Abstract
In this paper, multisample structural equation models with stochastic constrains are investigated using a Bayesian approach. Both identified and non-identified models are considered. Asymptotic properties of the Bayesian estimates are developed and a scoring type algorithm is implemented to obtain the solution. A simulation study is conducted to examine the empirical behaviors of the Bayesian estimates. The conclusion is that it is advantageous to incorporate stochastic constraints in the analysis of the model.
| Original language | English |
|---|---|
| Pages (from-to) | 441-453 |
| Number of pages | 13 |
| Journal | Computational Statistics and Data Analysis |
| Volume | 16 |
| Issue number | 4 |
| DOIs | |
| Publication status | Published - Oct 1993 |
Keywords
- Asymptotic properties
- Bayesian estimates
- Scoring algorithm
- Simulation study