APPLICATION OF NONPARAMETRIC BINARY REGRESSION TO EVALUATE THE SENSITIVITY OF EXPLOSIVES

The performance of slapper detonators depends on the sensitivity of th e explosive material within the detonators to a voltage stimulus. A se ries of experiments is typically used to estimate the sensitivity of t he explosive material by subjecting individual detonators to various s timulus levels. The traditional methods for selecting stimulus levels and analyzing the resulting binary data are based oil a parametric pro bit model that relates the probability of detonation to the level of t he voltage stimulus. In this article, we explore an alternative method for analyzing the binary data using nonparametric regression. The use of this alternative method is illustrated by analyzing the ungrouped binary data resulting from a series of 25 tests that were used to char acterize a single lot of detonators. We conclude that nonparametric re gression can be very useful in visualizing the underlying relationship between a binary response and a covariate, even when the sample size is relatively small.