让ÿ
直观地说,因为态假设的,是有意义的要求是Ë (Ÿ | ˉ X = ˉ X)= ˉ X
我最初的想法是使用条件正态分布来解决此问题,这通常是已知的结果。那里的问题是,由于我不知道期望值,因此也不知道中位数的方差,因此我将不得不使用k + 1
让ÿ
直观地说,因为态假设的,是有意义的要求是Ë (Ÿ | ˉ X = ˉ X)= ˉ X
我最初的想法是使用条件正态分布来解决此问题,这通常是已知的结果。那里的问题是,由于我不知道期望值,因此也不知道中位数的方差,因此我将不得不使用k + 1
Answers:
让X表示原始样品和Ž随机矢量的条目Ž ķ = X ķ - ˉ X。然后Z以法线为中心(但其项不是独立的,从它们的总和为零(很有可能)可以看出)。作为线性功能的X,载体(Ž ,ˉ X)是正常的,因此它的协方差矩阵就足够的计算表明ž是独立的ˉ X。
转到ÿ,人们可以看出Ŷ = ˉ X + Ť其中Ť是的中值Ž。特别是,Ť取决于Ž只因此Ť是独立的ˉ X,和分布Ž是对称的,因此Ť居中。
最后,È (ÿ | ˉ X)= ˉ X + È (Ť | ˉ X)= ˉ X + È (Ť )= ˉ X。
样本中位数是一个顺序统计量,并且具有非正态分布,因此样本中位数和样本均值(具有正态分布)的联合有限样本分布不会是双变量正态。借助近似,渐近地成立以下条件(请参阅此处的答案):
√Ñ [(ˉ X Ñ ý Ñ) - (μ v)] →大号N [(0 0),Σ ]
与
Σ=(σ2E(|X−v|)[2f(v)]−1E(|X−v|)[2f(v)]−1[2f(v)]−2)
where ˉXn
So approximately for large samples, their joint distribution is bivariate normal, so we have that
E(Yn∣ˉXn=ˉx)=v+ρσvσˉX(ˉx−μ)
where ρ
Manipulating the asymptotic distribution to become the approximate large-sample joint distribution of sample mean and sample median (and not of the standardized quantities), we have ρ=1nE(|X−v|)[2f(v)]−11nσ[2f(v)]−1=E(|X−v|)σ
So E(Yn∣ˉXn=ˉx)=v+E(|X−v|)σ[2f(v)]−1σ(ˉx−μ)
We have that 2f(v)=2/σ√2π
E(Yn∣ˉXn=ˉx)=v+√π2E(|X−μσ|)(ˉx−μ)
where we have used v=μ
E(Yn∣ˉXn=ˉx)=v+√π2√2π(ˉx−μ)=v+ˉx−μ=ˉx
The answer is ˉx
Let x=(x1,x2,…,xn)
PrF(x−ˉx∈E)=PrF(x−ˉx∈−E).
Applying the generalized result at /stats//a/83887 shows that the median of x−ˉx
Now since subtracting the same value ˉx
This is simpler than the above answers make it. The sample mean is a complete and sufficient statistic (when the variance is known, but our results do not depend on the variance, hence will be valid also in the situation when the variance is unknown). Then the Rao-Blackwell together with the Lehmann-Scheffe theorems (see wikipedia ...) will imply that the conditional expectation of the median, given the arithmetic mean, is the unique minimum variance unbiased estimator of the expectation μ
We did also use that the median is an unbiased estimator, which follows from symmetry.