American Journal of Epidemiology Vol. 145, No. 12: 1138-1144
Copyright © 1997 by The Johns Hopkins University School of Hygiene and Public Health
other |
Validity of Methods for Model Selection, Weighting for Model Uncertainty, and Small Sample Adjustment in Capture-Recapture Estimation
1School of Public Health, University of California Berkeley, CA
2Department of Pediatrics, University of California School of Medicine San Francisco, CA
3Department of Mathematics and Statistics, University of Minnesota-Duluth Duluth, MN
Correspondence to: Professor Emest B. Hook, School of Public Health, Warren Hall (M.C. 7360), University of California, Berkeley, CA 94720-7360.
In log-linear capture-recapture approaches to population size, the method of model selection may have a major effect upon the estimate. In addition, the estimate may also be very sensitive if certain cells are null or very sparse, even with the use of multiple sources. The authors evaluated 1) various approaches to the issue of model uncertainty and 2) a small sample correction for three or more sources recently proposed by Hook and Regal. The authors compared the estimates derived using 1) three different information criteria that included Akaike's Information Criterion (AIC) and two alternative formulations of the Bayesian Information Criterion (BIC), one proposed by Draper ("two pi") and one by Schwarz ("not two pi"); 2) two related methods of weighting estimates associated with models; 3) the independent model; and 4) the saturated model, with the known totals in 20 different populations studied by five separate groups of investigators. For each method, we also compared the estimate derived with or without the proposed small sample correction. At least in these data sets, the use of AIC appeared on balance to be preferable. The BIC formulation suggested by Draper appeared slightly preferable to that suggested by Schwarz. Adjustment for model uncertainty appears to improve results slightly. The proposed small sample correction appeared to diminish relative log bias but only when sparse cells were present. Otherwise, its use tended to increase relative log bias. Use of the saturated model (with or without the small sample correction) appears to be optimal if the associated interval is not uselessly large, and if one can plausibly exclude an all-source interaction. All other approaches led to an estimate that was too low by about one standard deviation. Am J Epidemiol 1997; 145: 1138–44.
Bayes theorem; bias (epidemiology); log-linear models; sample size
CiteULike 
Connotea 
Del.icio.us What's this?
This article has been cited by other articles:
|
|
 |
|
  G. Hay, M. Gannon, J. MacDougall, C. Eastwood, K. Williams, and T. Millar Capture--recapture and anchored prevalence estimation of injecting drug users in England: national and regional estimates Statistical Methods in Medical Research, August 1, 2009; 18(4): 323 - 339. [Abstract] [PDF]
|
|
|
|
 |
|
 L. Vaissade and S. Legleye Capture-recapture estimates of the local prevalence of problem drug use in six French cities Eur J Public Health, January 1, 2009; 19(1): 32 - 37. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 S. J. Lee, K. Lindquist, M. R. Segal, and K. E. Covinsky Development and Validation of a Prognostic Index for 4-Year Mortality in Older Adults JAMA, February 15, 2006; 295(7): 801 - 808. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 M. Hickman, V. Higgins, V. Hope, M. Bellis, K. Tilling, A. Walker, and J. Henry Injecting drug use in Brighton, Liverpool, and London: best estimates of prevalence and coverage of public health indicators J Epidemiol Community Health, September 1, 2004; 58(9): 766 - 771. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 R. M Cormack, Y.-F. Chang, and G. S Smith Estimating deaths from industrial injury by capture-recapture: a cautionary tale Int. J. Epidemiol., December 1, 2000; 29(6): 1053 - 1059. [Abstract] [Full Text] [PDF]
|
|
|
|
 |
|
 E. B. Hook and R. R. Regal Accuracy of Alternative Approaches to Capture-Recapture Estimates of Disease Frequency: Internal Validity Analysis of Data from Five Sources Am. J. Epidemiol., October 15, 2000; 152(8): 771 - 779. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
A. Gallay, V. Vaillant, P. Bouvet, P. Grimont, and J.-C. Desenclos How Many Foodborne Outbreaks of Salmonella Infection Occurred in France in 1995? : Application of the Capture-Recapture Method to Three Surveillance Systems Am. J. Epidemiol., July 15, 2000; 152(2): 171 - 177. [Abstract] [Full Text] [PDF]
|
|
|
|
|
|
C. Debrock, P.-M. Preux, D. Houinato, M. Druet-Cabanac, F. Kassa, C. Adjien, G. Avode, F. Denis, F. Boutros-Toni, and M. Dumas Estimation of the prevalence of epilepsy in the Benin region of Zinvie using the capture-recapture method Int. J. Epidemiol., April 1, 2000; 29(2): 330 - 335. [Abstract] [Full Text] [PDF]
|
|