The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Online Program Home
Abstract Details
Activity Number:
|
652
|
Type:
|
Contributed
|
Date/Time:
|
Thursday, August 2, 2012 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Section on Nonparametric Statistics
|
Abstract - #306772 |
Title:
|
Power of the Scan Statistics via FMCI
|
Author(s):
|
Wanchen Lee*+
|
Companies:
|
University of Manitoba
|
Address:
|
338 Machray Hall, Winnipeg, MB, R3T 2N2, Canada
|
Keywords:
|
FMCI ;
SCAN STATISTIC ;
POWER ;
HYPOTHESIS TEST
|
Abstract:
|
Wallenstein et al. (1993, 1994} discussed power, via combinatorial calculation, for scan statistic against a pulse alternative; however, it exists computational difficulties unless under certain proper conditions. Our work provides an alternative way to obtain the distribution of scan statistic under alternative hypothesis. In order to have a general expression we consider a sequence of $k$ blocks independent trials and the usual assumption of a sequence of $n$ independent bistate trials becomes a special case of our setting. An efficient and intuitive expression for the distribution of scan statistic is introduced via finite Markov chain imbedding (FMCI) technique. The numerical results of the exact power for a discrete scan statistic against (1) $k$-blocks independent trials which has $m_t$ events in $t^{th}$ block with chance of success $\pi(t)$ and $\sum_{t=1}^k m_t = n$ and (2) a sequence of $n$ Markov dependent trails are presented. Power, through FMCI, for a continuous scan statistic against a pulse alternative of assuming a higher relative risk of disease on a specified subinterval time is also discussed and compared with combinatorial calculation results.
|
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 2012 program
|
2012 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.