Inleiding Mathematische Statistiek 2025 September 2, 2025

Author: Alexander Dürre

Handbook of distributions

1 Discrete random variables with bounded support

Discrete uniform distribution
Parameters a, b ∈ Z with a < b, define n = b − a + 1
J {a, a + 1, . . . , b − 1, b}
1
f (x) n I[x ∈ J]

0 x<a


⌊x⌋−a+1
F (x) n a≤x≤b


1 x>b
a+b
E(X) 2
n2 −1
Var(X) 12
R ddunif(x,a,b), pdunif(x,a,b), rdunif(m,a,b) [extradistr]

Uniform distribution, a=1, different b

b=3
0.30

b=5
b=7
0.20
f(x)

0.10
0.00

1 2 3 4 5 6 7 8

Bernoulli distribution

Bernoulli distribution with different p

Parameters p ∈ [0, 1]
1.0

J {0, 1} p=1/4
(
1−p x=0 p=1/2
0.8

f (x) p=2/3
p x=1
0.6


0 x<0
f(x)



F (x)
0.4

1−p 0≤x<1


1 x≥1
0.2

E(X) p
0.0

Var(X) p(1 − p)
R dbinom(x,1,p), pbinom(x,1,p), rbinom(m,1,p)
0 1

1
Binomial distribution
Parameters n ∈ N0 , p ∈ [0, 1]
J {0, . . . , n}
n x

n−x
f (x) x p (1 − p)
F (x) complicated
E(X) np
Var(X) np(1 − p)
R dbinom(x,n,p), pbinom(x,n,p), rbinom(m,n,p)

Binomial distribution with n=10 Binomial distribution with p=0.5

and different p and different n
1.0

1.0
p=1/4 n=5
p=1/2 n=10
0.8

0.8
p=2/3 n=20
0.6

0.6
f(x)

f(x)
0.4

0.4
0.2

0.2
0.0

0.0

0 2 4 6 8 10 0 5 10 15 20

x x

Hypergeometric distribution
Parameters N, K, n ∈ N0 with K, n < N
J {max(0, n + K − N ), . . . , min(n, K)}
−K
(Kk )(Nn−k )
f (x) N
(n)
F (x) complicated
nK
E(X) N
N −K N −n
Var(X) nKN N N −1
R dhyper(x,K,N-K,n), phyper(x,K,N-K,n), rhyper(x,K,N-K,n)
Hypergeometric distribution with Hypergeometric distribution with Hypergeometric distribution with
K=10, n=5 and different N N=20, n=5 and different K K=10, N=20 and different n
1.0

1.0

1.0

N=15 K=5 n=5

N=20 K=10 n=10
0.8

0.8

0.8

N=40 K=15 n=15

0.6

0.6

0.6
f(x)

f(x)

f(x)
0.4

0.4

0.4
0.2

0.2

0.2
0.0

0.0

0.0

0 2 4 6 8 10 0 2 4 6 8 10 0 2 4 6 8 10

x x x

Beta-binomial distribution
Parameters n ∈ N0 , α, β > 0
J {0, . . . , n}
n B(x+α,n−x+β)


f (x) x B(α,β) where B(x, y) denotes beta function
F (x) complicated
nα
E(X) α+β
nαβ(α+β+n)
Var(X) (α+β)2 (α+β+1)
R dbbinom(x,n,α, β), pbbinom(x,n,α, β), rbbinom(m,n,α, β) [extraDistr]

2
 Beta binomial distribution with Beta binomial distribution with Beta binomial distribution with
alpha=beta=1 and different n n=10, beta=2 and different alpha n=10, alpha=0.5 and different beta
1.0

1.0

1.0
n=5 alpha=1 beta=0.1
n=10 alpha=2 beta=0.5
0.8

0.8

0.8
n=20 alpha=4 beta=2
0.6

0.6

0.6
f(x)

f(x)

f(x)
0.4

0.4

0.4
0.2

0.2

0.2
0.0

0.0

0.0
0 5 10 15 20 0 2 4 6 8 10 0 2 4 6 8 10

x x x

2 Discrete random variables with unbounded support

Poisson distribution
Parameters λ>0
J N
λx e−λ
f (x) x!
F (x) complicated
E(X) λ
Var(X) λ
R dpois(x,λ), ppois(x,λ), rpois(m,λ)

Poisson distribution with different lambda

1.0

lambda=1
lambda=5
0.8

lambda=10
0.6
f(x)

