这是一个有趣的数据集。遵循@whuber 的建议并在对数尺度上进行分析似乎是个好主意。然而,这里有不止一个假设。因为你可以有假设
H0:samples 1-5 have the same mean and variance on the log scale,
and this is different from the control mean
但你也可以有:
H1:samples 1-3 have the same mean and variance on the log scale,
and this is different from the control mean, and samples 4-5 have
the same mean and variance but different from both control group
and samples 1-3
H1对我来说似乎是最合理的假设。您还可以拥有:
H2:samples 1-5 have different means and variances on the log
scale, and are different from the control group
这些假设中的每一个,如果为真,都将构成某种“重要”结果。无论如何,一旦你确定它们不同,兴趣就会转移到说“好吧,它们到底有什么不同?”
我认为您的结果不太重要,因为您正在测试具有许多参数H2
对于,我们的为和,显示出明显的差异,behrens Fisher 统计量为
H0mean±standard dev5.0±0.623.8±0.22
T=5.0−3.80.62215+0.2222−−−−−−−−−√=5.39
两个样本的 T 统计量约为,但数据不支持方差相等的假设,特别是因为对照组是迄今为止最低的方差,几乎是合并样本方差的三倍。2.64
更多稍后,因为我现在必须停下来......