Icon of a blue cylindrical database with three stacked layers, depicted in a simple, flat style.

Computer Files

Posted October 15, 2017


Currently in the field of forensic science there is much international debate regarding the role of forensic evidence data, and the use of corresponding databases, to correctly identify a suspect in a crime. CSAFE recently convened a group of expert researchers at a Carnegie Mellon University workshop to discuss the impact of the limitations of forensic databases.
CSAFE Co-Director and Carnegie Mellon John. C. Warner Professor of Statistics Dr. Bill Eddy emphasized that in the forensic field there are many databases created to assist law enforcement in linking a suspect to a crime.  These databases can include fingerprints, bullet casings, automobile paint, and more.  However, many of the current forensic databases were developed as a response to law enforcement needs, usually without careful consideration of the statistical and scientific principles associated with use.

“I think many people think that a database is a pile of data, but it is actually organized in some way and typically is supported by a database management system so you can make inquiries,” Eddy said.   “However, when you using a database, important statistical issues arise.  There is, for example, the size of the database; how will the data represent the population of interest; and what other information the examiner has besides the sample evidence.”

These factors can lead to decreased accuracy when matching crime scene evidence to a suspect.  It can also cause disagreements among forensic science professionals about how much certainty an examiner has that the sample evidence matches a database element.

One goal of CSAFE is to build a community of skilled researchers and forensic science partners to address the lack of common understanding and agreement on how to accurately use forensic databases.  Our team is committed to continuously engaging in conversation with the forensic science, judicial, and lay communities to identify areas where the field can strengthen the scientific validity of its methods.

From the Blog

Journal article titled "Challenges in Modeling...Images as Forensic Evidence" by Kafadar and Carriquiry.

Two Journals for Sharing Your Forensic Science and Statistics Research

If you’re looking for a journal to showcase your latest research findings, consider exploring these …

NIST sign outside, surrounded by flowers and trees, on a sunny day.

NIST Report Highlights Key Challenges in Forensic Science and Provides Strategies for Addressing Them

In September, the National Institute of Standards and Technology (NIST) released a new report titled …

Recent Posts

ICFIS 2026 logo features a clock tower and the Forensic Inference and Statistics name.

Keynote Speakers Announced for ICFIS 2026

August 10, 2026

The Scientific Committee for the 12th International Conference on Forensic Inference and Statistics is pleased to announce the keynote speakers …

2026 Wisconsin NAFSB Conference logo on a dark blue background.

CSAFE Researchers will be Panel Speakers at NAFSB 2026 Conference

August 7, 2026

The annual National Association of Forensic Science Boards (NAFSB) Conference will be Oct. 13-16 at the Milwaukee Crime Lab Bureau …

ICFIS 2026 logo features a clock tower and the Forensic Inference and Statistics name.

ICFIS 2026 Moves Online, Abstract Deadline Extended to Aug. 17

July 27, 2026

The 12th International Conference on Forensic Inference and Statistics (ICFIS) will now be an online-only event, allowing participants from around the world …