A Comparison of Neural Network and Expert Systems Algorithms with Common Multivariate Procedures for Analysis of Social Science Data

Abstract

New computer techniques for data analysis, notably the algorithms associated with neural networks and with expert systems, have not caught on to a significant extent in social science. To appraise these developments, an empirical assessment is conducted in which expert systems and neural network approaches are compared with multiple linear regression, logistic regression, effects analysis, path analysis, and discriminant analysis. A simple method of partitioning neural network output layer connections in terms of input nodes (corresponding to independent variables) is also presented, allowing neural net analysis for modeling as well as classification purposes. It is concluded that back-propagation (neural networks) is more effective than other procedures, sometimes strikingly so, in correctly classifying the dependent, even when the amount of noise in the model is high. Back-propagation was of less help, however, in causal inference. None of the techniques performed well by this important criterion. The ID3 algorithm is found to provide a useful mode of knowledge representation quite different from other procedures. While this may be preferred by some analysts for certain types of research, ID3 is not consistently superior to procedures in the multiple linear general model (MLGH) family in terms of effectiveness, either for classification or for causal inference. Keywords: statistical inference, computers, modeling, simulation, regression, discriminant analysis, effects analysis, path analysis, expert systems, ID3, neural networks, back-propagation.