Premium
Assessment of Data Quality: Errors of Measurement and Errors of Process
Author(s) -
Arndt Stephan,
Woolson Robert W.
Publication year - 1993
Publication title -
biometrical journal
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.108
H-Index - 63
eISSN - 1521-4036
pISSN - 0323-3847
DOI - 10.1002/bimj.4710350307
Subject(s) - reliability (semiconductor) , computer science , process (computing) , reliability engineering , quality (philosophy) , data mining , observational error , data quality , statistics , non sampling error , algorithm , mathematics , engineering , operations management , metric (unit) , power (physics) , philosophy , physics , epistemology , quantum mechanics , operating system
As projects progress from pilot studies with few simple variables and small samples, the research process as a whole becomes qualitatively more complex and subject to an array of contamination by errors and mistakes. Data usually undergo a series of manipulations (e.g., recording, computer entry, transmission) prior to final statistical analysis. The process, then, consists of numerous operations only ending with eventual statistical analysis and write‐up. We present a means of estimating the impact of process error in the same terms as psychometric reliability and discuss the implications for reducing the impact of errors on overall data quality.