologies (2006) This study is about uncertainty medelling for vector features in geographic information systems (GIS). It has mainly two objectives which are about the band models used for uncertainty modelling . The first one is the assessment of accuracy of GBand model, which is the latest and the most complex uncertainty handling model for vector features. Some simulations and tests are applied to test the reliability of accuracy of G-Band with comparing Chrisman’s epsilon band model, which is the most frequently used b...
A new approach to multivariate adaptive regression splines by using Tikhonov regularization and continuous optimization TAYLAN, PAKİZE; Weber, Gerhard Wilhelm; Ozkurt, Fatma Yerlikaya (2010-12-01) This paper introduces a model-based approach to the important data mining tool Multivariate adaptive regression splines (MARS), which has originally been organized in a more model-free way. Indeed, MARS denotes a modern methodology from statistical learning which is important in both classification and regression, with an increasing number of applications in many areas of science, economy and technology. It is very useful for high-dimensional problems and shows a great promise for fitting nonlinear multivar...

Citation Formats

F. Yerlikaya, “A new contribution to nonlinear robust regression and classification with mars and its applications to data mining for quality control in manufacturing,” M.S. - Master of Science, Middle East Technical University, 2008.