Yıl 2019, Cilt 03 , Sayı 1, Sayfalar 15 - 25 2019-08-31

Genetic Algorithms Applied to Fractional Polynomials for Power Selection: Application to Diabetes Data

Barnabe NDABASHİNZE [1] , Gülesen USTUNDAG SİRAY [2] , Luca SCRUCCA [3]


Fractional polynomials are powerful statistic tools used in multivariable building model to select relevant variables and their functional form. This selection of variables, together with their corresponding power is performed through a multivariable fractional polynomials (MFP) algorithm that uses a closed test procedure, called function selection procedure (FSP), based on the statistical significance level α. In this paper, Genetic algorithms, which are stochastic search and optimization methods based on string representation of candidate solutions and various operators such as selection, crossover and mutation; reproducing genetic processes in nature, are used as alternative to MFP algorithm to select powers in an extended set of real numbers (to be specified) by minimizing the Bayesian Information Criteria (BIC). A simulation study and an application to a real dataset are performed to compare the two algorithms in many scenarios. Both algorithms perform quite well in terms of mean square error with Genetic algorithms that yied a more parsimonious model comparing to MFP Algorithm.

Fractional Polynomials, Genetic Algorithms, Function Selection Procedure
  • [1] P. Royston and D. G. Altman, ‘Regression using fractional polynomials of continuous covariates: parsimonious parametric modelling’, Appl. Stat., vol. 43, no. 3, pp. 429–467, 1994.
  • [2] P. Royston and W. Sauerbrei, ‘Multivariable model-building: a pragmatic approach to regression anaylsis based on fractional polynomials for modelling continuous variables’. John Wiley & Sons, 2008.
  • [3] L. Breiman, ‘Bagging predictors’, Mach. Learn., vol. 24, no. 2, pp. 123–140, 1996.
  • [4] J. H. Friedman, ‘Multivariate adaptive regression splines’, Ann. Stat., pp. 1–67, 1991.
  • [5] B. Efron, T. Hastie, I. Johnstone, R. Tibshirani, and others, ‘Least angle regression’, Ann. Stat., vol. 32, no. 2, pp. 407–499, 2004.
  • [6] P. Royston and W. Sauerbrei, Multivariable model-building: a pragmatic approach to regression anaylsis based on fractional polynomials for modelling continuous variables. John Wiley & Sons, 2008.
  • [7] G. Ambler and P. Royston, ‘Fractional polynomial model selection procedures: investigation of Type {I} error rate’, J. Stat. Comput. Simul., vol. 69, no. 1, pp. 89–108, 2001.
  • [8] W. Sauerbrei and P. Royston, ‘Corrigendum: Building multivariable prognostic and diagnostic models: transformation of the predictors by using fractional polynomials’, J. R. Stat. Soc. Ser. A (Statistics Soc., vol. 165, no. 2, pp. 399–400, 2002.
  • [9] C. Darwin, ‘The origin of species by means of natural selection, or, The preservation of favored races in the struggle for life. Vol. 1’, Int. Sci. Libr., 1897.
  • [10] J. H. Holland, Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control, and artificial intelligence. U Michigan Press, 1975.
  • [11] S. Owais, P. Gajdoš, and V. Snášel, ‘Usage of genetic algorithm for lattice drawing’, Concept Lattices Appl., vol. 2005, pp. 82–91, 2005.
  • [12] D. E. Golberg, ‘Genetic algorithms in search, optimization, and machine learning’, Addion wesley, vol. 1989, p. 102, 1989.
  • [13] R. L. Haupt and H. S. Ellen, Practical genetic algorithms. John Wiley & Sons, 2004.
  • [14] L. Scrucca, ‘{GA}: A Package for Genetic Algorithms in {R}’, J. Stat. Softw., vol. 53, no. 4, pp. 1–37, 2013.
  • [15] M. Wahde, Biologically inspired optimization methods: an introduction. WIT press, 2008.
  • [16] G. Ambler and A. Benner, ‘mfp: Multivariable Fractional Polynomials.{ R} package version 1.4. 9’. 2010.
  • [17] A. A. Neath and J. E. Cavanaugh, ‘The Bayesian information criterion: background, derivation, and applications’, Wiley Interdiscip. Rev. Comput. Stat., vol. 4, no. 2, pp. 199–203, 2012.
  • [18] D. E. Goldberg and K. Deb, ‘A comparative analysis of selection schemes used in genetic algorithms’, Found. Genet. algorithms, vol. 1, pp. 69–93, 1991.
  • [19] T. Blickle and L. Thiele, ‘A comparison of selection schemes used in evolutionary algorithms’, Evol. Comput., vol. 4, no. 4, pp. 361–394, 1996.
  • [20] B. L. Miller and D. E. Goldberg, ‘Genetic algorithms, tournament selection, and the effects of noise’, Complex Syst., vol. 9, no. 3, pp. 193–212, 1995.
Birincil Dil en
Konular Matematik
Yayınlanma Tarihi Ağustos
Bölüm Articles
Yazarlar

