The authors examine issues in applying multiple-capture methods to drug use prevalence estimation. Three published applications are first summarized to illustrate selected approaches. Important application issues are then discussed, including population definition, sampling, data characteristics, model choice, and population dynamics. Finally, three estimation approaches are compared, using simulated data.
Get full access to this article
View all access options for this article.
References
1.
BonettD. G.1983A linear model for estimating the size of a closed population. Unpublished Ph.D. diss. Univ. of California Los Angeles.
2.
BonettD.G.WoodwardJ.A.BentlerP.M.1986Some extensions of a linear model for categorical data. Biometrics41: 745–750.
3.
BrechtM.L.WickensT.D.1991A comparison of multiple-recapture models for drug prevalence estimation. American Statistical Assocaition 1991 Proceedings of the social Statistics Section, 556–561.
4.
CowanC. D.BreakeyW. R.FischerP. J.1986The methodology of counting the homeless. In Proceedings of the Survey Research Methods Section, American Statistical Association, 170–175.
5.
DoscherM. L.WoodwardJ. A.1983Estimating the size of subpopulations of heroin users: Applications of log-linear models to capture/recapture sampling. International Journal of the Addictions18: 167–182.
6.
EdlefsenL. E.JonesS. D.1986GAUSS programming language manual. Kent, Wash.: Aptech Systems.
7.
FrankB.SchmeidlerJ.JohnsonB.LiptonD. S.1978Seeking truth in heroin indicators: The case of New York City. Drug and Alcohol Dependence3:345–358.
8.
GilbertR. O.1973Approximations of the bias in the Jolly-Seber capture-recapture model. Biometrics29:501–526.
9.
GreenwoodJ. A.1971Estimating number of narcotic addicts. Washington, D. C.: U. S. Government Printing Office. (Drug Control Division, Office of Scientific Support, Bureau of Narcotics and Dangerous Drugs, U. S. Department of Justice.)
10.
HartnollR.LewisR.MitchesonM.BryerS.1985Estimating the prevalence of opioid dependence. The Lancet26 (Jan): 203–205.
11.
HinesJ. E.1988Program “JOLLY.”Laurell, Md.: U. S. Fish and Wildlife Service.
12.
JollyG. M.1965Explicit estimates from capture-recapture data with both death and immigration—stochastic model. Biometrika52:225–257.
13.
NewmeyerJ.1988The prevalence of drug use in San Francisco in 1987. Journal of Psychoactive Drugs20(2): 185–189.
14.
SeberG. A. F.1962The multi-sample single recapture census. Biometrika49: 339–349.
15.
SeberG. A. F.1965A note on the multiple-recapture census. Biometrika52: 249–259.
16.
SeberG. A. F.1982The estimation of animal abundance and related parameters. 2nd ed.London: Griffin.
17.
SudmanS.SirkenM. G.CowanC. D.1988Sampling rare and elusive populations. Science240: 991–995.
18.
WickensT. D.1989Multiway contingency tables analysis for the social sciences. Hillsdale, N.J.: Erlbaum.
19.
WittesJ. T.1974Applications of a multinomial capture-recapture model to epidemiological data. Journal of the American Statistical Association69: 93–97.
20.
WoodwardJ. A.BonettD. G.BrechtM.L.1985Estimating the size of a heroin-abusing population using multiple-recapture census. In Self-report methods of estimating drug use: Meeting current challenges to validity, ed. RouseB.KozelN.Richards. NIDA Research Monograph no. 57. DHHS Publication NO. (ADM)85–1402, 158–171. Washington, D.C.
21.
WoodwardJ.A.RitkaB.L.NgL.1984Construct validity of heroin abuse estimators. International Journal of the Addictions19:93–117.
