dc.contributor.advisor | Lindqvist, Bo Henry | |
dc.contributor.author | Fagerland, Marius | |
dc.date.accessioned | 2016-06-23T14:00:47Z | |
dc.date.available | 2016-06-23T14:00:47Z | |
dc.date.created | 2016-06-10 | |
dc.date.issued | 2016 | |
dc.identifier | ntnudaim:15288 | |
dc.identifier.uri | http://hdl.handle.net/11250/2393953 | |
dc.description.abstract | This thesis is an analysis of conditional sampling from a gamma distribution
given sufficient statistics. Several sampling algorithms are considered. An
algorithm similar to direct sampling is discussed in particular. This algorithm
uses parameter adjustments to meet conditions of sufficient statistics. However,
this algorithm is influenced by a pivotal condition. How this condition affects
algorithm 1 is presented. A Gibbs sampler is assumed to give correct samples,
and will be used in comparison to the other samplers. Several data sets are
used, and all of them follow the case of 3 data points. | |
dc.language | eng | |
dc.publisher | NTNU | |
dc.subject | Fysikk og matematikk, Industriell matematikk | |
dc.title | Conditional Sampling from a Gamma Distribution given Sufficient Statistics | |
dc.type | Master thesis | |
dc.source.pagenumber | 62 | |