Title :
On the existence of strongly consistent rules for estimation and classification
Author :
Kulkarni, S.R. ; Zeitouni, O.
Author_Institution :
Dept. of Electr. Eng., Princeton Univ., NJ, USA
Abstract :
Suppose we observe x1,x2,…ε𝒳 drawn i.i.d. according to some unknown distribution P selected from a family of distributions 𝒫. Let f:𝒫→Λ be a parameterisation of P∈𝒫. In this paper, we study necessary and sufficient conditions for the existence of strongly consistent estimators of f(P). A number of previous results along these lines are special cases of our main result
Keywords :
estimation theory; pattern classification; statistical analysis; classification; distributions; estimation; iid; independent identically distributed case; parameterisation; strongly consistent estimators; strongly consistent rules; unknown distribution; Artificial intelligence; Extraterrestrial measurements; Sufficient conditions; Testing;
Conference_Titel :
Information Theory, 1995. Proceedings., 1995 IEEE International Symposium on
Conference_Location :
Whistler, BC
Print_ISBN :
0-7803-2453-6
DOI :
10.1109/ISIT.1995.535770
