Comparisons of methods for generating conditional Poisson samples and Sampford samples
Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesis
Methods for conditional Poisson sampling (CP-sampling) and Sampford sampling are compared and the focus is on the efficiency of the methods. The efficiency is investigated by simulation in different sampling situations. It was of interest to compare methods since new methods for both CP-sampling and Sampford sampling were introduced by Bondesson, Traat & Lundqvist in 2004. The new methods are acceptance rejection methods that use the efficient Pareto sampling method. They are found to be very efficient and useful in all situations. The list sequential methods for both CP-sampling and Sampford sampling are other methods that are found to be efficient, especially if many samples are to be generated.
Place, publisher, year, edition, pages
2005. , 35 p.
acceptance rate, acceptance-rejection, conditional Poisson sam- pling, list sequential sampling, Pareto sampling, Sampford sampling, simulation
Probability Theory and Statistics
IdentifiersURN: urn:nbn:se:umu:diva-51321OAI: oai:DiVA.org:umu-51321DiVA: diva2:479020
UppsokPhysics, Chemistry, Mathematics