Ταξινόμηση ουρών συναρτήσεων κατανομών πιθανότητας
KeywordsΤαξινόμηση ουρών συναρτήσεων κατανομών ; Συναρτήσεις ; Κατανομές ; Ακραίες τιμές ; Extreme spacing
Methodologies to test hypotheses about the tail-heaviness of an underlying distribution are introduced based on results of Rojo (1996) using the limiting behavior of the extreme spacings. The tests are consistent and have point-wise robust levels in the sense of Lehmann (2005) and Lehmann and Loh (1990). Simulation results based on these new methodologies indicate that the tests exhibit medium control of the probability of Type I error and have adequate power properties for finite sample sizes. The tests are compared with a test proposed by Bryson (1974) and it is seen that Bryson’s test can not always control the Type I error. The operating characteristics of the tests are also explored when the data is blocked. It turns out that the power generally increases substantially by blocking. The methodology is illustrated by analyzing one particular data set.