Capture-Recapture, Epidemiology, and List Mismatches: Several Lists

Lee, Alan J.; Seber, G. A. F.; Holden, Jennifer K.; Huakau, John

doi:10.1111/j.0006-341x.2001.00707.x

Cited by 17 publications

(15 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…by Seber and Felton [25]. Their technique has recently been generalized to apply to problems in human epidemiology by Seber et al [26], Lee et al [27] and Lee [28]. While our methods are probabilistic, we assume complete and accurate information in the x vector.…”

Section: Discussionmentioning

confidence: 99%

Estimating population size and duplication rates when records cannot be linked

Laska¹,

Meisner²,

Wanderling³

et al. 2003

Statistics in Medicine

View full text Add to dashboard Cite

The capture-recapture approach to estimating the size of a population is a well-studied area of statistics. The number of distinct individuals, N(A) and N(B), on each of two lists, A and B, and the number common to both lists, N(AB), are used to form an estimate of the binomial probability of being on one of the lists, which then allows an estimate to be made of the size of the population. Critical to the method is an accurate count of N(AB). We consider situations in which this count is not available. Such problems arise in a variety of behavioural health contexts in which the need for protection of privacy may prevent sharing identifying information, so it is not possible to specifically match an individual who appears on one list with an individual on the other. Suppose that the birth dates and/or other demographics of individuals on each list are known. We introduce two methods for estimating the duplication rates and the size of the population. Conditioning on the set beta of birth dates of those on list B, N(A) and N(B), the maximum likelihood estimators (MLEs) and their variance are derived. The MLEs are based on the proportion of individuals on list A whose birth dates fall in beta. This approach is particularly useful if list B itself contains duplicates. The second model utilizes the full sample distribution of the birth dates. We generalize this approach to accommodate multiple demographic characteristics. The approaches are applied to the problem of estimating duplication rates and the population size of veterans who have mental illness in Kings County, NY. The data are lists of those receiving service from the Veterans Administration system and from providers funded or certified by the New York State Office of Mental Health.

show abstract

Section: Discussionmentioning

confidence: 99%

Estimating population size and duplication rates when records cannot be linked

Laska¹,

Meisner²,

Wanderling³

et al. 2003

Statistics in Medicine

View full text Add to dashboard Cite

show abstract

“…The ecology literature has developed some solutions to imperfect matching, which frame the problem in terms of lost tags on captured animals [Lee et al, 2001]. Similarly, the public health literature includes examples of capture-recapture estimates for cases when Cadwell et al, 2005].…”

Section: Multiple Systems Estimationmentioning

confidence: 99%

“…If we retain the data partitions, we would also like to compare the affect of increasing (or decreasing) the number of zero cells allowed in a "valid" dataset combination. We would also like to explore ways to incorporate uncertainties in our record matching into our models and the potential applicability of 'lost-tag' research in ecology [Lee et al, 2001] and insufficient identifying markers in public health [Laska et al, 2003, Cadwell et al, 2005. Lastly, we are eager to apply this new method in other departments and, eventually, across all of Colombia.…”

Section: Future Workmentioning

confidence: 99%

See 1 more Smart Citation

Measuring Elusive Populations with Bayesian Model Averaging for Multiple Systems Estimation: A Case Study on Lethal Violations in Casanare, 1998-2007

Lum¹,

Price²,

Guberek³

et al. 2010

Statistics, Politics, and Policy

View full text Add to dashboard Cite

Collecting data for the analysis of past human rights violations is fraught with challenges. For example, individuals from or about whom data should be collected may be displaced, missing, or dead. Some reports of acts may be easier to find than others, and as a result, datasets will be biased toward those cases. These challenges must be overcome in order to create effective official policy for violence mitigation and prevention. This relies on statistical analyses that can meet these challenges.We propose a combination of Bayesian Model Averaging and Multiple Systems Estimation as an example of this type of analysis, which presents an important advancement in human rights research. In particular, this method allows the use of multiple data sources to estimate the number of undocumented violations -those that have not been recorded by any source.We present an application of this method in Casanare, Colombia, where we estimate a total (both documented and undocumented) of 5,832 killings (95% credible interval: 3,822, 9,332) and 2,345 disappearances (1,221, 4,901) between 1998 and 2007.

show abstract

“…This may occur if the data consist of incomplete summary statistics or if individuals are misidentified on some occasions. Examples of capture-recapture studies that are prone to identification errors include (i) multi-list studies in which individuals may be matched based on personal information such as name, birth date, medical record number (Seber, Huakau, and Simmons, 2000;Lee et al, 2001;Sutherland and Schwarz, 2005;Fienberg and Manrique-Vallier, 2009), (ii) animal studies in which individual identity is found from noninvasive sampling, for example, genetic information from scat or hair (Wright et al, 2009;Link et al, 2010;Yoshizaki et al, 2011) or photographic ID of individuals (Yoshizaki et al, 2009;Bonner and Holmberg, 2013;McClintock et al, 2013), and (iii) studies in which (at least) two sources of capturerecapture information are available for the same population with little to no information about how the individual IDs in one source corresponds to individual ID from the other sources (Bonner and Holmberg, 2013;McClintock et al, 2013).…”

Section: Introductionmentioning

confidence: 99%