© 2003 by Biometrika Trust
Miscellanea |
A counterexample to a claim about stochastic simulations
1 Department of Mathematical Sciences, Norwegian University of Science and Technology, N-7491 Trondheim, Norway bo{at}math.ntnu.no 2 SINTEF Telecom and Informatics, N-7465 Trondheim, Norway gunnar.taraldsen{at}sintef.no 3 Department of Mathematical Sciences, Norwegian University of Science and Technology, N-7491 Trondheim, Norway magnar.lillegard{at}math.ntnu.no steinar.engen{at}math.ntnu.no
Engen & Lillegård (1997) presented a general method for doing Monte Carlo simulations conditioned on a sufficient statistic.The basic idea was to adjust the parameter values in the corresponding unconditional simulation so that the actual value of the sufficient statistic is obtained, and the claim was that if this adjustment is unique then the modified simulation is from the conditional distribution. Unfortunately the claim is not correct, as shown by a counterexample.
Key Words: Conditional distribution; Stochastic simulation; Sufficient statistic
Received April 2002. Revised October 2002
![]()
CiteULike
Connotea
Del.icio.us What's this?
This article has been cited by other articles:
![]() |
R. A. Lockhart, F. J. O'Reilly, and M. A. Stephens Use of the Gibbs Sampler to Obtain Conditional Tests, with Applications Biometrika, December 1, 2007; 94(4): 992 - 998. [Abstract] [PDF] |
||||
