 |
|
 |
 |
|
Monday, January 27, 2003 in REC 307 4:30 PM Mr. Xuefeng Li University of Pennsylvania will speak on Gamma Autoregressive and Moving Average Models Abstract Time series models with infinitely divisible marginal distributions are studied. Motivated from a project of analyzing call center data, we propose several different constructions of autoregressive and moving average models with Gamma margins. The first one has a form similar to the classical time series ARMA model but with random coefficients. The second one is based on the integration of random fields with Gamma innovations. Both of these yield positively correlated Gamma sequences. The third one comes from the Beta-Gamma transform and yields negatively correlated Gamma sequences. Maximum likelihood, conditional least squares and moment estimates are investigated. Their asymptotic properties are studied. Finally we generalize the first two constructions to the family of infinitely divisible distributions. Open questions and future research directions are discussed. This is a joint work with Dr. Lawrence Brown.
|
|
Seminars and Events | Research | Consulting | Career Resources Related Programs and Links | Site Index | Site Search |
©1999 Department of Statistics Last Update: Jan 10, 2003 Please send comments and suggestions to the Webmaster. |