The DN A Database Search Controversy

Balding, David J.

doi:10.1111/j.0006-341x.2002.00241.x

Cited by 30 publications

(25 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…the probability that the match is correct should be treated as small. This paper's position, following for example Balding (2002), is to suggest that such an argument would be misleading. It is true that the probability of finding a match does increase the longer the search and thus that the journalist's discovery may be unremarkable overall.…”

Section: Identification Risk For Linkage By Matchingmentioning

confidence: 97%

“…This contrasts with an alternative argument, which has been advanced for example by Stockmarr (1999), that the risk may be severely reduced by such a database search. See Dawid (2001) and Balding (2002) for some of the ensuing debate. To illustrate this debate in an SDC context, suppose that a journalist claims to have found a unique match between a named individual and a record in a public use microdata file released by a statistical agency.…”

Section: Identification Risk For Linkage By Matchingmentioning

confidence: 99%

See 1 more Smart Citation

The Probability of Identification: Applying Ideas from Forensic Statistics to Disclosure Risk Assessment

Skinner

2006

Journal of the Royal Statistical Society Series A: Statistics in Society

View full text Add to dashboard Cite

Summary. This paper establishes a correspondence between statistical disclosure control and forensic statistics regarding their common use of the concept of 'probability of identification'. The paper then seeks to investigate what lessons for disclosure control can be learnt from the forensic identification literature. The main lesson considered here is that disclosure risk assessment cannot, in general, ignore the search method employed by an intruder seeking to achieve disclosure. The effects of using several search methods are considered. Through consideration of the plausibility of assumptions and 'worst case' approaches, the papers suggests how the impact of search method can be handled. The paper focuses on foundations of disclosure risk assessment, providing some justification for some modelling assumptions underlying some existing record level measures of disclosure risk. The paper illustrates the effects of using different search methods in a numerical example based upon microdata from a sample from the 2001 Census.

show abstract

Section: Identification Risk For Linkage By Matchingmentioning

confidence: 97%

Section: Identification Risk For Linkage By Matchingmentioning

confidence: 99%

The Probability of Identification: Applying Ideas from Forensic Statistics to Disclosure Risk Assessment

Skinner

2006

Journal of the Royal Statistical Society Series A: Statistics in Society

View full text Add to dashboard Cite

show abstract

“…The two different approaches led to a considerable debate known as the database search controversy. Stockmarr's approach was heavily criticized by Evett et al (2000), Dawid (2001), and Balding (2002). In their points of view, H

_{italicp_{2}}

and H

_{italicd_{2}}

are not the hypotheses of interest and hence LR 2 should not be presented to the court.…”

Section: Single‐source Stainsmentioning

confidence: 99%

“…Using a different formulation of the hypotheses, Stockmarr (1999) reached a different conclusion suggesting that the larger the database the weaker the DNA evidence. Their contradictory results give rise to a considerable debate referred to as the DNA database search controversy (Devlin, 2000; Evett et al, 2000; Dawid, 2001; Balding, 2002). Meester and Sjerps (2003) give a comprehensive discussion to resolve the confusion.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of DNA Mixtures from Database Search

Chung

Fung

2010

Biometrics

View full text Add to dashboard Cite

With the aim of bridging the gap between DNA mixture analysis and DNA database search, a novel approach is proposed to evaluate the forensic evidence of DNA mixtures when the suspect is identified by the search of a database of DNA profiles. General formulae are developed for the calculation of the likelihood ratio for a two-person mixture under general situations including multiple matches and imperfect evidence. The influence of the prior probabilities on the weight of evidence under the scenario of multiple matches is demonstrated by a numerical example based on Hong Kong data. Our approach is shown to be capable of presenting the forensic evidence of DNA mixtures in a comprehensive way when the suspect is identified through database search.

show abstract

“…The issues that seem important in this debate are (a) Double-counting: Balding [20] notes that ''the notion that evidence that has led to the identification of the suspect should not be subsequently used as evidence in court is analogous with some modes of statistical reasoning. But it is inconsistent with legal practice and would, I believe, be regarded as absurd by legal commentators''.…”

Section: Introductionmentioning

confidence: 99%