Premium
Estimating the unknown change point in the parameters of the lognormal distribution
Author(s) -
Jandhyala V. K.,
Fotopoulos S. B.
Publication year - 2007
Publication title -
environmetrics
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.68
H-Index - 58
eISSN - 1099-095X
pISSN - 1180-4009
DOI - 10.1002/env.808
Subject(s) - log normal distribution , mathematics , statistics , econometrics , point estimation , point (geometry) , distribution (mathematics) , maximum likelihood , german , interval (graph theory) , confidence interval , geography , mathematical analysis , combinatorics , geometry , archaeology
We develop change‐point methodology for identifying dynamic trends in the parameters of a two‐parameter lognormal distribution. The methodology primarily considers the asymptotic distribution of the maximum likelihood estimate of the unknown change point. Among others, the asymptotic distribution enables one to construct confidence interval estimates for the unknown change point. The methodology is applied to identify changes in the monthly water discharges of the Nacetinsky Creek in the German part of the Ergebirge Mountains. Copyright © 2006 John Wiley & Sons, Ltd.