The relevance of any possibly significant covariate when using a generalized linear model should be further investigated by means of an appropriate statistical test. The most known parametric approach might fail when some assumptions are missing, losing the control of type I error. Permutation tests can often be useful in these situations, requiring fewer assumptions, and we will apply them in this general framework.
Conditional tests for generalized linear models
Anna Vesely;Livio Finos
2022
Abstract
The relevance of any possibly significant covariate when using a generalized linear model should be further investigated by means of an appropriate statistical test. The most known parametric approach might fail when some assumptions are missing, losing the control of type I error. Permutation tests can often be useful in these situations, requiring fewer assumptions, and we will apply them in this general framework.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
