The objective of this proposal is to propose new parametric goodness fit of teststatistics that are applicable for general distributions for checking the appositeness ofthe underlying model assumption in the setting of generalized linear models. We planto accomplish our intended mission by taking advantage of the fact that the meanregression parameters can be consistently estimated by using normal, gamma andPoisson working models even when model fails. We will compare our novelapproaches with several commonly used and implemented existing methods, includingthose based on empirical distribution functions, with simulations and real dataanalyses.
|Effective start/end date||1/08/15 → 31/07/16|
- Goodness of fit
- Model misspecification
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.