Exact and approximate runs distributions
Let R = Rn denote the total (and unconditional) number of runs of successes or failures in a sequence of n Bernoulli (p) trials, where p is assumed to be known throughout. The exact distribution of R is related to a convolution of two negative binomial random variables with parameters p and q (=1-p). Using the representation of R as the sum of 1-dependent indicators, a Berry-Esséen theorem is derived; the obtained rate of sup norm convergence is O(n - 1/2. This yields an unconditional version of the classical result of Wald and Wolfowitz. © 1992, Taylor & Francis Group, LLC. All rights reserved.
Communications in Statistics - Theory and Methods
Exact and approximate runs distributions.
Communications in Statistics - Theory and Methods,
Retrieved from: https://digitalcommons.mtu.edu/michigantech-p/9233