On Resampling for the Contingency Table based on Information Energy
(English)Manuscript (preprint) (Other academic)
The bootstrap method is studied herein for the analysis of categorical data,in particular for the contingency table. The way to carry out atest of association is to bootstrap on the basis of expected values that havealready been ascertained by a few authors. This paper shows the theoreticalapproach of bootstrapping for a contingency table, and the idea which it isbased on has been inspired by the use of the informational energy function.The properties of the proposed tests are illustrated and discussed using MonteCarlo simulations. The paper ends with analytical examples that elucidate the use ofthe proposed tests.
Bootstrap method; Chi-squared test; Contingency table; Informational energy; Monte Carlo investigation
Probability Theory and Statistics
Research subject Statistics
IdentifiersURN: urn:nbn:se:uu:diva-158980OAI: oai:DiVA.org:uu-158980DiVA: diva2:441929