Archivio Istituzionale della RicercaAbstract We compare four conditional tests for Poisson data through a simulation study: the exact binomial test, its asymptotic approximation, a Markov Chain Monte Carlo test and the standard permutation test. Despite being non-parametric, we observe that permutation tests are as effective as the others. From a theoretical point of view we justify this result by observing that the orbits of permutations form a good partition of the conditional space.
Comparison of conditional tests on Poisson data / Crucinio, FRANCESCA ROMANA; Fontana, Roberto. - ELETTRONICO. - (2017), pp. 333-338. (Intervento presentato al convegno Statistics and Data Science: new challenges, new generations 28–30 June 2017 tenutosi a Firenze nel 28–30 June 2017).
Comparison of conditional tests on Poisson data
CRUCINIO, FRANCESCA ROMANA;FONTANA, ROBERTO
2017
Abstract
Abstract We compare four conditional tests for Poisson data through a simulation study: the exact binomial test, its asymptotic approximation, a Markov Chain Monte Carlo test and the standard permutation test. Despite being non-parametric, we observe that permutation tests are as effective as the others. From a theoretical point of view we justify this result by observing that the orbits of permutations form a good partition of the conditional space.
| File | Dimensione | Formato | |
|---|---|---|---|
|
estratto da 3407_11724.pdf
accesso aperto
Descrizione: Articolo
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Creative commons
Dimensione
173.43 kB
Formato
Adobe PDF
|
173.43 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2675994
Attenzione
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo