A theory based on Markovian principles and transition probability desc
ription is presented here to predict the statistics of the ordered pea
ks in a random process. It takes into account the statistical dependen
ce that exists between the peaks in a single time history. The theory
is more general than the other existing theories and, in special cases
, it is shown to lead to the independent order statistics as well as t
o a first passage problem. Digital simulation has been carried out to
validate the analytical results. The effects of governing parameters o
n the statistics of various orders of peaks have also been studied.