更新:推导已补充
离散型分布
两点分布 X ∼ B ( 1 , p ) X \sim B(1,p) X∼B(1,p)
随机变量X只能取值0和1,且服从参数为P的(0-1)分布,对应一次伯努利试验. (相当于随机变量取值限制的二项分布)
其分布律为:
P { X = k } = p k ( 1 − p ) 1 − k , k = 0 , 1 ; P\{X=k\} = p^k (1-p)^{1-k}, k=0,1; \ \ \ \ \ P{ X=k}=pk(1−p)1−k,k=0,1;
其数学期望为: E ( X ) = p E(X) = p E(X)=p
方差为: D ( X ) = p ( 1 − p ) D(X) = p(1-p) D(X)=p(1−p)
推导:
E ( X ) = 0 + 1 ⋅ p 1 ( 1 − p ) 0 = p E(X) = 0 + 1\cdot p^1(1-p)^0 = p E(X)=0+1⋅p1(1−p)0=p
D ( X ) = E ( x 2 ) − [ E ( x ) ] 2 = = ( 1 − p ) ( 0 − p ) 2 + p ( 1 − p ) 2 = p − p 2 D(X) = E(x^2) - [E(x)]^2 ==(1-p)(0-p)^2+p(1-p)^2 = p - p^2 D(X)=E(x2)−[E(x)]2==(1−p)(0−p)2+p(1−p)2=p−p2
二项分布 X ∼ B ( n , p ) X \sim B(n,p) X∼B(n,p)
随机变量X的所有可能取值为: 0 , 1 , 2... , n 0,1,2...,n 0,1,2...,n ,而各取值的概率为:
P { X = k } = C n k p k q n − k , k = 0 , 1 , 2 , . . . , n P\{X=k\} = C_n^k p^k q^{n-k}, \;\; k = 0,1,2,...,n P{ X=k}=Cnkpkqn−k,k=0,1,2,...,n
其中, 0
其数学期望为: E ( X ) = n p E(X) = np E(X)=np
方差为: D ( X ) = n p ( 1 − p ) D(X) = np(1-p) D(X)=np(1−p)
推导:
KaTeX parse error: Mismatch: \begin{aligned} matched by \end{align} at position 193: …+p)^{n-1} = np \̲e̲n̲d̲{align}
E ( X 2 ) = ∑ k = 0 n k 2 C n k p k ( 1 − p ) n − k = n p ∑ k = 1 n k C n − 1 k − 1 p k − 1 ( 1 − p ) n − k = n p ∑ k = 0 n − 1 ( k + 1 ) C n − 1 k p k ( 1 − p ) n − k − 1 = n p ∑ k = 1 n − 1 k C n − 1 k p k ( 1 − p ) n − k + n p = n ( n − 1 ) p 2 ∑ k = 1 n − 1 C n − 2 k − 1 p k − 1 ( 1 − p ) n − 1 − k = n ( n − 1 ) p 2 + n p D ( X ) = E ( X 2 ) − E 2 ( X ) = n p [ ( n − 1 ) p + 1 ] − n 2 p 2 = n p ( 1 − p ) \begin{aligned} E(X^2) &= \sum^n_{k=0} k^2 C_n^k p^k(1-p)^{n-k} \\ &=np\sum^n_{k=1} k C_{n-1}^{k-1} p^{k-1}(1-p)^{n-k} =np\sum^{n-1}_{k=0} (k+1) C_{n-1}^{k} p^k(1-p)^{n-k-1}\\ &= np\sum^{n-1}_{k=1}kC^k_{n-1}p^k(1-p)^{n-k}+np\\ &= n(n-1)p^2\sum^{n-1}_{k=1}C^{k-1}_{n-2}p^{k-1}(1-p)^{n-1-k}=n(n-1)p^2+np \\ D(X) &= E(X^2) - E^2(X)= np[(n-1)p+1] - n^2p^2= np(1-p) \end{aligned} E(X2)D(X)=k=0∑nk2Cnkpk(1−p)n−k=npk=1∑nkCn−1k−1pk−1(1−p)n−k=npk=0∑n−1(k+1)Cn−1kpk(1−p)n−k−1=npk=1∑n−1kCn−1kpk(1−p)n−k+np=n(n−1)p2k=1∑n−1Cn−2k−1pk−1(1−p)n−1−k=n(n−1)p2+np=E(X2)−E2(X)=np[(n−1)p+1]−n2p2=np(1−p)
由于二项分布对应n重独立的伯努利试验,相当于n个两点分布的叠加,因此有:
E B ( X ) = E 0 − 1 ( n X ) = n E 0 − 1 ( X ) = n p E_B(X) = E_{0-1}(nX) = nE_{0-1}(X)=np EB(X)=E0−1(nX)=nE0−1(X)=np
D B ( X ) = D 0 − 1 ( n X ) = n p ( 1 − p ) D_B(X) = D_{0-1}(nX)=np(1-p) DB(X)=D0−1(nX)=np(1−p)
几何分布 X ∼ G ( p ) X\sim G(p) X∼G(p)
分布律为:
P { X = k } = p ( 1 − q ) k − 1 , k = 1 , 2 , 3... , p ∈ ( 0 , 1 ] P\{X=k\} = p(1-q)^{k-1}, k=1,2,3..., p\in (0,1] P{ X=k}=p(1−q)k−1,k=1,2,3...,p∈(0,1]
其数学期望与方差为:
E ( X ) = 1 p , D ( X ) = 1 − p p 2 E(X) = \frac1p,\ \ \ D(X) = \frac{1-p}{p^2} E(X)=p1, D(X)=p21−p
推导<1>:
E ( X ) = lim n → ∞ ∑ k = 1 n k p ( 1 − p ) k − 1 , ( 1 − p ) E ( X ) = lim n → ∞ ∑ k = 1 n k p ( 1 − p ) k ⇒ p E ( X ) = lim n → ∞ [ p ∑ k = 1 n [ ( k − 1 ) ( 1 − p ) k − 1 − k ( 1 − p ) k ] + p ∑ k = 1 n ( 1 − p ) k − 1 ] E ( X ) = lim n → ∞ [ − n ( 1 − p ) n + ( 1 − p ) n − 1 ( 1 − p ) − 1 ] = lim n → ∞ 1 p [ 1 − ( 1 − p ) n ( 1 + n p ) ] = 1 p \begin{aligned} &E(X)=\lim_{n\to \infty}\sum^n_{k=1}kp(1-p)^{k-1}, \ \ (1-p)E(X)=\lim_{n\to \infty}\sum^n_{k=1}kp(1-p)^{k }\\ &\Rightarrow pE(X)= \lim_{n\to \infty}[p\sum^n_{k=1}[(k-1)(1-p)^{k-1} -k(1-p)^k]+p\sum^n_{k=1}(1-p)^{k-1}] \\ &E(X)=\lim_{n\to \infty}[-n(1-p)^n+\frac{(1-p)^n-1}{(1-p)-1}]=\lim_{n\to \infty}\frac1p [1-(1-p)^n(1+np)] = \frac1p \end{aligned} E(X)=n→∞limk=1∑nkp(1−p)k−1, (1−p)E(X)=n→∞limk=1∑nkp(1−p)k⇒pE(X)=n→∞lim[pk=1∑n[(k−1)(1−p)k−1−k(1−p)k]+pk=1∑n(1−p)k−1]E(X)=n→∞lim[−n(1−p)n+(1−p)−1(1−p)n−1]=n→∞limp1[1−(1−p)