Robust Lag Weighted Lasso for Time Series Model
2021 ◽
Vol 19
(1)
◽
pp. 2-15
Keyword(s):
The Real
◽
The lag-weighted lasso was introduced to deal with lag effects when identifying the true model in time series. This method depends on weights to reflect both the coefficient size and the lag effects. However, the lag weighted lasso is not robust. To overcome this problem, we propose robust lag weighted lasso methods. Both the simulation study and the real data example show that the proposed methods outperform the other existing methods.
Keyword(s):
Keyword(s):
2015 ◽
Vol 26
(12)
◽
pp. 1550137
◽
Keyword(s):
1992 ◽
Vol 21
(2)
◽
pp. 519-531
◽
2013 ◽
Vol 2013
◽
pp. 1-11
◽
Keyword(s):