The reliability of ProZone MatchViewer: a video-based technical performance analysis system
Paul Bradley,
Peter O’Donoghue,
Blake Wooster and
Phil Tordoff
International Journal of Performance Analysis in Sport, 2007, vol. 7, issue 3, 117-129
Abstract:
The aim of the present study was to determine the inter-observer reliability of ProZone’s MatchViewer system. Two groups of trained observers independently analysed an English FA Premier League soccer match. In total, 2552 events were recorded by both observers with 12 events being recorded only by the first observer and 37 events being recorded only by the second observer. The mean absolute error of event time was 0.007 s with very good strengths of inter-observer agreement found for event type (κ = 0.990), player (κ = 0.995) and second player involved in the event (κ = 0.979). The mean absolute error in pitch location of event was 3.6 m with the location of 95% of events being agreed by the two observers to within 8.5 m. The results suggest that ProZone’s MatchViewer system is reliable when operated by observers that have undergone the recommended quantity of end-user training.
Date: 2007
References: View complete reference list from CitEc
Citations: View citations in EconPapers (2)
Downloads: (external link)
http://hdl.handle.net/10.1080/24748668.2007.11868415 (text/html)
Access to full text is restricted to subscribers.
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:taf:rpanxx:v:7:y:2007:i:3:p:117-129
Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/RPAN20
DOI: 10.1080/24748668.2007.11868415
Access Statistics for this article
International Journal of Performance Analysis in Sport is currently edited by Peter O'Donoghue
More articles in International Journal of Performance Analysis in Sport from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().