假设检验是体育统计中的重要方法,但检验的可靠性往往受制于数据的数量.从理论和实验两个方面分析了检验的可靠性(检验功效)与样本量的关系.在此基础上,提出了单样本和双样本的改进SMOTE算法,以此来增加样本量,进而提高小样本体育数据假设检验结果的可靠性.最后通过小样本体育数据的假设检验实例结果验证了所提方法的有效性.%Hypothesis test is an important technique in sports statistical analysis ,but the reliability of its results is often subject to the size of data .In this paper ,the relationship between the reliability and the sample size is analyzed from the perspectives of theory and experiment .On this basis , the improved SMOTE algorithm of one set and paired sets is proposed to increase the sample size in order to promote the reliability of small sample-sized sports data hypothesis test .The results on two real sports data sets show the effectiveness of the proposed method .
展开▼