If you need an accessible version of this item please contact JSTOR User Support

Identification and Preliminary Estimation in Linear Transfer Function Models

Markku Rahiala
Scandinavian Journal of Statistics
Vol. 13, No. 4 (1986), pp. 239-255
Stable URL: http://www.jstor.org/stable/4616033
Page Count: 17
  • Download PDF
  • Cite this Item

You are not currently logged in.

Access your personal account or get JSTOR access through your library or other institution:

login

Log in to your personal account or through your institution.

If you need an accessible version of this item please contact JSTOR User Support
Identification and Preliminary Estimation in Linear Transfer Function Models
Preview not available

Abstract

A new method based on spectral estimation is proposed for the identification and estimation of univariate ARMA-models. The method maximizes the entropy of the estimated innovation spectrum. On the other hand, it is possible to estimate the spectral density of the disturbance of a linear transfer function model without making any assumptions about the transfer function forms. This enables one to start the identification of a transfer function model by first estimating an ARMA-model for the disturbance. At the next stage, one can derive asymptotically efficient estimates for all the linear parameters in the model. On the basis of these efficient estimates, the specification of suitable transfer function forms is relatively straightforward.

Page Thumbnails

  • Thumbnail: Page 
[239]
    [239]
  • Thumbnail: Page 
240
    240
  • Thumbnail: Page 
241
    241
  • Thumbnail: Page 
242
    242
  • Thumbnail: Page 
243
    243
  • Thumbnail: Page 
244
    244
  • Thumbnail: Page 
245
    245
  • Thumbnail: Page 
246
    246
  • Thumbnail: Page 
247
    247
  • Thumbnail: Page 
248
    248
  • Thumbnail: Page 
249
    249
  • Thumbnail: Page 
250
    250
  • Thumbnail: Page 
251
    251
  • Thumbnail: Page 
252
    252
  • Thumbnail: Page 
253
    253
  • Thumbnail: Page 
254
    254
  • Thumbnail: Page 
255
    255