Separate the covariates from a 'formula' with a cluster effect from the ones with an identical effect in each cluster if provided.
A symbolic description of the model. In
the parametric case we write for example
Given a 'formula' of the form
Y ~ clust(T1 + T2 +
...) + pop(X1 + X2 + ...) or just
Y ~ clust(T1 +
T2 + ...), it returns a list of two or one 'formula' of
Y ~ T1 + T2 + ... and
~ X1 + X2 +
... if provided.
The first element of the list correspond to the covariates with a different effects corresponding to the cluster, the 2nd correspond to covariates having an identical effect in each cluster.
In the non-parametric case only one covariate is allowed.
A list of 1 or 2 [formula].
Meant to be used internally.