The expression “better late than never” applies to this post. Over the span of two days in June 2013 the Measurement Science and Standards in Forensic Handwriting Analysis (MSSFHA) conference was held. It explored the (then) current state of forensic handwriting analysis, aka, forensic handwriting examination (FHE). Presentations varied in content but most discussed recent advancements in measurement science and quantitative analyses as it relates to FHE.
The conference was organized by NIST’s Law Enforcement Standards Office (OLES) in collaboration with the AAFS — Questioned Document Section, the ABFDE, the ASQDE, the FBI Laboratory, the NIJ and SWGDOC.
You can get general information about the conference at this link. On that page you will also find a link to the archived webcast of the event. You can jump straight to PDFs of the presentations using this link.
My personal contribution was a presentation entitled “Error, Confidence and (Un)certainty — Deconstructing Authorship Opinions Using a Forced-Call Testing Protocol”. The abstract for the presentation read as follows:
The issue of potential error and uncertainty in the opinions expressed by forensic handwriting examiners (FHE) should be of interest to all practitioners. These concepts are relevant whether an examiner expresses an opinion in the form of posterior probabilities/odds such as the approach outlined in ASTM E1658, or as some form of likelihood-ratio (LR).
This presentation will discuss a forced-call testing protocol intended to “decouple” the authorship call (opinion) from the confidence rating for that call. This approach permits a more in-depth analysis of the relationship between confidence and error helping to clarify the meaning of the confidence scale embodied in E1658. At the same time, it provides a possible framework for the empirical justification of any multi-level opinion scale.
There will be some discussion of issues and concerns relating to testing, potential error and uncertainty in authorship opinions, including suggestions as to how uncertainty might be expressed more clearly in FHE conclusions. The goal of this talk is to promote better understanding and further discussion about error and uncertainty in both the FHE evaluation process and the resulting opinions.
I did not prepare a written document to accompany that presentation but I can provide a PDF of the slides for the presentation. Please note that some of the slides may be difficult to understand without the accompanying verbal commentary. If you have any questions or comments please let me know. Or you can also watch the webcast of the event.Brent_Ostrum__NIST_2013_Error_and_Uncertainty_Final