Page 1 of 1

Choosing 'beta_fixed' paramters for Latent Class

Posted: 01 Jul 2026, 17:51
by mweir
Hi, I'm wondering if anyone can point me toward resources that discuss selection of parameters to fix when estimating latent class. If I recall correctly, some programs automatically select parameters to fix at starting values (or zero) while Apollo allows flexibility of choice. Are their best practices for selecting these parameters?

Thanks for any help folks can provide.

Re: Choosing 'beta_fixed' paramters for Latent Class

Posted: 03 Jul 2026, 13:09
by stephanehess
Hi

the simple logic to follow is that only differences in utility matter. So in each class, you need to make sure that your model is idenitifed, so e.g. fixing one level for categorical variables and one ASC. In the class allocation models, the characteristics are shared across classes, so there, you need to fix the parameters in one class to serve as the base. The choice of which class to use as the base is arbitrary as only differences matter

Stephane