Yazar: Barnabe NDABASHİNZE
Kurum: CUKUROVA UNIVERSITY
Ülke: Turkey


Yazar: Gülesen USTUNDAG SİRAY (Sorumlu Yazar)
Kurum: CUKUROVA UNIVERSITY
Ülke: Turkey


Yazar: Luca SCRUCCA
Ülke: Italy


Tarihler

Yayımlanma Tarihi : 31 Ağustos 2019

Bibtex @araştırma makalesi { forecasting514761, journal = {Turkish Journal of Forecasting}, issn = {}, eissn = {2618-6594}, address = {Giresun Üniversitesi Fen Edebiyat Fakültesi İstatistik Bölümü, Güre Yerleşkesi, 28100 Merkez, Giresun}, publisher = {Giresun Üniversitesi}, year = {2019}, volume = {03}, pages = {15 - 25}, doi = {10.34110/forecasting.514761}, title = {Genetic Algorithms Applied to Fractional Polynomials for Power Selection: Application to Diabetes Data}, key = {cite}, author = {Ndabashi̇nze, Barnabe and Ustundag Si̇ray, Gülesen and Scrucca, Luca} }
APA Ndabashi̇nze, B , Ustundag Si̇ray, G , Scrucca, L . (2019). Genetic Algorithms Applied to Fractional Polynomials for Power Selection: Application to Diabetes Data . Turkish Journal of Forecasting , 03 (1) , 15-25 . DOI: 10.34110/forecasting.514761
MLA Ndabashi̇nze, B , Ustundag Si̇ray, G , Scrucca, L . "Genetic Algorithms Applied to Fractional Polynomials for Power Selection: Application to Diabetes Data" . Turkish Journal of Forecasting 03 (2019 ): 15-25 <https://dergipark.org.tr/tr/pub/forecasting/issue/50239/514761>
Chicago Ndabashi̇nze, B , Ustundag Si̇ray, G , Scrucca, L . "Genetic Algorithms Applied to Fractional Polynomials for Power Selection: Application to Diabetes Data". Turkish Journal of Forecasting 03 (2019 ): 15-25
RIS TY - JOUR T1 - Genetic Algorithms Applied to Fractional Polynomials for Power Selection: Application to Diabetes Data AU - Barnabe Ndabashi̇nze , Gülesen Ustundag Si̇ray , Luca Scrucca Y1 - 2019 PY - 2019 N1 - doi: 10.34110/forecasting.514761 DO - 10.34110/forecasting.514761 T2 - Turkish Journal of Forecasting JF - Journal JO - JOR SP - 15 EP - 25 VL - 03 IS - 1 SN - -2618-6594 M3 - doi: 10.34110/forecasting.514761 UR - https://doi.org/10.34110/forecasting.514761 Y2 - 2019 ER -
EndNote %0 Turkish Journal of Forecasting Genetic Algorithms Applied to Fractional Polynomials for Power Selection: Application to Diabetes Data %A Barnabe Ndabashi̇nze , Gülesen Ustundag Si̇ray , Luca Scrucca %T Genetic Algorithms Applied to Fractional Polynomials for Power Selection: Application to Diabetes Data %D 2019 %J Turkish Journal of Forecasting %P -2618-6594 %V 03 %N 1 %R doi: 10.34110/forecasting.514761 %U 10.34110/forecasting.514761
ISNAD Ndabashi̇nze, Barnabe , Ustundag Si̇ray, Gülesen , Scrucca, Luca . "Genetic Algorithms Applied to Fractional Polynomials for Power Selection: Application to Diabetes Data". Turkish Journal of Forecasting 03 / 1 (Ağustos 2019): 15-25 . https://doi.org/10.34110/forecasting.514761
AMA Ndabashi̇nze B , Ustundag Si̇ray G , Scrucca L . Genetic Algorithms Applied to Fractional Polynomials for Power Selection: Application to Diabetes Data. TJF. 2019; 03(1): 15-25.
Vancouver Ndabashi̇nze B , Ustundag Si̇ray G , Scrucca L . Genetic Algorithms Applied to Fractional Polynomials for Power Selection: Application to Diabetes Data. Turkish Journal of Forecasting. 2019; 03(1): 15-25.