Fitting time series models to nonstationary processes
Dahlhaus, R.
Ann. Statist., Tome 25 (1997) no. 6, p. 1-37 / Harvested from Project Euclid
A general minimum distance estimation procedure is presented for nonstationary time series models that have an evolutionary spectral representation. The asymptotic properties of the estimate are derived under the assumption of possible model misspecification. For autoregressive processes with time varying coefficients, the estimate is compared to the least squares estimate. Furthermore, the behavior of estimates is explained when a stationary model is fitted to a nonstationary process.
Publié le : 1997-02-14
Classification:  Nonstationary processes,  time series,  evolutionary spectra,  minimum distance estimates,  model selection,  62M15,  62F10
@article{1034276620,
     author = {Dahlhaus, R.},
     title = {Fitting time series models to nonstationary processes},
     journal = {Ann. Statist.},
     volume = {25},
     number = {6},
     year = {1997},
     pages = { 1-37},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1034276620}
}
Dahlhaus, R. Fitting time series models to nonstationary processes. Ann. Statist., Tome 25 (1997) no. 6, pp.  1-37. http://gdmltest.u-ga.fr/item/1034276620/