Null distribution of the likelihood ratio statistic for feed-forward neural networks.

Despite recent publications exploring model complexity with modern regression methods, their dimensionality is rarely quantified in practice and the distributions of related test statistics are not well characterized. Through a simulation study, we describe the null distribution of the likelihood ratio statistic for several different feed-forward neural network models.

Department of Biostatistics, Graduate School of Public Health, Universityof Pittsburgh, Pennsylvania 15261, USA.