0

I am trying to applying a sandwich estimator to a Poisson regression with QMLE in R, where I used the glmrob function. The code I am using looks like:

model <- glmrob(y ~ x + x1 + x2, family = poisson, data = data, method= "Mqle", control = glmrobMqle.control(tcc= 1.2))

Ordinarily, I could apply the robust estimator using the sandwich package as: coeftest(model, vcov = sandwich)

But it is not compatible with the robustbase package. Is there another way to do this but inputting the manual values for the MLE coefficients obtained in the original model?

Thanks!

Daniel M
  • 1

1 Answers1

0

There may not be a way to do this (i.e., it hasn't been developed statistically yet). You can use a non-robust Poisson QMLE just using glm(., family = quasipoisson) and then get the robust standard errors, or just use the usual standard errors produced by vcov(). Alternatively, you can get bootstrap standard errors using vcovBS(), i.e., coeftest(fit, vcov. = sandwich::vcovBS).

Noah
  • 20,638
  • 2
  • 20
  • 58