问一道题：NO.PZ2020011101000036

NO.PZ2020011101000036 问题如下 If asset hzero skewness, whis the maximum kurtosis it chave to not rejenormality with a sample size of 100 using a 5% test? Whif the sample size is 2,500? The Jarque-Bera hχ22\chi_2^2χ22​ stribution, anthe criticvalue for a test with a size of 5% is 5.99. The Jarque-Bera statistic isJB=(T−1)(S^2/6+(κ^−3)2/24)JB = (T - 1)(\wihS^2/6+(\wihat\kappa-3)^2/24) JB=(T−1)(S2/6+(κ−3)2/24)so thwhen the skewness S^=0\wihS = 0 S=0, the test statistic is (T−1)(κ^−3)2/24(T - 1)(\wihat\kappa-3)^2/24 (T−1)(κ−3)2/24.In orr to not rejethe null, we nee(T−1)(κ^−3)2/24(T - 1)(\wihat\kappa-3)^2/24 (T−1)(κ−3)2/24 ≤ 5.99anso (κ^−3)2≤24∗5.99/(T−1)(\wihat\kappa-3)^2 ≤ 24*5.99/(T-1) (κ−3)2≤24∗5.99/(T−1)anκ^≤3+24∗5.99/(T−1)\wihat\kappa ≤ 3+\sqrt {24*5.99/(T-1)} κ≤3+24∗5.99/(T−1)​.When T = 100, this value is 4.20. When T = 2,500 this value is 3.24. This shows ththe JB test statistic is sensitive to even milexcess kurtosis. 请问为什么自由度不是样本数量-1呢，之前第三章的时候一直都是用的样本个数-1

\"This shows ththe JB test statistic is sensitive to even milexcess kurtosis.\"这句话怎么理解？