EFFECT SIZE AND ALTERNATIVE STATISTICAL APPROACHES IN SPORTS SCIENCES

Abstract

It is known that there are some limitations in transferring the results of scientific studies to the practice in the sports sciences as in other disciplines. Main reason for the gap between research and practice in sports sciences is considered as the reporting approach of only the analysis results and P- values in many studies using null hypothesis. Some researchers have suggested that practical importance of the intervention effect should be focused, arguing that the null hypothesis is always false in the real world. In recent years, it has been emphasized that the research results using the current statistical approach should be supported with methods that appeal to practice, such as the effect size. The aim of this study is to examine models that are suggested to be an alternative to the current statistical approach commonly used in scientific studies and some supportive methods, and to increase to the use of methods considered useful in the field of sports sciences. Although there is a consensus in the literature regarding the reporting of effect size, there are some disagreements regarding the classification of the effect size. Despite some practical advantages of the magnitude based inferences and the Bayesian statistical models, it is more accepted that it cannot be an alternative to valid statistical approach used in the current conditions. On the other hand, it is stated that the supportive methods that emphasize the smallest important change amount and error terms, which are considered critical in practice, will provide practical benefits in sports sciences. Consequently, although the discussions about the models that can be an alternative to the current statistical approach in the literature continue, there is a widespread consensus that supporting analyzes of the null hypothesis (P- value, statistical significance) with methods for practical use provide important benefits.

Keywords

• Practical significance
• smallest worthwhile change
• typical error

SPOR BİLİMLERİNDE ETKİ BÜYÜKLÜĞÜ VE ALTERNATİF İSTATİSTİK YAKLAŞIMLARI

Öz

Öz: Diğer disiplinlerde olduğu gibi spor bilimleri alanında da bilimsel çalışmaların sonuçlarının sahaya aktarılmasında bazı sınırlılıklar olduğu bilinmektedir. Birçok araştırmanın sadece yokluk hipotezinin test edildiği analiz sonuçları ve p-değeri ile rapor edilmesi, spor bilimlerinde araştırma ve uygulama arasındaki boşluğun başlıca sebebi olarak gösterilmektedir. Bazı araştırmacılar gerçek dünyada yokluk hipotezinin daima yanlış olduğunu ileri sürerek müdahale etkisinin pratikteki büyüklüğüne daha fazla odaklanılması gerektiğini savunmaktadır. Son yıllarda mevcut istatistiktik yaklaşımının kullanıldığı araştırma sonuçlarının etki büyüklüğü gibi pratiğe hitap eden yöntemler ile desteklenmesine sıkça vurgu yapılmaktadır. Bu çalışmanın amacı bilimsel çalışmalarda sıklıkla kullanılan genel istatistik yaklaşımına alternatif olabileceği ileri sürülen modelleri ve destekleyici nitelik taşıyan bazı yöntemleri incelemek ve faydalı olduğu düşünülen yöntemlerin spor bilimleri alanında yaygınlaşmasına katkıda bulunmaktır. Literatürde özellikle etki büyüklüğünün rapor edilmesine ilişkin bir fikir birliği sağlanmış olsa da etki büyüklüğünün sınıflandırılmasına ilişkin bazı görüş ayrılıkları vardır. Büyüklük temelli çıkarım modeli ve Bayesci istatistik modelinin de pratikte sağladığı bazı avantajlara rağmen mevcut şartlarda kullanılan istatistik yaklaşımına bir alternatif olamayacağı daha fazla kabul görmektedir. Diğer taraftan pratikte önemli kabul edilen en küçük değişim miktarının ve hata terimlerinin vurgulandığı destekleyici yöntemlerin spor bilimlerinde pratik bir fayda sağlayacağı belirtilmektedir. Sonuç olarak literatürde mevcut istatistik yaklaşımına alternatif olabilecek modeller ile ilgili tartışmaların devam etmesine rağmen, yokluk hipotezinin test edildiği sonuçların (p-değeri, istatistiksel anlamlılık analizleri) pratik kullanıma ilişkin destekleyici yöntemler ile birlikte sunulmasının önemli yararlar sağladığı konusunda yaygın bir kabul oluşmuştur.

