Abstract
A good approximation of the Gaussian likelihood of simultaneous autoregressive (SAR) model is proposed. The approximation yields us an asymptotically efficient estimate of the parameters. No integration of the spectral density nor any other expensive calculation is necessary, so that our estimation procedure is applicable for any SAR model without restriction. Numerical experiments show that our estimate has less bias and variance than the other estimate, although our comparison is limited to the case where random number generation and the calculation of the other estimate are both feasible.
Original language | English |
---|---|
Pages (from-to) | 31-46 |
Number of pages | 16 |
Journal | Journal of Statistical Planning and Inference |
Volume | 173 |
DOIs | |
Publication status | Published - 2016 Jun 1 |
Fingerprint
Keywords
- Circulant matrix
- Maximum likelihood
- Simultaneous autoregressive model
- Spatial process
- Whittle approximation
ASJC Scopus subject areas
- Statistics, Probability and Uncertainty
- Applied Mathematics
- Statistics and Probability
Cite this
A good approximation of the Gaussian likelihood of simultaneous autoregressive model which yields us an asymptotically efficient estimate of parameters. / Rikimaru, Yuki; Shibata, Ritei.
In: Journal of Statistical Planning and Inference, Vol. 173, 01.06.2016, p. 31-46.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - A good approximation of the Gaussian likelihood of simultaneous autoregressive model which yields us an asymptotically efficient estimate of parameters
AU - Rikimaru, Yuki
AU - Shibata, Ritei
PY - 2016/6/1
Y1 - 2016/6/1
N2 - A good approximation of the Gaussian likelihood of simultaneous autoregressive (SAR) model is proposed. The approximation yields us an asymptotically efficient estimate of the parameters. No integration of the spectral density nor any other expensive calculation is necessary, so that our estimation procedure is applicable for any SAR model without restriction. Numerical experiments show that our estimate has less bias and variance than the other estimate, although our comparison is limited to the case where random number generation and the calculation of the other estimate are both feasible.
AB - A good approximation of the Gaussian likelihood of simultaneous autoregressive (SAR) model is proposed. The approximation yields us an asymptotically efficient estimate of the parameters. No integration of the spectral density nor any other expensive calculation is necessary, so that our estimation procedure is applicable for any SAR model without restriction. Numerical experiments show that our estimate has less bias and variance than the other estimate, although our comparison is limited to the case where random number generation and the calculation of the other estimate are both feasible.
KW - Circulant matrix
KW - Maximum likelihood
KW - Simultaneous autoregressive model
KW - Spatial process
KW - Whittle approximation
UR - http://www.scopus.com/inward/record.url?scp=84959099802&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84959099802&partnerID=8YFLogxK
U2 - 10.1016/j.jspi.2016.01.003
DO - 10.1016/j.jspi.2016.01.003
M3 - Article
AN - SCOPUS:84959099802
VL - 173
SP - 31
EP - 46
JO - Journal of Statistical Planning and Inference
JF - Journal of Statistical Planning and Inference
SN - 0378-3758
ER -