A Hybrid Computational Method Based on Convex Optimization for Outlier Problems: Application to Earthquake Ground Motion Prediction

Statistical modelling plays a central role for any prediction problem of interest. However, predictive models may give misleading results when the data contain outliers. In many real-world applications, it is important to identify and treat the outliers without direct elimination. To handle such issues, a hybrid computational method based on conic quadratic programming is introduced and employed on earthquake ground motion dataset. This method aims to minimize the impact of the outliers on regression estimators as well as handling the nonlinearity in the dataset. Results are compared against widely used parametric and nonparametric ground motion prediction models.

[1]  Gerhard-Wilhelm Weber,et al.  An approach to the mean shift outlier model by Tikhonov regularization and conic programming , 2014, Intell. Data Anal..

[2]  Antanas Zilinskas,et al.  On similarities between two models of global optimization: statistical models and radial basis functions , 2010, J. Glob. Optim..

[3]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[4]  Peter J. Rousseeuw,et al.  Robust Regression and Outlier Detection , 2005, Wiley Series in Probability and Statistics.

[5]  J. Simonoff,et al.  Procedures for the Identification of Multiple Outliers in Linear Models , 1993 .

[6]  Arkadi Nemirovski,et al.  Lectures on modern convex optimization - analysis, algorithms, and engineering applications , 2001, MPS-SIAM series on optimization.

[7]  A. C. Rencher.  Linear models in statistics , 1999 .

[8]  Ken Lane,et al.  What Is Robust Regression and How Do You Do It , 2002 .

[9]  W. Krzanowski,et al.  Simultaneous variable selection and outlier identification in linear regression using the mean-shift outlier model , 2008 .

[10]  David M. Boore,et al.  SEA99: A Revised Ground-Motion Prediction Relation for Use in Extensional Tectonic Regimes , 2005 .

[11]  S. Akkar,et al.  A Local Ground-Motion Predictive Model for Turkey, and Its Comparison with Other Regional and Global Ground-Motion Models , 2010 .

[12]  G. Weber,et al.  An alternative approach to the ground motion prediction problem by a non-parametric adaptive regression method , 2014 .

[13]  G. Weber,et al.  CMARS: a new contribution to nonparametric regression with multivariate adaptive regression splines supported by continuous optimization , 2012 .

[14]  B. Ripley,et al.  Robust Statistics , 2018, Encyclopedia of Mathematical Geosciences.

[15]  J. Brian Gray,et al.  Introduction to Linear Regression Analysis , 2002, Technometrics.

[16]  A. ilinskas,et al.  One-Dimensional global optimization for observations with noise , 2005 .

[17]  Vic Barnett,et al.  Outliers in Statistical Data , 1980 .

[18]  S. Weisberg,et al.  Residuals and Influence in Regression , 1982 .

[19]  Iztok Peruš,et al.  Ground‐motion prediction by a non‐parametric approach , 2010 .

[20]  Amir Hossein Alavi,et al.  Prediction of principal ground-motion parameters using a hybrid method coupling artificial neural networks and simulated annealing , 2011 .

[21]  PETER J. ROUSSEEUW,et al.  Computing LTS Regression for Large Data Sets , 2005, Data Mining and Knowledge Discovery.

[22]  J. Tezcan,et al.  Support vector regression for estimating earthquake response spectra , 2012, Bulletin of Earthquake Engineering.

[23]  Clifford H. Thurber,et al.  Parameter estimation and inverse problems , 2005 .

[24]  Yurii Nesterov,et al.  Interior-point polynomial algorithms in convex programming , 1994, Siam studies in applied mathematics.

[25]  Dale Borowiak,et al.  Linear Models, Least Squares and Alternatives , 2001, Technometrics.

[26]  Polat Gülkan,et al.  The recently compiled Turkish strong motion database: preliminary investigation for seismological parameters , 2010 .

[27]  G. Atkinson,et al.  Ground-Motion Prediction Equations for the Average Horizontal Component of PGA, PGV, and 5%-Damped PSA at Spectral Periods between 0.01 s and 10.0 s , 2008 .

[28]  J. Freidman,et al.  Multivariate adaptive regression splines , 1991 .

[29]  Gerhard-Wilhelm Weber,et al.  A Review and New Contribution on Conic Multivariate Adaptive Regression Splines (CMARS): A Powerful Tool for Predictive Data Mining , 2014 .