New training: Assessing Data Quality and Disclosure Risk in Numeric Data

The Research Data Service, in collaboration with the UK Data Service, are running workshops on the theme ‘Assessing Data Quality and Disclosure Risk in Numeric Data’. These hands-on sessions introduce the key elements of data quality and disclosure risk, and include practical demonstrations of two tools to evaluate the quality (QAMyData) and disclosure risk (sdcMicro) of numeric research data.

Workshops will run across two days, with sessions on different days for researchers interested in social survey data (10th June) and health data (11th June).

Session 1: Assessing Data Quality in Numeric Data

This workshop will introduce the key elements of data quality assessment, including file checks, and undertaking data and metadata checks. Attendees will gain hands-on experience using QAMyData, a purpose-built configurable tool to quickly and automatically detect some of the most common problems in survey and other numeric data (SPSS, STATA, SAS & csv files).

Session 2: Assessing Disclosure Risk in Numeric Data

This workshop will provide an introduction to statistical disclosure control (SDC), covering: types of Identifiers; de-identification and anonymization; types of disclosure; SDC approaches; k-anonymity and l-diversity. The workshop introduces sdcMicro, a practical R package for measuring disclosure risk in numeric data. The session will give attendees hands-on experience using sdcMicro to assess disclosure risk and apply SDC methods to anonymize numeric data, while evaluating the balance between disclosure risk and data loss.

These sessions are available to research staff and students and can be booked using the links below:

Assessing Data Quality in Numeric Data (Social Survey Data) –                                      10th June 0930-1200, Lister Learning and Teaching Centre, Room 1.16 (Central Area)  https://www.events.ed.ac.uk/index.cfm?event=book&scheduleID=34939

Assessing Disclosure Risk in Numeric Data (Social Survey Data) –                                10th June 1330-1700, Lister Learning and Teaching Centre, Room 1.16 (Central Area) https://www.events.ed.ac.uk/index.cfm?event=book&scheduleID=34941

Assessing Data Quality in Numeric Data (Health Data) –                                                  11th June 0930-1230, Microlab 1, Chancellor’s Building (Little France) https://www.events.ed.ac.uk/index.cfm?event=book&scheduleID=34940

Assessing Disclosure Risk in Numeric Data (Health Data) –                                            11th June 1300-1700, Microlab 1, Chancellor’s Building (Little France)                                 https://www.events.ed.ac.uk/index.cfm?event=book&scheduleID=34942

Bob Sanders
Research Data Support
Library & University Collections

Leave a Reply

Your email address will not be published. Required fields are marked *