Anahtar Kelimeler

• Pratik anlamlılık
• minimum anlamlı değişim
• tipik hata

Kaynakça

1. Alpar, R. (2010). Spor, sağlık ve eğitim bilimlerinden örneklerle uygulamalı istatistik ve geçerlik-güvenirlik: Detay yayıncılık.
2. Altman, D. G., Bland, J. M. (2005). Standard deviations and standard errors. Bmj, 331(7521), 903.
3. Barker, R. J., Schofield, M. R. (2008). Inference about magnitudes of effects. International journal of sports physiology and performance, 3(4), 547-557.
4. Batterham, A. M., Hopkins, W. G. (2006). Making meaningful inferences about magnitudes. International journal of sports physiology and performance, 1(1), 50-57.
5. Bayes, T. (1991). An essay towards solving a problem in the doctrine of chances. 1763. MD computing: computers in medical practice, 8(3), 157.
6. Bernards, J. R., Sato, K., Haff, G. G., Bazyler, C. D. (2017). Current research and statistical practices in sport science and a need for change. Sports, 5(4), 87.
7. Bortz, J., Döring, N. (2007). Forschungsmethoden und Evaluation für Human-und Sozialwissenschaftler: Limitierte Sonderausgabe: Springer-Verlag.
8. Cohen, J. (1969). Statistical Power Analysis for the Behavioral Science: New York: Academic Press.

