The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Abstract Details
|
Activity Number:
|
557
|
|
Type:
|
Invited
|
|
Date/Time:
|
Wednesday, August 3, 2011 : 2:00 PM to 3:50 PM
|
|
Sponsor:
|
ASA
|
| Abstract - #303438 |
|
Title:
|
Misclassication Probabilities For N-Fold Random Samples
|
|
Author(s):
|
Michael Klass and Usha S. Govindarajulu*+
|
|
Companies:
|
Brigham and Women's Hospital and University of California at Berkeley
|
|
Address:
|
254 Main St., Watertown, 02472,
|
|
Keywords:
|
|
|
Abstract:
|
Suppose it is of interest to classify a new distribution on the basis of a random sample of size n as being either P0 or P1, the support of which is a nite set f1; 2; : : : ;Lg. Nothing is known about the distributions P0 and P1 except that we have training samples of size n0 and n1 from P0 and P1, respectively. Assuming that n0 an and n1 bn for some a; b > 0 it is shown that the probability of misclassi cation goes to zero exponentially as n becomes large. Our method of classi cation employs the data from all three samples to construct two distinct pairs of maximum likelihood distributions for P0 and P1, the rst assuming the sample to be classi ed has distribution P0, the second assuming it has distribution P1, deciding how to classify the sample in question by means of a likelihood ratio statistic.
|
The address information is for the authors that have a + after their name.
Authors who are presenting talks have a * after their name.
Back to the full JSM 2011 program
|
2011 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.