Premium
On multiple portmanteau tests *
Author(s) -
Katayama Naoya
Publication year - 2009
Publication title -
journal of time series analysis
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.576
H-Index - 54
eISSN - 1467-9892
pISSN - 0143-9782
DOI - 10.1111/j.1467-9892.2009.00621.x
Subject(s) - mathematics , statistic , residual , joint probability distribution , asymptotic analysis , statistics , test statistic , statistical hypothesis testing , algorithm
. The portmanteau statistic based on the first m residual autocorrelations is used for diagnostic checks on the adequacy of fitting a model with varying m . In this article, we propose an approximation of the joint probability of multiple portmanteau tests with different degrees of freedom (DF). This distribution is easy to compute when all DF are even integers; its empirical behaviour is clarified in terms of asymptotic theory.