9. Cohen, J. (1973). Eta-squared and partial eta-squared in fixed factor ANOVA designs. Educational and psychological measurement, 33(1), 107-112.
10. Cohen, J. (1988). Statistical power analysis for the behavioral sciences, 2nd edn. Á/L: Erbaum Press, Hillsdale, NJ, USA.
11. Cohen, J. (2013). Statistical power analysis for the behavioral sciences: Academic press.
12. Coyne, J. O., Tran, T. T., Secomb, J. L., Lundgren, L., Farley, O. R., Newton, R. U., Sheppard, J. M. (2015). Reliability of pull up ve dip maximal strength tests. J Aust Strength Cond, 23, 21-27.
13. Cumming, G. (2014). The new statistics: Why and how. Psychological science, 25(1), 7-29.
14. Çelebi, V. (2019). Bayes teoremi bağlamında olasılıkçı Bayes epistemolojisinin kapsamı üzerine bir inceleme. Felsefe ve Sosyal Bilimler Dergisi (FLSF)(28).
15. Dankel, S. J., Mouser, J. G., Mattocks, K. T., Counts, B. R., Jessee, M. B., Buckner, S. L., . . . Loenneke, J. P. (2017). The widespread misuse of effect sizes. Journal of Science and Medicine in Sport, 20(5), 446-450.
16. do Nascimento, M. A., Ribeiro, A. S., de Souza Padilha, C., da Silva, D. R. P., Mayhew, J. L., do Amaral Campos Filho, M. G., Cyrino, E. S. (2017). Reliability and smallest worthwhile difference in 1RM tests according to previous resistance training experience in young women. Biology of Sport, 34(3), 279-285.
17. Ferreira da Silva Santos, J., Lopes-Silva, J. P., Loturco, I., Franchini, E. (2020). Test-retest reliability, sensibility and construct validity of the frequency speed of kick test in male black-belt taekwondo athletes. Ido Movement for Culture. Journal of Martial Arts Anthropology, 20(3), 38-46.
18. Flanagan, E. P. (2013). The effect size statistic—Applications for the strength and conditioning coach. Strength ve Conditioning Journal, 35(5), 37-40.
19. Fritz, C. O., Morris, P. E., Richler, J. J. (2012). Effect size estimates: current use, calculations, and interpretation. Journal of experimental psychology: General, 141(1), 2.
20. Fröhlich, M., Emrich, E., Pieter, A., Stark, R. (2009). Outcome effects and effects sizes in sport sciences. International Journal of Sports Science and Engineering, 3(3), 175-179. Greenland, S., Senn, S. J., Rothman, K. J., Carlin, J. B., Poole, C., Goodman, S. N., Altman, D. G. (2016). Statistical tests, P values, confidence intervals, and power: a guide to misinterpretations. European journal of epidemiology, 31(4), 337-350.
21. Guyatt, G. H., Kirshner, B., Jaeschke, R. (1992). Measuring health status: what are the necessary measurement properties? Journal of clinical epidemiology, 45(12), 1341-1345.
22. Hazir, T., Kose, M. G., Kin-Isler, A. (2018). The validity of running anaerobic sprint test to assess anaerobic power in young soccer players. Isokinetics and Exercise Science, 26(3), 201-209.
23. Hedges, L. V., Olkin, I. (2014). Statistical methods for meta-analysis: Academic press.
24. Hopkins, W. G., Batterham, A. (2018). The vindication of magnitude-based inference. Sportscience, 22, 19-29.
25. Hopkins, W. G., Marshall, S., Batterham, A., Hanin, J. (2009). Progressive statistics for studies in sports medicine and exercise science. Medicine+ Science in Sports+ Exercise, 41(1), 3.
26. Hopkins, W. G. (2000). Measures of reliability in sports medicine and science. Sports medicine, 30(1), 1-15.
27. Hopkins, W. G. (2002). A scale of magnitudes for effect statistics. A new view of statistics, 502, 411.
28. Hopkins, W. G. (2017). Estimating Sample Size for Magnitude-Based Inferences. Sportscience, 21.
29. Hopkins, W. G. (2019). Compatibility intervals and magnitude-based decisions for standardized differences and changes in means. Sportscience.
30. Lakens, D. (2013). Calculating and reporting effect sizes to facilitate cumulative science: a practical primer for t-tests and ANOVAs. Frontiers in psychology, 4, 863.
31. Levine, T. R., Hullett, C. R. (2002). Eta squared, partial eta squared, and misreporting of effect size in communication research. Human Communication Research, 28(4), 612-625.
32. Lohse, K., Sainani, K., Taylor, J. A., Butson, M. L., Knight, E., Vickers, A. (2020). Systematic Review of the use of “Magnitude-Based Inference” in Sports Science and Medicine.
33. Mengersen, K. L., Drovandi, C. C., Robert, C. P., Pyne, D. B., Gore, C. J. (2016). Bayesian estimation of small effects in exercise and sports science. PloS one, 11(4), e0147311.
34. Özbay, S., Ulupınar, S. (2019). Reliability of 1RM, 5RM and 10RM Tests in Upper Body Resistance Exercises. The Journal of Turkish Sport Sciences for Health, 2(1), 1-7.
35. Özbay, S., Ulupınar, S., Çınar, V., Akbulut, T. (2019). Reliability of Easily Applicable Non-Laboratory Methods Used for Determination of the Upper Body Strength. Turkiye Klinikleri Journal of Sports Sciences, 11(2).
36. Panissa, V. L., Fukuda, D. H., Caldeira, R. S., Gerosa-Neto, J., Lira, F. S., Zagatto, A. M., Franchini, E. (2018). Is oxygen uptake measurement enough to estimate energy expenditure during high-intensity intermittent exercise? Quantification of anaerobic contribution by different methods. Frontiers in Physiology, 9, 868.
37. Peltola, E. (2005). Competitive performance of elite track-and-field athletes: variability and smallest worthwhile enhancements. Sportscience, 9, 17-21.
38. Peterson, M. D., Rhea, M. R., Alvar, B. A. (2004). Maximizing strength development in athletes: a meta-analysis to determine the dose-response relationship. The Journal of Strength ve Conditioning Research, 18(2), 377-382.
39. Pyne, D. B. (2003). Interpreting the results of fitness testing. Paper presented at the International science and football symposium.
40. Rhea, M. R. (2004). Determining the magnitude of treatment effects in strength training research through the use of the effect size. Journal of strength and conditioning research, 18, 918-920. Rhea, M. R., Alderman, B. L. (2004). A meta-analysis of periodized versus nonperiodized strength and power training programs. Research quarterly for exercise and sport, 75(4), 413-422. Rhea, M. R., Alvar, B. A., Burkett, L. N. (2002). Single versus multiple sets for strength: a meta-analysis to address the controversy. Research quarterly for exercise and sport, 73(4), 485-488.
41. Rhea, M. R., Alvar, B. A., Burkett, L. N. ve Ball, S. D. (2003). A meta-analysis to determine the dose response for strength development.
42. Rosenthal, R., Rosnow, R. L. (1985). Contrast analysis: Focused comparisons in the analysis of variance: CUP Archive.
43. Rosnow, R. L., Rosenthal, R. (2003). Effect sizes for experimenting psychologists. Canadian Journal of Experimental Psychology/Revue canadienne de psychologie expérimentale, 57(3), 221.
44. Sainani, K. L. (2018). The Problem with" Magnitude-based Inference". Medicine and science in sports and exercise, 50(10), 2166-2176.
45. Sawilowsky, S. S. (2009). New effect size rules of thumb. Journal of Modern Applied Statistical Methods, 8(2), 26.
46. Sullivan, G. M., Feinn, R. (2012). Using effect size—or why the P value is not enough. Journal of graduate medical education, 4(3), 279-282.
47. Tomczak, M., Tomczak, E. (2014). The need to report effect size estimates revisited. An overview of some recommended measures of effect size.
48. Weir, J. P. (2005). Quantifying test-retest reliability using the intraclass correlation coefficient and the SEM. The Journal of Strength ve Conditioning Research, 19(1), 231-240.
49. Welsh, A. H., Knight, E. J. (2015). “Magnitude-based inference”: a statistical review. Medicine and science in sports and exercise, 47(4), 874.
50. Wilkinson, T. J., Xenophontos, S., Gould, D. W., Vogt, B. P., Viana, J. L., Smith, A. C., Watson, E. L. (2019). Test–retest reliability, validation, and “minimal detectable change” scores for frequently reported tests of objective physical function in patients with non-dialysis chronic kidney disease. Physiotherapy theory and practice, 35(6), 565-576.