0.4
0.2
0.0

0 5 10 15

Negative binomial distribution

Parameters r ∈ N, p ∈ [0, 1]
J N0
x+r−1


f (x) x (1 − p)x pr
F (x) complicated
r(1−p)
E(X) p
r(1−p)
Var(X) p2
R dnbinom(x,r,p), pnbinom(x,r,p), rnbinom(m,r,p)

3
 Negative binomial distribution with Negative binomial distribution with
p=0.5 and different r r=2 and different p
1.0

1.0
r=1 p=1/4
r=2 p=1/2
0.8

0.8
r=5 p=2/3
0.6

0.6
f(x)

f(x)
0.4

0.4
0.2

0.2
0.0

0.0
0 2 4 6 8 10 0 2 4 6 8 10

x x

Example: Geometric distribution

Parameters p ∈ (0, 1]
J N
f (x) (1 − p)x−1 p
(
0 x<1
F (x)
⌊x⌋
1 − (1 − p) x≥1
1
E(X) p
1−p
Var(X) p2
R dgeom(x+1,p), pgeom(x+1,p), rgeom(m,p)+1

Geometric distribution with different p

1.0

p=1/4
p=1/2
0.8

p=2/3
0.6
f(x)

0.4
0.2
0.0

0 5 10 15

2.1 Continuous random variables with bounded support

Rectangular distribution
Parameters a<b
J [a, b]
1
f (x) b−a

0 x<a


F (x) x−a
a≤x<b
 b−a

1 x≥b
a+b
E(X) 2
1
Var(X) − a)2
12 (b
R dunif(x,a,b), punif(x,a,b), runif(m,a,b)

4
 Rectangular distribution with a=0 and different b
2.0
b=1/2
b=1
1.5

b=3
f(x)

1.0
0.5
0.0

0 1 2 3 4 5

x
Triangular distribution
Parameters a<c<b
Triangular distribution with different a,b,c
J [a, b]

2(x−a)
2.0

 (b−a)(c−a)

 a≤x<c a=−4,c=−2,b=0
f (x) 2 a=−1,c=0,b=1
x=c
 b−a
1.5

a=−2,c=0,b=1
 2(b−x)

c<x<b
 (b−a)(b−c)
f(x)

1.0



0 x≤a
(x−a)2

a<x≤c


0.5

(b−a)(c−a)
F (x) (b−x)2


1 − (b−a)(b−c) c≤x<b
0.0



1 x≥b
a+b+c −4 −2 0 2
E(X) 3
a2 +b2 +c2 −ab−ac−bc
Var(X) 18 x
R dtriang(x,a,b,c), dtriang(x,a,b,c), dtriang(m,a,b,c) [extraDistr]

Beta distribution
Parameters α, β > 0
J [0, 1]
xα−1 (1−x)β−1
f (x) β(α,β) where β(x, y) denotes the Beta function
F (x) no easy expression
α
E(X) α+β
αβ
Var(X) (α+β)2 (α+β+1)
R dbeta(x,α, β, pbeta(x,α, β), rbeta(m,α, β)

Beta distribution with different Beta distribution with beta=1 and

alpha and beta different alpha
2.5

2.5

alpha=0.5,beta=0.5 alpha=0.5
alpha=1,beta=1 alpha=1
2.0

2.0

alpha=2,beta=2 alpha=2
1.5

1.5
f(x)

f(x)
1.0

1.0
0.5

0.5
0.0

0.0

0.0 0.2 0.4 0.6 0.8 1.0 0.0 0.2 0.4 0.6 0.8 1.0

x x

5
2.2 Continuous random variables with semi-infinite support
Exponential distribution
Parameters λ>0
J [0, ∞)
f (x) λe−λx
F (x) 1 − e−λx
1
E(X) λ
1
Var(X) λ2
R dexp(x,λ), pexp(x,λ), rexp(m,λ)

Exponential distribution with different lambda

2.0

lambda=1
lambda=2
1.5

lambda=5
f(x)

1.0
0.5
0.0

0 1 2 3 4 5

Gamma distribution
Parameters θ, k > 0
J (0, ∞)
x
f (x) 1
Γ(k)θ k
xk−1 e− θ
F (x) no easy expression
E(X) kθ
Var(X) kθ2
R dgamma(x,shape=k,scale=θ), pgamma(m,shape=k,scale=θ), rgamma(x,shape=k,scale=θ)

Gamma distribution with different k and theta

2.0

k=1,theta=1
k=1,theta=2
1.5

k=2,theta=1
k=2,theta=2
k=5,theta=2
f(x)

