Error in zero inflated Poisson regression in R

Question

zip<-zeroinfl(No.of.fatal~.|., data=LI, link="logit", dist="poisson")
Error in solve.default(as.matrix(fit$hessian)) : 
Lapack routine dgesv: system is exactly singular: U[72,72] = 0
In addition: Warning message:
glm.fit: fitted probabilities numerically 0 or 1 occurred 

• I do not understand this error, am I missing something in the data?
• Is it possible to know what error was committed in this program?
• How can I fix this error?
• What is meant by "system is exactly singular"?

Answer 1

You should specify which package you're doing this in.

Is it pscl ? ...

There's not enough information given to hazard a definitive answer, but my guess is that either the predictors are multicollinear, or just maybe that you don't have enough zeros for all the parameters you're fitting to predict their probability.