Accession Number:

ADA160016

Title:

The Strong Consistency of Error Probability Estimates in NN Discrimination.

Descriptive Note:

Technical rept.,

Corporate Author:

PITTSBURGH UNIV PA CENTER FOR MULTIVARIATE ANALYSIS

Personal Author(s):

Report Date:

1984-10-01

Pagination or Media Count:

21.0

Abstract:

Since 1971, T.J. Wagner introduced an error probability estimate in NN Nearest Neighbor discrimination rule and proved the weak convergency of this estimate. The problem of strong consistency is not yet solved. This paper shows the exponential convergence rate of this estimate. Hence, the strong consistency of this estimate holds automatically. Author

Subject Categories:

  • Statistics and Probability

Distribution Statement:

APPROVED FOR PUBLIC RELEASE