Suppose a Bayesian factor analysis is contemplated but some of the observable variables in the data vectors are jointly continuous, and others are jointly discrete. What ways might you explore to carry out the analysis?

Suppose that examination in each dimension, separately, of the data vectors shows that in each dimension beyond the first, the data are indeed approximately normally distributed, but that in the first dimension, the data tend to follow some other continuous distribution. What might you do in order to have the assumptions of the Bayesian factor analysis model apply, at least approximately?