Standardisation of models

[lrnv]

Following the discutions that started at #44, i'd like to continue my investigation on norms for models.

For Univariates (and non-bootstrap) models, do we agree that :

• A model takes a single triangle as a data input, or something that can be coerced to a triangle
• A model can take aditional parameters such as :
• A model object should contains at least :
  • Some standard results : last diagonal, ultimates, reserves, standard error of reserves, etc...
  • One matrix : the completed triangle
  • Estimated parameters if any.
  • Quality assessing values (p-values for glm,...)
• The object returned by the model should ansewr correctly some generic functions :
  • Ultimates()
  • CDR()
  • Others ?

Do i miss something that's important to one model or another ?

My goal is to be able to fit models from the same function, in the caret-way, something like :

data(ABC)
mod1 <- fitTriangle(ABC,method="Mack",...)
mod2 <- fitTriangle(ABC,method="Merz",...)
mod3 <- fitTriangle(ABC,method="glm",family=quasipoisson(link="log"),...)
mod4 <- fitTriangle(ABC,method="glm.nb",...)
mod.list = list(mod1,mod2,mod3,mod4)

and then to get extraction in a standardized way :

purrr::map(mod.list,CDR)
purrr::map(mod.list,"ultimates")
purrr::map(mod.list,"ultimate.s.e")
purrr::map(mod.list,"total.s.e")

etc.

Thoughts ?