Publications de l'Institut Mathématique, Nouvelle Série Vol. 88(102), pp. 87–98 (2010) 

$AR(1)$ TIME SERIES WITH APPROXIMATED BETA MARGINALBozidar V. PopovicStatistical Office of the Republic of Serbia, Belgrade, SerbiaAbstract: We consider the $AR(1)$ time series model $X_t\beta X_{t1}=\xi_t$, $\beta^{p}\in\mathbb{N}\smallsetminus\{1\}$, when $X_t$ has Beta distribution $\mathrm{B}(p,q)$, $p\in(0,1]$, $q>1$. Special attention is given to the case $p=1$ when the marginal distribution is approximated by the power law distribution closely connected with the Kumaraswamy distribution $\operatorname{Kum}(p,q)$, $p\in(0,1]$, $q>1$. Using the Laplace transform technique, we prove that for $p=1$ the distribution of the innovation process is uniform discrete. For $p\in(0,1)$, the innovation process has a continuous distribution. We also consider estimation issues of the model. Keywords: Beta distribution, Kumaraswamy distribution, approximated Beta distribution, Kummer function of the first kind, first order autoregressive model Classification (MSC2000): 62M10; 33C15, 66F10, 60E10 Full text of the article: (for faster download, first choose a mirror)
Electronic fulltext finalized on: 19 Nov 2010. This page was last modified: 6 Dec 2010.
© 2010 Mathematical Institute of the Serbian Academy of Science and Arts
