期望与方差

分布分布列或概率密度期望(E)方差(D)
0-1P{X=k}=pk(1p)1k,k=0,1P\{X=k\}=p^k(1-p)^{1-k},k=0,1ppp(1p)p(1-p)
二项 B(n,p)B(n,p)P{X=k}=Cnkpk(1p)nk,k=0,1,,nP\{X=k\}=C^k_np^k(1-p)^{n-k},k=0,1,\cdots,nnpnpnp(1p)np(1-p)
泊松 P(λ)P(\lambda)P{X=k}=λkk!eλ,k=0,1P\{X=k\}=\frac{\lambda^k}{k!}e^{-\lambda},k=0,1λ\lambdaλ\lambda
几何G(p)G(p)P{X=k}=(1p)k1p,k=1,2,P\{X=k\}=(1-p)^{k-1}p,k=1,2,\cdots1p\frac{1}{p}1pp2\frac{1-p}{p^2}
正态N(μ,σ2)N(\mu,\sigma^2)f(x)=12πσe(xμ)22σ2,<x<+f(x)=\frac{1}{\sqrt{2\pi}\sigma}e^{-\frac{(x-\mu)^2}{2\sigma^2}}, - \infty < x < + \inftyμ\muσ2\sigma^2
均匀U(a,b)U(a,b)f(x)=1ba,a<x<bf(x)=\frac{1}{b-a}, a<x<ba+b2\frac{a+b}{2}(ba)212\frac{(b-a)^2}{12}
指数E(λ)E(\lambda)f(x)=λeλx,x>0f(x)=\lambda e^{-\lambda x}, x>01λ\frac{1}{\lambda}1λ2\frac{1}{\lambda^2}

Cov(X,Y)=E[(XEX)(YEY)]=E(XY)EXEYCov(X,Y)=E[(X-EX)(Y-EY)]=E(XY)-EX\cdot EY

ρ=Cov(X,Y)DXDY\rho=\frac{Cov(X,Y)}{\sqrt{DX}\sqrt{DY}}

ρXY=0\rho_{XY}=0 则 XY 不相关

ρXY0\rho_{XY} \ne 0 则 XY 相关