Regression Analysis under Probabilistic Multi-Linkage
Article first published online: 18 NOV 2011
© 2011 The Authors. Statistica Neerlandica © 2011 VVS
Volume 66, Issue 1, pages 64–79, February 2012
How to Cite
Kim, G. and Chambers, R. (2012), Regression Analysis under Probabilistic Multi-Linkage. Statistica Neerlandica, 66: 64–79. doi: 10.1111/j.1467-9574.2011.00509.x
- Issue published online: 12 JAN 2012
- Article first published online: 18 NOV 2011
- Received: 29 August 2011. Revised: 25 September 2011.
- probabilistic record linkage;
- linkage errors;
- linear regression;
- estimating equations
Linkage errors can occur when probability-based methods are used to link records from two distinct data sets corresponding to the same target population. Current approaches to modifying standard methods of regression analysis to allow for these errors only deal with the case of two linked data sets and assume that the linkage process is complete, that is, all records on the two data sets are linked. This study extends these ideas to accommodate the situation when more than two data sets are probabilistically linked and the linkage is incomplete.