Abstract
An autoregressive process is proposed to model time series data with multiple observations at each time point. The joint autocorrelation function for the model has a product form, the first factor being the autocorrelation function for a stationary AR(p) process and the second factor involving a constant intraclass correlation ρ. The least-squares and the Gaussian maximum likelihood estimators of the autoregression parameters θ=(θ1,...,θp)T and the intraclass correlation ρ are presented and their limit distributions are derived.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 137-154 |
| Number of pages | 18 |
| Journal | Journal of Statistical Planning and Inference |
| Volume | 39 |
| Issue number | 2 |
| DOIs | |
| State | Published - Apr 15 1994 |
| Externally published | Yes |
Fingerprint
Keywords
- Intraclass correlation
- Panel time series
- asymptotic distributions
- least-squares estimation
- maximum likelihood estimation
ASJC Scopus subject areas
- Statistics and Probability
- Statistics, Probability and Uncertainty
- Applied Mathematics
Cite this
Parameter estimation in a stationary autoregressive process with correlated multiple observations. / Sethuraman, S.; Basawa, I. V.
In: Journal of Statistical Planning and Inference, Vol. 39, No. 2, 15.04.1994, p. 137-154.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Parameter estimation in a stationary autoregressive process with correlated multiple observations
AU - Sethuraman, S.
AU - Basawa, I. V.
PY - 1994/4/15
Y1 - 1994/4/15
N2 - An autoregressive process is proposed to model time series data with multiple observations at each time point. The joint autocorrelation function for the model has a product form, the first factor being the autocorrelation function for a stationary AR(p) process and the second factor involving a constant intraclass correlation ρ. The least-squares and the Gaussian maximum likelihood estimators of the autoregression parameters θ=(θ1,...,θp)T and the intraclass correlation ρ are presented and their limit distributions are derived.
AB - An autoregressive process is proposed to model time series data with multiple observations at each time point. The joint autocorrelation function for the model has a product form, the first factor being the autocorrelation function for a stationary AR(p) process and the second factor involving a constant intraclass correlation ρ. The least-squares and the Gaussian maximum likelihood estimators of the autoregression parameters θ=(θ1,...,θp)T and the intraclass correlation ρ are presented and their limit distributions are derived.
KW - Intraclass correlation
KW - Panel time series
KW - asymptotic distributions
KW - least-squares estimation
KW - maximum likelihood estimation
UR - http://www.scopus.com/inward/record.url?scp=38149147857&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=38149147857&partnerID=8YFLogxK
U2 - 10.1016/0378-3758(94)90203-8
DO - 10.1016/0378-3758(94)90203-8
M3 - Article
AN - SCOPUS:38149147857
VL - 39
SP - 137
EP - 154
JO - Journal of Statistical Planning and Inference
JF - Journal of Statistical Planning and Inference
SN - 0378-3758
IS - 2
ER -