1 概率
- 古典概型和几何概型
- 古典概型(有限等可能)
- 几何概型(无限等可能)
- 条件概率
P ( A ∣ B ) = P ( A B ) P ( B ) P(A|B) = \frac{P(AB)}{P(B)} P(A∣B)=P(B)P(AB)
- 全概率公式
P ( B ) = ∑ i = 1 n P ( A i ) P ( B ∣ A i ) P(B) = \sum \limits_{i = 1}^n P(A_i)P(B|A_i) P(B)=i=1∑nP(Ai)P(B∣Ai)
- 贝叶斯公式:根据先验概率计算后验概率
P ( H ∣ E ) = P ( H ) P ( E ∣ H ) P ( E ) P ( B i ∣ A ) = P ( B i ) P ( A ∣ B i ) ∑ i P ( B i ) P ( A ∣ B i ) P ( H i ∣ E 1 E 2 ⋯ E m ) = P ( E 1 ∣ H i ) P ( E 2 ∣ H i ) ⋯ P ( E m ∣ H i ) P ( H i ) ∑ j = 1 n P ( E 1 ∣ H j ) P ( E 2 ∣ H j ) ⋯ P ( E m ∣ H j ) P ( H j ) P(H|E) = \frac{P(H)P(E|H)}{P(E)} \\ P(B_i | A) = \frac{P(B_i)P(A|B_i)}{\sum_i P(B_i) P(A|B_i)} \\ P(H_i | E_1E_2 \cdots E_m) = \frac{P(E_1|H_i)P(E_2|H_i) \cdots P(E_m|H_i)P(H_i)}{\sum \limits_{j = 1}^n P(E_1|H_j)P(E_2|H_j) \cdots P(E_m|H_j)P(H_j)} P(H∣E)=P(E)P(H)P(E∣H)P(Bi∣A)=∑iP(Bi)P(A∣Bi)P(Bi)P(A∣Bi)P(Hi∣E1E2⋯Em)=j=1∑nP(E1∣Hj)P(E2∣Hj)⋯P(Em∣Hj)P(Hj)P(E1∣Hi)P(E2∣Hi)⋯P(Em∣Hi)P(Hi)
- 先验概率和后验概率
- 先验概率:事情未发生,根据以往数据分析得到的概率
- 后验概率:事情已发生,这件事情发生的原因是由某个因素引起的概率。 P ( B i ∣ A ) P(B_i|A) P(Bi∣A) 中 B i B_i Bi 为某个因素, A A A 为已经发生的结果
2 离散随机变量及分布
X X X 的概率分布函数:
- 两点分布(01分布) X ∼ B ( 1 , p ) X \thicksim B(1, p) X∼B(1,p)
P ( X = 0 ) = 1 − p P ( X = 1 ) = p p ∈ ( 0 , 1 ) P(X = 0) = 1 - p \\ P(X = 1) = p \\ p \in (0,1) P(X=0)=1−pP(X=1)=pp∈(0,1)
- 二项分布(伯努利分布) X ∼ B ( n , p ) X \thicksim B(n, p) X∼B(n,p)
P ( X = k ) = C n k p k ( 1 − p ) n − k p ∈ ( 0 , 1 ) , k = 0 , 1 , 2 , ⋯ , n P(X = k) = C_n^k p^k (1 - p)^{n - k} \hspace{1em} p \in (0,1), k = 0,1,2,\cdots, n P(X=k)=Cnkpk(1−p)n−kp∈(0,1),k=0,1,2,⋯,n
- 泊松分布 X ∼ P ( λ ) X \thicksim P(\lambda) X∼P(λ)
P ( X = k ) = λ k e − λ k ! λ > 0 , k = 0 , 1 , 2 , ⋯ P(X = k) = \frac{\lambda ^ k e ^{- \lambda}}{k!} \hspace{1em} \lambda \gt 0, k = 0,1,2,\cdots P(X=k)=k!λke−λλ>0,k=0,1,2,⋯
- 几何分布 X ∼ G ( p ) X \thicksim G(p) X∼G(p)
P ( X = k ) = ( 1 − p ) k − 1 p p ∈ ( 0 , 1 ) , k = 1 , 2 , ⋯ P(X = k) = (1 - p) ^ {k - 1} p \hspace{1em} p \in (0, 1), k = 1, 2, \cdots P(X=k)=(1−p)k−1pp∈(0,1),k=1,2,⋯
- 超几何分布 X ∼ h ( n , N , M ) X \thicksim h(n, N, M)