Accession Number:

ADA093150

Title:

Estimating a Distribution Function When New is Better Than Used.

Descriptive Note:

Interim technical rept.,

Corporate Author:

CALIFORNIA UNIV DAVIS INTERCOLLEGE DIV OF STATISTICS

Personal Author(s):

• Samaniego,Francisco J.
• Boyles,Russell A.

Report Date:

1980-09-01

Pagination or Media Count:

30.0

Abstract:

The problem we study in this paper is the estimation of the distribution function F under the assumption that F belongs to the class of NBU distributions. Without the NBU restriction, the empirical distribution function Fn converges to F in several senses and at the best possible rate. However, Fn need not to be NBU, and, in fact, it is not difficult to show that Pfn is NBU going to 0 when sampling from some NBU distributions for example, the exponential distribution. Our goal here is to construct a sequence Fn of NBU distributions which achieve the same asymptotic optimality as the sequence Fn.

Descriptors:

• *NONPARAMETRIC STATISTICS
• *DISTRIBUTION FUNCTIONS
• ALGORITHMS
• RANDOM VARIABLES
• TEST METHODS
• STATISTICAL SAMPLES
• ESTIMATES
• RELIABILITY
• CONVERGENCE
• EXPONENTIAL FUNCTIONS
• ITERATIONS
• ASYMPTOTIC NORMALITY
• THEOREMS
• MINIMAX TECHNIQUE

Subject Categories:

• Statistics and Probability

Distribution Statement:

APPROVED FOR PUBLIC RELEASE