Title :
Some notes on Rissanen´s stochastic complexity
Author :
Qian, Guoqi ; Künsch, Hans R.
Author_Institution :
Sch. of Stat., La Trobe Univ., Bundoora, Vic., Australia
fDate :
3/1/1998 12:00:00 AM
Abstract :
A new version of stochastic complexity for a parametric statistical model is derived, based on a class of two-part codes. We show that choosing the quantization in the first step according to the Fisher information is optimal and we compare our approach to a recent result of Rissanen (1983). An application to robust regression model selection is presented
Keywords :
approximation theory; codes; computational complexity; nonparametric statistics; quantisation (signal); stochastic processes; Fisher information; Rissanen´s stochastic complexity; approximation; parametric statistical model; quantization; robust regression model selection; two-part codes; Australia; Books; H infinity control; Probability; Quantization; Robustness; Seminars; Statistics; Stochastic processes;
Journal_Title :
Information Theory, IEEE Transactions on
