In the past I have had success modelling discrete missing outcome variables by marginalizing over the missing values with log_mix. However, I don’t know how to extend this approach to more than two categories. I had been dealing with missing binary data with the following: target += log_mix( theta[…

The log_mix function is basically just a wrapper for log_sum_exp in the two component case. There was a PR merged into develop that generalized this to the case of more than two components. See https://github.com/stan-dev/math/pull/751 but it is essentially just target += log_sum_exp(log(theta) +…

Log_mix for missing categorical data

Modeling

Erik_Ringen July 5, 2019, 1:00pm 7

Check out the solution in this thread: Imputation of a 3 category covariate to model a binary outcome

Topic		Replies	Views
Imputation of a 3 category covariate to model a binary outcome Modeling	2	1130	December 3, 2018
Missing categorical outcome data Modeling	2	359	June 30, 2020
Missing Data: Mixed Discrete-Continuous Gaussian Copula Modeling	12	881	September 12, 2022
Multivariate probit with missing outcomes Modeling rstan , specification	9	595	September 16, 2022
Missing data problem: Missing probabilities in categorical distributions General specification , meta-analysis , missing-data	2	778	December 4, 2021

Log_mix for missing categorical data

Related Topics