NAACCR Online Education
Synthetic Datasets: Generating Cancer Registry Data for Testing and Teaching Purposes
Recorded On: 01/24/2022
This NAACCR Talk will provide a contextual overview of the need for a NAACCR Synthetic Dataset, the history of NAACCR work in this area, guidance on what the synthetic data represent, and list some appropriate use cases. This will be followed by a tutorial on how to generate a synthetic dataset using File*Pro along with a discussion on the methods for generating specific variables.
David Stinchcomb, MS
Senior Health Research Manager
Dave Stinchcomb is a senior health research manager at Westat Inc. focusing primarily on disease surveillance, geospatial analysis, data linkages, public health informatics, and data visualization. At Westat, Mr. Stinchcomb chairs a data visualization working group that serves as a steering committee for Westat's data visualization activities.
Fabian Depry, MS
Senior Systems Analyst
Information Management Services
Fabian Depry, focuses on the design and implementation of biomedical computer systems. He has extensive experience and expertise in systems design and object-oriented programming, focusing mainly on Java Desktop and Web applications. Mr. Depry is a lead developer and designer on the SEER*DMS project. He also designed and developed the SEER Abstracting tool, the SEER*Edits Submission tool and the SEER Data Viewer tool. Mr Depry holds a BS in Computer Science from Universite Catholique de Louvain (UCL), Belgium and a MS in Computer Science from Hood College, Frederick. He has been with IMS since 2003.