vuong {pscl} | R Documentation |
Compares two models fit to the same data that do not nest via Vuong's non-nested test.
vuong(m1, m2, digits = getOption("digits"))
m1 |
model 1, an object inheriting from class glm ,
negbin or zeroinfl |
m2 |
model 2, as for model 1 |
digits |
significant digits in printed result |
The Vuong non-nested test is based on a comparison of the predicted probabilities of two models that do not nest. Examples include comparisons of zero-inflated count models with their non-zero-inflated analogs (e.g., zero-inflated Poisson versus ordinary Poisson, or zero-inflated negative-binomial versus ordinary negative-binomial). A large, positive test statistic provides evidence of the superiority of model 1 over model 2, while a large, negative test statistic is evidence of the superiority of model 2 over model 1. Under the null that the models are indistinguishable, the test statistic is asymptotically distributed standard normal.
The function will fail if the models do not contain identical values
in their respective components named y
(the value of the
response being modeled).
nothing returned, prints the test-statistic and p value and exits silently.
Simon Jackman jackman@stanford.edu
Vuong, Q.H. 1989. "Likelihood ratio tests for model selection and non-nested hypotheses." Econometrica. 57:307-333.
data("bioChemists") ## compare Poisson GLM and ZIP glm1 <- glm(art ~ ., data = bioChemists, family = poisson) zip <- zeroinfl(art ~ . | ., data = bioChemists, EM = TRUE) vuong(glm1, zip) ## compare negbin with zero-inflated negbin nb1 <- glm.nb(art ~ ., data=bioChemists) zinb <- zeroinfl(art ~ . | ., data = bioChemists, dist = "negbin", EM = TRUE) vuong(nb1, zinb)