1.0
0.5
0.0

0 1 2 3 4 5 6

6
Beta prime distribution
Parameters α, β > 0
J [0, ∞)
xα−1 (1+x)−α−β
f (x) β(α,β) where β(x, y) denotes the Beta function
F (x) no easy expression
α
E(X) β−1 if β > 1
α(α+β−1)
Var(X) (β−2)(β−1)2 if β > 2
R dbetapr(x,α, β), pbetapr(x,α, β), rbetapr(m,α, β) [extraDistr]

Beta prime distribution with different alpha and beta

2.0

alpha=1,beta=1
alpha=2,beta=2
1.5

alpha=4,beta=4
alpha=1,beta=4
alpha=4,beta=1
f(x)

1.0
0.5
0.0

0 1 2 3 4 5 6

Chi-squared distribution
Parameters k∈N
J [0, ∞)
k x
f (x) k
1
x 2 −1 e− 2
2 2 Γ(k/2)
F (x) no easy expression
E(X) k
Var(X) 2k
R dchisq(x,k), pchisq(x,k), rchisq(m,k)

Chi−squared distribution with different k

1.0

k=1
k=2
0.8

k=3
k=5
0.6
f(x)

0.4
0.2
0.0

0 2 4 6 8 10

7
2.3 Example: F distribution
Parameters d1 , d2 > 0
J r ∞)
[0,
d
(d1 x)d1 d2 2
f (x) (d1 x+d2 )d1 +d2
/(xB(d1 /2, d2 /2)) where β(x, y) denotes the Betafunction
F (x) no easy expression
d2
E(X) d2 −2 if d2 > 2
2d22 (d1 +d2 −2)
Var(X) if d2 > 4
d1 (d2 −2)2 (d2 −4)
R df(x,d1 , d2 ), pf(x,d1 , d2 ), rf(m,d1 , d2 )

F distribution with different k1 and k2

1.0

k1=1,k2=1
k1=2,k2=2
0.8

k1=5,k2=5
k1=1,k2=5
0.6

k1=5,k2=1
f(x)

0.4
0.2
0.0

0 1 2 3 4 5 6

2.4 Example: Frechet distribution

Parameters α, s > 0, m ∈ R
J (m, ∞)
−α
α x−m −1−α −( x−m s )


f (x) s
 s e
0 x<m
F (x) x−m −α
e − ( s ) x≥m
E(X) m + sΓ(1 − α1 ) if α > 1 where Γ denotes the gamma function
Var(X) s2 (Γ(1 − α2 ) − [Γ(1 − α1 )]2 ) if α > 2
R dfrechet(x,α, m, s), pfrechet(x,α, m, s), rfrechet(m,α, m, s) [extraDistr]

Frechet distribution with different alpha and s

2.0

alpha=1,s=1
alpha=2,s=2
1.5

alpha=5,s=5
alpha=1,s=5
alpha=5,s=1
f(x)

1.0
0.5
0.0

0 1 2 3 4 5 6

8
 Kolmogorov distribution Log-normal distribution
Parameters - Parameters µ ∈ R, σ > 0
J [0, ∞) J (0, ∞)
(ln[x]−µ)2
f (x) no easy expression f (x) 1
√ e− 2σ 2
( xσ 2π
0 x≤0 F (x) no easy expression
F (x) P∞ 2 2 σ2
1 − 2 k=1 (−1)k+1 e−2k x x>0 E(X) eµ+ 2
2 2
E(X) no easy expression Var(X) (eσ − 1)e2µ+σ
Var(X) no easy expression R dlnorm(x,µ, σ), plnorm(x,µ, σ)
R pKSdist(x) [robcp] rlnorm(m,µ, σ) [extraDistr]

Log−normal distribution with different mu and sigma

1.0

mu=0,sigma=0.5
mu=0,sigma=1
0.8

mu=0,sigma=2
mu=1,sigma=1
0.6

mu=3,sigma=1
f(x)

0.4
0.2
0.0

0 1 2 3 4 5 6

Pareto distribution
Parameters xm , α > 0
J [xm , ∞)
αxα
f (x) m
(α+1
x
0 x ≤ xm
F (x) xm α


1− x x > xm
axm
E(X) α−1 if α > 1
x2m α
Var(X) (α−1)2 (α−2) if
α>2
R dpareto(x,α, xm ), ppareto(x,α, xm ), rpareto(m,α, xm ) [extraDistr]

Pareto distribution with different alpha and xm

1.0

alpha=0.5,xm=1
alpha=1,xm=1
0.8

alpha=2,xm=1
alpha=1,xm=2
0.6

alpha=1,xm=4
f(x)

