TY - JOUR
T1 - Robust recursive estimation for correlated observations
AU - Guttman, Irwin
AU - Lin, Dennis K.J.
N1 - Funding Information:
We thank one referee for helpful comments on an earlier version of this article. Irwin Guttman was partially supported by Grant A8743 from NSERC (Canada), and Dennis K.J. Lin was partially supported by the Professional Development Award, the University of Tennessee and by the National Science Foundation under Grant DMS-9204007.
PY - 1995/4
Y1 - 1995/4
N2 - The Kalman filter is probably the most popular recursive estimation method. It is, however, known to be non-robust to spuriously generated observations. Much attention has been focused on finding the so-called robust recursive estimation under the assumption that the observations are independent. In this paper, we show that Lin and Guttman's robust recursive estimation scheme can be easily applied to the correlated observations. Examples when the noise follows an AR(2) process with/without outliers are given for illustration.
AB - The Kalman filter is probably the most popular recursive estimation method. It is, however, known to be non-robust to spuriously generated observations. Much attention has been focused on finding the so-called robust recursive estimation under the assumption that the observations are independent. In this paper, we show that Lin and Guttman's robust recursive estimation scheme can be easily applied to the correlated observations. Examples when the noise follows an AR(2) process with/without outliers are given for illustration.
UR - http://www.scopus.com/inward/record.url?scp=0005471033&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0005471033&partnerID=8YFLogxK
U2 - 10.1016/0167-7152(94)00098-S
DO - 10.1016/0167-7152(94)00098-S
M3 - Article
AN - SCOPUS:0005471033
VL - 23
SP - 79
EP - 92
JO - Statistics and Probability Letters
JF - Statistics and Probability Letters
SN - 0167-7152
IS - 1
ER -