Summary of Special Probability Distributions Continuous Probability Distributions Distribution
Parameters a, b
Uniform on [a, b]
µ, σ
Normal
λ
Exponential
λ, r
Gamma
n
Chi-square
Density Function 1 f ( x) = , a≤ x≤b b−a
f ( x) =
1 e σ 2π
( x − µ )2 − 2σ 2
Mean µ=
f ( x) =
Γ (r )
b+a . 2
µ=
x r −1e − λ x , x > 0
µ=
n −1 1 f ( x ) = n 2 n x 2 e− x 2 , x > 0 2 Γ( 2 )
(b − a )
σ2 =
µ
, −∞ < x < ∞
f ( x ) = λ e − λ x if x ≥ 0
λr
Variance
12
2
Moment Generating Function etb − eta , t ≠ 0. M (t ) = (b − a ) t
M (t ) = e
σ2 1
σ2 =
λ r
σ2 =
λ
µ=n
1
λ
M X (t ) =
.
λ
, t<λ λ −t r ⎛ λ ⎞ M (t ) = ⎜ ⎟ , t<λ ⎝ λ −t ⎠
2
r
λ2
σ 2 = 2n
1 2
µ t + σ 2t 2
⎛ 1 ⎞ M (t ) = ⎜ 1 2 ⎟ ⎝ 2 −t ⎠
n2
=
1
(1 − 2t )
n2
, t<
1 2
Discrete Probability Distributions Distribution Binomial Negative Binomial Geometric Poisson
Parameters n, p k, p
p
λ
Mass Function ⎛n⎞ n− x f ( x ) = ⎜ ⎟ p x (1 − p ) , x = 0, 1, 2, …, n ⎝ x⎠ ⎛ x − 1⎞ k x−k f ( x) = ⎜ ⎟ p (1 − p ) , ⎝ k − 1⎠ x = k , k + 1, k + 2, … .
f ( x ) = p (1 − p ) f ( x ) = e− λ
λx x!
x −1
, x = 1, 2, 3, …
, x = 0, 1, 2, …
Mean
Variance
µ = np
σ 2 = np (1 − p )
k µ= p
k (1 − p ) σ = p2
µ=
1 p
µ =λ
2
σ2 =
1− p p2
σ2 =λ
Moment Generating Function
(
M ( t ) = 1 + p ( et − 1)
M X (t ) =
( pe )
t k
⎡⎣1 − (1 − p ) et ⎤⎦
M X (t ) =
k
)
n
, t < − ln (1 − p )
pet , t < − ln (1 − p ) 1 − (1 − p ) et
M ( t ) = exp ⎡⎣λ ( et − 1) ⎤⎦