While I was a Pew Fellow in Health Policy at the Institute for Health Policy Studies at the University of California-San Francisco, I worked on modeling hospital choice.
An econometric model indicated that California patients were more likely to go to hospitals with better than expected outcomes for the procedure they were having performed.
Phibbs, Ciaran S., David H. Mark, Harold S. Luft, Deborah J. Peltzman-Rennie, Deborah W. Garnick, Erik Lichtenberg and Stephen J. McPhee, "Choice of Hospital for Delivery: A Comparison of High-Risk and Low-Risk Women", HSR: Health Services Research 28. 201-222 (June 1993).
Luft, Harold S., Deborah W. Garnick, Ciaran S. Phibbs, Deborah J. Peltzman, Erik Lichtenberg and Stephen J. McPhee, "A Model to Simulate the Effects of Hospital Quality and Charges on Choice of Hospital", Journal of Health Care Marketing 11, 2-11 (September 1991).
Luft, Harold S., Deborah W. Garnick, David H. Mark, Deborah J. Peltzman, Ciaran S. Phibbs, Erik Lichtenberg and Stephen J. McPhee, "Does Quality Influence Choice of Hospital?", Journal of the American Medical Association 263, 2899-2906 (June 6, 1990).
The data used to estimate gravity models of hospital choice typically contain many zeroes (because patients from some locations do not attend a given hospital in some years). Maximum likelihood estimation of discrete choice models gives more robust estimates of the model parameters than linearized models that require ad hoc adjustments to these zero observations.
Garnick, Deborah W., Erik Lichtenberg, Ciaran S. Phibbs, Harold S. Luft, Deborah J. Peltzman and Stephen J. McPhee, "The Sensitivity of Conditional Choice Models for Hospital Care to Estimation Technique", Journal of Health Economics 8, 377-397 (1989).