Applications of Confidence Limits and Effect Sizes in Sport Research
نویسنده
چکیده
This article describes the origins of the conventional use of null hypothesis significance testing and why this convention has led to difficulties in implementing research results in applied settings. This article continues to explain the the value of expressing research results with confidence limits and effect sizes for sporting application. As researchers investigating human performance, one of our greatest measures of success is for our research outcome to be implemented by sports coaches for their athletes. While coaches are becoming increasingly receptive to the results of sports scientists, coaches are often frustrated by the inconclusive and numerically cryptic results we report. Conventional null hypothesis significance testing dictates that unless the probability of rejecting the null in error (p-value) is less than 5%, we must accept the null hypothesis that the difference between our groups is zero. But to return to a sports coach after six weeks of a training intervention to report “nothing happened” is frustrating and probably not entirely accurate. It may be possible that the intervention did have an effect, but due to sources of error in human performance testing, the results lacked sufficient consistency to pass the conventional 5% rule. However, is the p-value returned by our results greater than 5% because nothing happened, or is the problem in our use of the arbitrary 5% line in the sand to justify the success or failure of our intervention? After all, “... surely, God loves the .06 nearly as much as the .05." [1, p. 1277]. Origins of the p-values in Null Hypothesis Significance Testing Initially describing type I and type II error rates was the work of Neyman and Pearson [2]. Neyman and Pearson considered that there was sufficient evidence to reject a null hypothesis if the probability of its rejection in error was less than 5%. The work by Fisher [3] initially described some standard levels (e.g. 1%, 5%, 10%, etc.) of area under the 2 , tand f-distributions, thereby making 5% of these distributions widely accessible to researchers. While Fisher only intended percentages of these distributions to add support to inferences drawn from data, Neyman and Pearson argued that in order for research to be used to make decisions, 5% of these distributions was an acceptable (cut-off point) [4]. Since this time, accepting or rejecting a null hypothesis based on a 5% probability of error has become the norm. The sport science interpretation of Neyman and Pearson’s work would be that sports coaches (i.e. research end-users) can only make informed decisions when told if an intervention works or does not work, whereas Fisher would argue that sports coaches should be the ones to decide what probability of error is unacceptably high for their athletes [4]. *Address correspondence to this author at the School of Human Movement Studies, Charles Sturt University, Panorama Avenue, Bathurst, NSW, Australia, 2795, Australia; Tel: +61 2 6338 6116; Fax: +61 2 6338 4065; E-mail: [email protected] Confidence Limits After decades of accepting or rejecting null hypotheses based on p-values of less than or greater than 0.05, there has been a recent criticism of using solely the p-value to accept or reject research findings [5]. Confidence limits express the precision of the mean changes within a sample (or mean differences between samples, hereafter called the mean estimate) by expressing upper and lower boundaries within a confidence bandwidth (e.g. 90%, 95%) rather than simply expressing the probability that the mean estimate equals zero. When expressing a mean estimate (e.g. there was 66 W difference between two groups) Fig. (1), the true difference between the two groups for the population is unlikely to be exactly 66 W. The 66 W only represents an estimate from the sample; there is certain to be error in the mean estimate when making inferences from the sample to the population. For example, in a recent piece of research [6] we indicated that the estimated difference between two trials was 66 W and, while accepting that 66 W was unlikely to be the exact effect of the intervention, we were 95% certain that the true value of the difference between trials lay between 36 and 96W. In this way, we provided much more useful information about the precision of our estimate, rather than just the 66 W estimate and that the probability of the estimated difference was actually zero was less than 1% [6]. Confidence limits can be derived for any percent level, though most common are 90% and 95%. While some researchers [7] feel that the range of 95% confidence limits is too broad to be useful, others [6] feel that 95% confidence limits are more suitable in the current climate in which many journal reviewers still look for statistical significance of results. A p-value of less than 0.05 (i.e. ‘statistically significant’) can be derived from 95% confidence limits if both the upper and lower limits are on the same side of the zero (e.g. 36 to 96 W, Figure 1, Series 1); if the upper and lower limits are on different sides of the zero (e.g. -14 to 146 W, Fig. (1), Series 2) then the result had a p-value of greater than 0.05.
منابع مشابه
Outer and Inner Confidence Intervals Based on Extreme Order Statistics in a Proportional Hazard Model
Let Mi and Mi be the maximum and minimum of the ith sample from k independent sample with different sample sizes, respectively. Suppose that the survival distribution function of the ith sample is F ̄i = F ̄αi, where αi is known and positive constant. It is shown that how various exact non-parametric inferential proce- ′ dures can be developed on the basis of Mi’s and Mi ’s for distribution ...
متن کاملThe Effect of Supplementing a Novel n-3 Polyunsaturated Fatty Acids Formulation Containing Schisandra chinensis Extract and Vitamin D3 to a Group of Elite Sport Athletes on Competition Related Stress, Anxiety and Self-confidence
Background. Competitive sport has the potential for high levels of stress and anxiety that may affect performance and increase the risk of injuries. While benefits of pre-training assumption of N-3 polyunsaturated fatty acids are well known, poor data are available on Schisandra chinensis. Schisandra chinensis is a medicinal plant in use in Chinese medicine which increases physical working capa...
متن کاملThe Effect of Magnetic Water and Calcic And Potasic Zeolite on the Yield of Lepidium Sativum L.
The use of recent technologies for the increase of growth indexes and the plants yields is an important aspects and till now many research works for this has been done. One of these efforts is the usage of magnetic water and zeolite for the increase of yield plants. This research work is an study on the effects of magnetic water and zeolite that has been done on frame work of pore random design...
متن کاملThe Effect of Magnetic Water and Calcic And Potasic Zeolite on the Yield of Lepidium Sativum L.
The use of recent technologies for the increase of growth indexes and the plants yields is an important aspects and till now many research works for this has been done. One of these efforts is the usage of magnetic water and zeolite for the increase of yield plants. This research work is an study on the effects of magnetic water and zeolite that has been done on frame work of pore random design...
متن کاملSelf-Compassion and Pre- Competition Anxiety among Martial Arts Students
Objective: This study is an examination of the relationship between self-compassion, cognitive anxiety, somatic anxiety, and self-confidence as competitive state anxiety among female athletes Students. Methodology: The research method was descriptive-correlational. Two hundred and fifty-three female student (140 taekwondo and 113 karate) were selected among athletes present at the 14th Student ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2008