问题描述
设总体 X ∼ U [ 0 , θ ] X\sim U[0,\,\theta] X∼U[0,θ] , 其中 θ > 0 \theta >0 θ>0 , X 1 , X 2 , ⋯ , X n X_1,\,X_2,\cdots,X_n X1,X2,⋯,Xn 为其样本,
(1) 求 θ \theta θ 的矩估计量 θ 1 ^ \hat{\theta_1} θ1^ 和最大似然估计量 θ 2 ^ \hat{\theta_2} θ2^
(2) 求 E ( θ 1 ^ ) E(\hat{\theta_1}) E(θ1^) 和 E ( θ 2 ^ ) E(\hat{\theta_2}) E(θ2^)
题解
解析
关于 F θ 2 ^ ( x ) = [ F ( x ) ] n F_{\hat{\theta_2}}(x)=[F(x)]^n Fθ2^(x)=[F(x)]n 怎么得来 ?
首先 , F θ 2 ^ ( x ) = P { θ 2 ^ ≤ x } = P { m a x { X 1 , X 2 , ⋯ , X n } ≤ x } = λ F_{\hat{\theta_2}}(x)=P\{\hat{\theta_2}\leq x\}=P\{max\{X_1,X_2,\cdots,X_n\}\leq x\} = \lambda Fθ2^(x)=P{θ2^≤x}=P{max{X1,X2,⋯,Xn}≤x}=λ
∵ \because ∵ 最大值比 x x x 小 , 所以所有 X i X_i Xi 都比 x x x 小, 又因为 X i X_i Xi 之间相互独立,
∴ \therefore ∴ λ = P { X 1 < = x } × P { X 2 < = x } × ⋯ × P { X n < = x } = [ F ( x ) ] n \lambda = P\{ X_1<=x \}\times P\{ X_2<=x \}\times\cdots \times P\{ X_n<=x \}=[F(x)]^n λ=P{X1<=x}×P{X2<=x}×⋯×P{Xn<=x}=[F(x)]n