Presentation Type
Poster
Student
Yes
Track
Forensic Statistics
Abstract
In forensic source identification the forensic expert is responsible for providing a summary of the evidence that allows for a decision maker to make a logical and coherent decision concerning the source of some trace evidence of interest. The academic consensus is usually that this summary should take the form of a likelihood ratio (LR) that summarizes the likelihood of the trace evidence arising under two competing propositions. These competing propositions are usually referred to as the prosecution’s proposition, that the specified source is the actual source of the trace evidence, and the defense’s proposition, that another source in a relevant background population is the actual source of the trace evidence. When a relevant background population has a subpopulation structure, the rates of misleading evidence of the LR will tend to vary within the subpopulations, sometimes to an alarming degree. Our preliminary work concerning synthetic and real data indicates that the rates of misleading evidence are different among subpopulations of different sizes, which can lead to a systematic bias when using a LR to present evidence. In this presentation we will summarize our preliminary results for characterizing this bias.
Start Date
2-7-2023 1:00 PM
End Date
2-7-2023 2:00 PM
Included in
A Characterization of Bias Introduced into Forensic Source Identification when there is a Subpopulation Structure in the Relevant Source Population.
Volstorff A
In forensic source identification the forensic expert is responsible for providing a summary of the evidence that allows for a decision maker to make a logical and coherent decision concerning the source of some trace evidence of interest. The academic consensus is usually that this summary should take the form of a likelihood ratio (LR) that summarizes the likelihood of the trace evidence arising under two competing propositions. These competing propositions are usually referred to as the prosecution’s proposition, that the specified source is the actual source of the trace evidence, and the defense’s proposition, that another source in a relevant background population is the actual source of the trace evidence. When a relevant background population has a subpopulation structure, the rates of misleading evidence of the LR will tend to vary within the subpopulations, sometimes to an alarming degree. Our preliminary work concerning synthetic and real data indicates that the rates of misleading evidence are different among subpopulations of different sizes, which can lead to a systematic bias when using a LR to present evidence. In this presentation we will summarize our preliminary results for characterizing this bias.