We have over 12,000 students, from over 100 countries, within one of the safest campuses in the UK


93% of Lancaster students go into work or further study within six months of graduating

Home > Research > Publications & Outputs > Mining institutional datasets to support policy...
View graph of relations

« Back

Mining institutional datasets to support policy making and implementation

Research output: Contribution to journalJournal article


  • Mantz Yorke
  • Greg Barnett
  • Peter Evanson
  • Chris Haines
  • Don Jenkins
  • Peter Knight
  • Dave Scurry
  • Marie Stowell
  • Harvey Woolf
Journal publication date2005
JournalJournal of Higher Education Policy and Management
Number of pages14
Original languageEnglish


Datasets are often under‐exploited by institutions, yet they contain evidence that is potentially of high value for planning and decision‐making. This article shows how institutional data were used to determine whether the demographic background of students might have an influence on their performance: this is a matter of particular interest where participation in higher education is being widened. Analyses showed that, whilst area of domicile appeared to be related to lower performance in a few disciplinary areas, much stronger relationships were evident in respect of other demographic variables. The use of nonparametric analyses based on cutting module performances at the median, rather than using raw scores, is of methodological interest since the distribution of raw marks is influenced by the subject discipline.