The predictive accuracy of feed forward neural networks and multiple regression in the case of heteroscedastic data

During the last few years, several comparative studies for regression analysis and neural networks have been published. Our paper contributes to this stream of research by comparing the performance of feed forward neural network and multiple regression when heteroscedasticity is present in the data. Datasets are simulated that vary systematically on various dimensions like sample size, noise levels and number of independent variables to assess the consequences of deviations from underlying assumptions of homoscedasticity on the comparative performance of regression analysis and neural networks. Comparative analysis is carried out using appropriate experimental design and the results are presented.

[1]  Tom Heskes,et al.  Practical Confidence and Prediction Intervals , 1996, NIPS.

[2]  William Remus,et al.  Neural network models for intelligent support of managerial decision making , 1994, Decis. Support Syst..

[3]  Huynh Huynh,et al.  Some approximate tests for repeated measurement designs , 1978 .

[4]  B. J. Winer.  Statistical Principles in Experimental Design , 1992 .

[5]  Michael H. Kutner.  Applied Linear Statistical Models , 1974 .

[6]  Jean Gaudart,et al.  Comparison of the performance of multi-layer perceptron and linear regression for epidemiological data , 2004, Comput. Stat. Data Anal..

[7]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[8]  Brad Warner,et al.  Understanding Neural Networks as Statistical Tools , 1996 .

[9]  Parag C. Pendharkar,et al.  Scale economies and production function estimation for object-oriented software component and source code documentation size , 2006, Eur. J. Oper. Res..

[10]  Barbara A. Kitchenham,et al.  Using simulated data sets to compare data analysis techniques used for software cost modelling , 2001, IEE Proc. Softw..

[11]  H. Glejser.  A New Test for Heteroskedasticity , 1969 .

[12]  Lisa M. Lix,et al.  Testing Repeated Measures Hypotheses When Covariance Matrices are Heterogeneous , 1993 .

[13]  R. Sawyer,et al.  Sample Size and the Accuracy of Predictions Made from Multiple Regression Equations , 1982 .

[14]  Wilpen L. Gorr,et al.  Comparative study of artificial neural network and statistical models for predicting student grade point averages , 1994 .

[15]  S. Chatterjee,et al.  Use of the Bootstrap and Cross-validation in Ridge Regression , 1986 .

[16]  Geoffrey E. Hinton.  Learning Translation Invariant Recognition in Massively Parallel Networks , 1987, PARLE.

[17]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[18]  Kenneth Levenberg.  A METHOD FOR THE SOLUTION OF CERTAIN NON – LINEAR PROBLEMS IN LEAST SQUARES , 1944 .

[19]  Confidence intervals for the slope of a regression line when the error term has nonconstant variance , 1996 .