TY - JOUR
TI - A Self-Organizing Model for Logic Regression
PY - 2010/04/09
Y2 - 2024/06/14
JF - European Journal of Pure and Applied Mathematics
JA - Eur. J. Pure Appl. Math.
VL - 3
IS - 2
LA - en
UR - https://www.ejpam.com/index.php/ejpam/article/view/602
SP - 163-173
AB - Logic regression, as developed by Ruczinski, Kooperberg, and LeBlanc (Ruczinski, Kooperberg, and LeBlanc 2003) is a multivariable regression methodology that constructs logical relationships among Boolean predictor variables that best predicts a Boolean dependent variable.Â More specifically, they find a regression model of the form g(E/Y)= b0+b1L1+...+bmLmÂ Â where both the coefficients b0,b1,...,bmÂ and the logical expressions Lj, j=1,...,m Â are determined.Â The logical expressionsÂ Â are logical relationships among the predictor variables, such as "X1,X2Â are true but not X5"Â Â , or "X3,X5,X7 are true but not X1Â or X2".Â In their paper, the authors investigate the use a simulated annealing algorithm.Â In this paper, we use the Group Method of Data Handling (GMDH) to approach the problem.Â Â
ER -