0.4
0.2
0.0

1 2 3 4 5 6 7

9
Weibull distribution
Parameters λ, k > 0
J [0, ∞)
k x k−1 −(x/λ)k


f (x) λ λ e
(
0 x≤0
F (x) k
1 − e−(x/λ) x > 0
E(X) λΓ(1 + 1/k)
λ2 Γ(1 + k2 ) − [Γ(1 + k1 )]2


Var(X)
R dweibull(x,k,λ), pweibull(x,k,λ), dweibull(m,k,λ) [extraDistr]

Weibull distribution with different k and lambda

2.0

k=0.5,lambda=1
k=1,lambda=1
1.5

k=2,lambda=1
k=5,lambda=1
k=2,lambda=4
f(x)

1.0
0.5
0.0

0 1 2 3 4 5 6

2.5 Continuous random variables with unbounded support

Normal distribution
Parameters µ ∈ R, σ > 0
J R
2
1 (x−µ)
f (x) √ 1 e− 2 σ2
2πσ
F (x) Φ([x − µ]/σ) [no closed form]
E(X) µ
Var(X) σ2
R dnorm(x,µ, σ), pnorm(x,µ, σ), rnorm(m,µ, σ)

Normal distribution with different mu and sigma

1.0

mu=0,sigma=0.5
mu=0,sigma=1
0.8

mu=0,sigma=2
mu=2,sigma=1
0.6

mu=−2,sigma=1
f(x)

0.4
0.2
0.0

−4 −2 0 2 4

10
Exponential power distribution
Parameters µ ∈ R, α, β > 0
J (−∞, ∞)
β −(|x−µ|/α)β
f (x) 2αΓ(1/β) e
F (x) no easy expression
E(X) µ
α2 Γ(3/β)
Var(X) Γ(1β) where Γ denotes the gamma function
R dgnorm(x,µ, α, β), pgnorm(x,µ, α, β), rgnorm(m,µ, α, β) [gnorm]

Exponential power distribution with different mu, alpha and beta

1.0

mu=0,alpha=1,beta=0.5
mu=0,alpha=1,beta=1
0.8

mu=0,alpha=1,beta=2
mu=0,alpha=1,beta=5
0.6

mu=1,alpha=2,beta=1
f(x)

0.4
0.2
0.0

−4 −2 0 2 4

Gumbel distribution
Parameters µ ∈ R, β > 0
J (−∞, ∞)
x−µ
 
−
− x−µ
β +e
β
1
f (x) β e
−e−(x−µ)/β
F (x) e
E(X) µ + βγ where γ ≈ 0.577 (Euler-Mascheroni constant)
π2 2
Var(X) 6 β
R dgumbel(x,µ, β), pgumbel(x,µ, β), rgumbel(n,µ, β) [extraDistr]

Gumbel distribution with different mu and beta

1.0

mu=0,beta=0.5
mu=0,beta=1
0.8

mu=0,beta=2
mu=2,beta=1
0.6

mu=−2,beta=1
f(x)

0.4
0.2
0.0

−4 −2 0 2 4

11
Laplace distribution
Parameters µ ∈ R, b > 0
J (−∞, ∞)
|x−µ|
f (x) 1
2b e− b

1 x−µ
(
2e
b x≤µ
F (x) x−µ
1 − 12 e− b x>µ
E(X) µ
Var(X) 2b2
R dlaplace(x,µ,b), plaplace(x,µ,b), rlaplace(m,µ,b) [extraDistr]

Laplace distribution with different mu and b

1.0

mu=0,b=0.5
mu=0,b=1
0.8

mu=0,b=2
mu=2,b=1
0.6

mu=−2,b=1
f(x)

0.4
0.2
0.0

−4 −2 0 2 4

t distribution
Parameters µ ∈ R, ν, τ > 0
J (−∞, ∞)
Γ( ν+1
2 )

−(ν+1)/2
1 x−µ 2
f (x) ν √
Γ( 2 ) πντ
1 + ν τ where Γ denotes the gamma function
F (x) no easy expression
E(X) µ if ν > 1
ν
Var(X) τ 2 ν−2 if ν > 2
R dlst(x,ν, µ, τ ), plst(x,ν, µ, τ ), rlst(m,ν, µ, τ ) [extraDistr]

t distribution with different mu, nu and tau

0.5

mu=0,tau=1,nu=1
mu=0,tau=1,nu=3
0.4

mu=0,tau=1,nu=10
mu=2,tau=1,nu=3
0.3

mu=0,tau=2,nu=3
f(x)

0.2
0.1
0.0

−4 −2 0 2 4

12