嗨:我没有遵循整个事情(甚至没有接近。术语对我不起作用)但是您可能错误地解释了 n 规则的平方根。n规则的平方根实际上意味着以下统计。
假设我有一个正态分布的随机变量 $x$,其 sd 已知为 $\sigma_{x}$。(注意我说 $\sigma$ 是已知的而不是估计的)并且已知的意思是什么(把它当作零,但没关系)。所以
$x_{i}$s 来自均值为零和 sd $\sigma_{x}$ 的正态分布。x whose sd was known to be σx. ( notice I said σ is known and not estimated ) and known mean whatever ( take it as zero but it doesn't matter ). So
xis come from the normal distribution with mean zero and sd σx.
实验:生成 $n~ x_{i}$'s 并计算平均值:$\bar{x}_{1}$。同样,生成 $n~ x_{i}$'s 并计算平均 $\bar{x}_{2}$。重复这样做 $N$ 次,得到 $N$ 个随机变量,$\bar{x}_{i}, \ldots \bar{x}_{N}$ 每个都是 $N$ 的平均值n$ 观察。n xi's and calculate the average: x¯1.
Again, generate n xi's and calculate the average x¯2.
Do this over and over say N times so you get N random variables, x¯i,…x¯N each of which is an average of n observations.
然后,正确的“n 的平方根”语句是 $\bar{x}_{i}$(其中有 N 个,但现在可以认为它们来自一个群体)具有正态分布与原始平均值相同的平均值(因此为零)和标准差 $\frac{\sigma_{x}}{\sqrt{n}}$x¯i ( there are N of them but now one can think of them as coming from a population ) have a normal distribution with the same mean as the original mean ( so zero ) and standard deviation σxn√
混淆可能源于这样一个事实,即使用 CLT 得出相同结论的该语句的变体,但 CLT 需要较大的 n 以确保收敛,并且一旦您需要 CLT,事情就会变得更加模糊,这就是您误解的地方(如果有的话)可能来自。
如果 $\sigma_{x}$ 已知并且基础分布是正态的,则不需要 CLT 作为假设,并且此陈述是事实并且与 $n$ 的值无关(CLT 版本需要大 n 并且不需要假设 $\sigma_{x}$ 已知,因此您需要假设 $\sigma_{x}$ 的估计值已收敛到真实值)。您可以在 matlab 或 R 中尝试实验并亲自查看。如果我有时间,我会在 R 中展示它,但我没有。σx is known and the underlying distribution is
normal, then the CLT is not needed as an assumption and this statement is fact and independent of the value of n ( CLT versions need large n and don't assume σx known so you need to assume that the estimated value of σx has converged to the true one ). You can try the experiment out in matlab or R and see for yourself. If I had time, I'd show it in R but I don't.
就像我说的,我不关注你在做什么,但这可能就是奇怪的来源。我希望这有帮助。