Bootstrap methods for the up and down test on pyrotechnics sensitivity analysis

We start with a data set recently obtained from a Bruceton test. The data c ome from the study of CS-M-3 ignitor in a military experiment and are analy zed by the up-and-down method of Dixon and Mood (1948). Wie reexamine the m ethod and develop a more appropriate inference that takes account of the sp ecial dependent data structure. Two bootstrap confidence interval procedure s, percentile and bootstrap-t, are introduced to find approximate confidenc e intervals for the parameters of interest. A simulation study shows that t he bootstrap-t, with proper bias corrections, gives better coverage probabi lity, but is considerably more computer-intensive than non-bias-corrected v ersions. This leads to the development of an importance resampling techniqu e which can reduce the CPU time by a factor of 10 or more. Finally, we appl y the proposed procedure to analyze our data set.