Testing for parameter constancy in non‐Gaussian time series. (13th July 2012)

• Record Type: Journal Article
• Authors: Han, Lu; McCabe, Brendan
• Is Part Of: Journal of time series analysis. Volume 34:Number 1(2013:Jan.)
• Page Start: 17
• Page End: 29
• Publication Date: 2012-07-13
• Subjects: Time-series analysis -- Periodicals; 519.232
• DOI: 10.1111/j.1467-9892.2012.00810.x
• Languages: English
• ISSNs: 0143-9782

Abstract

<abstract abstract-type="main" xml:lang="en"> <title> <x xml:space="preserve">Abstract</x> </title> <p>This paper investigates testing for parameter constancy in models for non‐Gaussian time series. Models for discrete valued count time series are investigated as well as more general models with autoregressive conditional expectations. Both sup‐tests and <italic>CUSUM</italic> procedures are suggested depending on the complexity of the model being used. The asymptotic distribution of the <italic>CUSUM</italic> test is derived for a general class of conditional autoregressive models.</p> </abstract>