Structural Expectation-Maximization
Context
- Structural Expectation-Maximization (or Structural EM for short) is very similar to Dynamic Imputation, but instead of imputing values after each structural modification of the model, the set of observations is supplemented with one weighted observation per combination of the states of the jointly unobserved variables.
- Each weight equals the posterior joint probability of the corresponding state combination.
- The distributions produced by Structural EM are also quite similar to those obtained with Dynamic Imputation.
- However, in theory, Structural EM should perform slightly better. However, the computational cost can be even higher than that of Dynamic Imputation because the computational cost of Structural EM also depends on the number of state combinations of the jointly unobserved variables.
Usage
- Select
Menu > Learning > Missing Values Processing > Structural EM.
For a thorough introduction to this topic, please see Chapter 9: Missing Values Processing in our e-book.