R-estimation in Autoregression with Square-Integrable Score Function
نویسندگان
چکیده
منابع مشابه
On the Properties of the Integer Translates of a Square Integrable Function in L(R)
(1.1) 〈ψ〉 = span{ψ(· − k) ≡ ψk : k ∈ Z} That is, 〈ψ〉 is the L2(R) closure of the space generated by the finite linear combinations of the integer translates, (Tkψ)(x) ≡ ψ(x − k) ≡ ψk(x), of ψ ∈ L2(R). Such a space is often called the principal shift invariant space generated by ψ. In general, a closed subspace V ⊂ L2(R) is shift invariant if and only if TkV ⊂ V for all translates Tk, k ∈ Z. The...
متن کاملImproved Subset Autoregression: With R Package
The FitAR R (R Development Core Team 2008) package that is available on the Comprehensive R Archive Network is described. This package provides a comprehensive approach to fitting autoregressive and subset autoregressive time series. For long time series with complicated autocorrelation behavior, such as the monthly sunspot numbers, subset autoregression may prove more feasible and/or parsimoni...
متن کاملTwo-wavelet constants for square integrable representations of G/H
In this paper we introduce two-wavelet constants for square integrable representations of homogeneous spaces. We establish the orthogonality relations fo...
متن کاملComment on " Quantile Autoregression " by R . Koenker
My remarks about this paper are organised within four points. The rst of these notes the close connection between the authors random coe¢ cient model and some earlier models that were not formulated in terms of "random coe¢ cients". The second comments on the models identi cation. The third point queries the transition from the authorsbasic model (1) to their quantile version (2). Finally w...
متن کاملMulti-Task Learning in Square Integrable Space
Several kernel based methods for multi-task learning have been proposed, which leverage relations among tasks as regularization to enhance the overall learning accuracies. These methods assume that the tasks share the same kernel, which could limit their applications because in practice different tasks may need different kernels. The main challenge of introducing multiple kernels into multiple ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Multivariate Analysis
سال: 2002
ISSN: 0047-259X
DOI: 10.1006/jmva.2001.1998