Evaluation of Tennis Match Data - New Acquisition Model

• Authors: Niksa Djurovic , Vinko Lozovina , Leo Pavicic
• Languages of publication: EN

Abstracts

EN

The purpose of this research was to analyze and interpret the latent (factor) area of a tennis match. The entities in this research make 128 tennis matches played at the 2007 and 2008 Grand Slams hard court surfaces. The variables were created by use of the official statistics kept by the IBM Software - IBM DB2 Universal Database. The original variables were standardized to the number of sets in a match. A factor analysis under a component model was conducted. The number of factors retained, which was determined by the G-K criterion, explained 83.38 % of the total variance. Five significant factors substantiated the hypothesis established in this paper. The first factor named Match Successfulness is determined by the total number of break points; break points won and received points. The second factor named First Serve Significance is determined by the total number of first serves and winning points after the first serve. The third factor named Serve Speed is determined by the average speed of the serve and the fastest serve. The fourth factor named Net Play is determined by the total net approaches as well as the winning points after net approaches which are directly dependent on the total number of serves. The fifth factor named Play Errors is determined by unforced and double-fault errors. Winning matches differentiate from the lost matches by a smaller number of unforced and double-fault errors; considerably better results of the first serve, maximum serve speed and the number of aces scored, high score of total break points and break points won. The facts that do not differentiate winning matches from the lost ones are: first serves total, first serve throw-in, winning points after the first serve, number of net approaches and winning points after net approaches. The classification results show that with a system of 15 variables it is possible to recognize 96.0% of lost and 96.9% of winning matches. The achieved results indicate that the official match statistics with a modified system of 15 selected variables can properly interpret and predict match successfulness. This enables creators of a match observation system to valorize and enhance it with new indices.

Keywords

EN

directoblimin rotation; match successfulness; grand slam tournaments; tennis latent dimensions

• Publisher: De Gruyter Open
• Journal: Journal of Human Kinetics
• Year: 2009
• Volume: 21
• Pages: 15-21

Dates

published

1 - 1 - 2009

online

17 - 7 - 2009

Contributors

author

Niksa Djurovic

• Faculty of Kinesiology, Split University

author

Vinko Lozovina

• Faculty of Maritime Studies, Split University

author

Leo Pavicic

• Faculty of Kinesiology, Zagreb University

References

• Brody H. Unforced errors and error reduction in tennis. Brit J Sports Med, 2006. 40: 397-400.[Crossref]
• Bruce E. Biomechanics and tennis, Brit J Sports Med, 2006. 40: 392-396.
• Chow J.W., Carlton L.G., Chae W., Shim J., Lim J., Kuenster, A.F. Movement characteristics of the tennis volley. Med Sci Sports Exerc, 1999. 31: 855-863.[Crossref][PubMed]
• Crognier L., Féry Y.A. Effect of Tactical Initiative on Predicting Passing Shots in Tennis. Appl Cognitive Psych, 2005. 19: 637-649.[Crossref]
• FischerG. Exercise in probability and statistics, or the probability of winning at tennis. Am J Phys, 1980. 48(1), 14-19.[Crossref]
• Frings C. Who will win Wimbledon? The recognition heuristic in predicting sports events. J Behav Decis Making, 2006. 19: 321-332.
• IBM Software - IBM DB2 Universal Database.
• Klaassen F., Magnus J. Are points in tennis independent and identically distributed? Evidence from a dynamic binary panel data model. J Am Stat Assoc, 2001. 96: 500-509.[Crossref]
• Magnus J., Klaassen F. The final set in a tennis match: Four years at Wimbledon. J Appl Stat, 1999. 26: 461-468.[Crossref]
• Magnus J., Klaassen F. On the advantage of serving first in a tennis set: Four years at Wimbledon. The Statistician, 1999. 48: 247-256.
• Match Analysis DVD
• Miles R.E. Symmetric sequential analysis: the efficiencies of sports scoring systems. J Roy Stat Soc B Met, 1984. 46: 93-108.
• Newton P.K., Keller J.B. Probability of winning at tennis I. Theory and data. Stud Appl Math, 2005. 114: 241-269.[Crossref]
• O'DonoghueP.G. The most important points in Grand Slam singles tennis. Res Q Exercise Sport, 2001. 72: 125-131.
• Paserman M.D. Gender Differences in Performance in Competitive Environments: Evidence from Professional Tennis Players, 2007. C.E.P.R. 6335 Discussion Papers.
• Pollard G., Cross R., Meyer D. An analysis of ten years of the four grand slam men's singles data for lack of independence of set outcomes. J Sports Sci Med, 2006. 5 : 561-566.
• Pugh S. F., Kovaleski J. E., Heitman R. J., Gilley W. F. Upper and lower body strength in relation to ball speed during a serve by male collegiate tennis players. Perceptual and motor skills, 2003. 97 : 867-872.[PubMed]
• Riddle L. H. Probability Models for Tennis Scoring Systems. Appl Stat, 1988. 37: 63-75.[Crossref]
• ScheibehenneB., Broder A. Predicting Wimbledon 2005 tennis results by mere player name recognition. Int J Forecasting, 2007. 23: 415-426.

Identifiers

DOI

10.2478/v10078-09-0002-9