Non-nested random effect models

[tqtbui]

Hi James,

This is a question, rather than an issue with the package. I was running a random effects model with a fixed effect for, say covariate X1, and a random effect for covariate X2. I'm wanting to get a clustered variance for clustering on X1. However, I encounter this error message:

"Non-nested random effects detected. clubSandwich methods are not available for such models."

My questions are:

• Is there any reason that clustered variances work for nested random effects? Are the clustered variance formulas the same for nested random effect model as for the fixed effect model? Is there any reference paper that I can read about it? I have only been able to discover your paper on fixed effects model.
• What makes it impossible to apply clubSandwich methods for models with non-nested random effects?

Thank you and I'm looking forward to hearing from you.