Abstract
An iterative procedure for estimating HIV incidence from AIDS incidence data is discussed. The approach, proposed by Becker et al. (1991), makes use of the EM algorithm combined with a smoothing step. In this paper we suggest a modification of the method, based on an alternative choice for the complete data model used to invoke the EM algorithm. It is found that this modification improves the stability and flexibility of the estimates, although it generally leads to slower convergence.
Original language | English |
---|---|
Pages (from-to) | 1-20 |
Number of pages | 20 |
Journal | Journal of Statistical Computation and Simulation |
Volume | 50 |
Issue number | 1-2 |
DOIs | |
Publication status | Published - 1 Aug 1994 |
Externally published | Yes |
Keywords
- Back-projection
- EM-algorithm
- HIV/AIDS incidence
- smoothing