Stat 5101 Notes: Brand Name Distributions

Charles J. Geyer

December 15, 2012

Contents
1 Discrete Uniform Distribution 2

2 General Discrete Uniform Distribution 2

3 Uniform Distribution 3

4 General Uniform Distribution 3

5 Bernoulli Distribution 4

6 Binomial Distribution 5

7 Hypergeometric Distribution 6

8 Poisson Distribution 7

9 Geometric Distribution 8

10 Negative Binomial Distribution 9

11 Normal Distribution 10

12 Exponential Distribution 12

13 Gamma Distribution 12

14 Beta Distribution 14

15 Multinomial Distribution 15

1
16 Bivariate Normal Distribution 18

17 Multivariate Normal Distribution 19

18 Chi-Square Distribution 21

19 Student’s t Distribution 22

20 Snedecor’s F Distribution 23

21 Cauchy Distribution 24

22 Laplace Distribution 25

1 Discrete Uniform Distribution

Abbreviation DiscUnif(n).

Type Discrete.

Rationale Equally likely outcomes.

Sample Space The interval 1, 2, . . ., n of the integers.

Probability Mass Function

1
f (x) = , x = 1, 2, . . . , n
n

Moments
n+1
E(X) =
2
2
n −1
var(X) =
12

2 General Discrete Uniform Distribution

Type Discrete.

Sample Space Any finite set S.

2
Probability Mass Function
1
f (x) = , x ∈ S,
n
where n is the number of elements of S.

3 Uniform Distribution
Abbreviation Unif(a, b).

Type Continuous.

Rationale Continuous analog of the discrete uniform distribution.

Parameters Real numbers a and b with a < b.

Sample Space The interval (a, b) of the real numbers.

Probability Density Function

1
f (x) = , a<x<b
b−a

Moments
a+b
E(X) =
2
(b − a)2
var(X) =
12

Relation to Other Distributions Beta(1, 1) = Unif(0, 1).

4 General Uniform Distribution

Type Continuous.

Sample Space Any open set S in Rn .

3
Probability Density Function
1
f (x) = , x∈S
c
where c is the measure (length in one dimension, area in two, volume in
three, etc.) of the set S.

5 Bernoulli Distribution
Abbreviation Ber(p).

Type Discrete.

Rationale Any zero-or-one-valued random variable.

Parameter Real number 0 ≤ p ≤ 1.

Sample Space The two-element set {0, 1}.

Probability Mass Function

(
p, x=1
f (x) =
1 − p, x = 0

Moments

E(X) = p
var(X) = p(1 − p)

Addition Rule If X1 , . . ., Xk are IID Ber(p) random variables, then

X1 + · · · + Xk is a Bin(k, p) random variable.

Degeneracy If p = 0 the distribution is concentrated at 0. If p = 1 the

distribution is concentrated at 1.

Relation to Other Distributions Ber(p) = Bin(1, p).

4
6 Binomial Distribution
Abbreviation Bin(n, p).

Type Discrete.

Rationale Sum of n IID Bernoulli random variables.

Parameters Real number 0 ≤ p ≤ 1. Integer n ≥ 1.

Sample Space The interval 0, 1, . . ., n of the integers.

Probability Mass Function

 
n x
f (x) = p (1 − p)n−x , x = 0, 1, . . . , n
x

Moments

E(X) = np
var(X) = np(1 − p)

Addition Rule If X1 , . . ., Xk are independent random variables, Xi being

Bin(ni , p) distributed, then X1 + · · · + Xk is a Bin(n1 + · · · + nk , p) random
variable.

Normal Approximation If np and n(1 − p) are both large, then

Bin(n, p) ≈ N np, np(1 − p)

Poisson Approximation If n is large but np is small, then

Bin(n, p) ≈ Poi(np)

Theorem The fact that the probability mass function sums to one is
equivalent to the binomial theorem: for any real numbers a and b
n  
X n k n−k
a b = (a + b)n .
k
k=0

5
Degeneracy If p = 0 the distribution is concentrated at 0. If p = 1 the
distribution is concentrated at n.

Relation to Other Distributions Ber(p) = Bin(1, p).

7 Hypergeometric Distribution
Abbreviation Hypergeometric(A, B, n).

Type Discrete.

Rationale Sample of size n without replacement from finite population of

B zeros and A ones.

Sample Space The interval max(0, n − B), . . ., min(n, A) of the integers.

Probability Mass Function

A

B

x n−x
f (x) = A+B

, x = max(0, n − B), . . . , min(n, A)
n

Moments

E(X) = np
N −n
var(X) = np(1 − p) ·
N −1

where

A
p= (7.1)
A+B
N =A+B

Binomial Approximation If n is small compared to either A or B, then

Hypergeometric(n, A, B) ≈ Bin(n, p)

where p is given by (7.1).

6
Normal Approximation If n is large, but small compared to either A
or B, then

Hypergeometric(n, A, B) ≈ N np, np(1 − p)
where p is given by (7.1).

Theorem The fact that the probability mass function sums to one is
equivalent to
min(A,n)     
X A B A+B
=
x n−x n
x=max(0,n−B)

8 Poisson Distribution
Abbreviation Poi(µ)

Type Discrete.

Rationale Counts in a Poisson process.

Parameter Real number µ > 0.

Sample Space The non-negative integers 0, 1, . . . .

Probability Mass Function

µx −µ
f (x) = e , x = 0, 1, . . .
x!

Moments

E(X) = µ
var(X) = µ

Addition Rule If X1 , . . ., Xk are independent random variables, Xi being

Poi(µi ) distributed, then X1 +· · ·+Xk is a Poi(µ1 +· · ·+µk ) random variable.

Normal Approximation If µ is large, then

Poi(µ) ≈ N (µ, µ)

7
Theorem The fact that the probability mass function sums to one is
equivalent to the Maclaurin series for the exponential function: for any
real number x
∞
X xk
= ex .
k!
k=0

9 Geometric Distribution
Abbreviation Geo(p).

Type Discrete.

Rationales

• Discrete lifetime of object that does not age.

• Waiting time or interarrival time in sequence of IID Bernoulli trials.

• Inverse sampling.

• Discrete analog of the exponential distribution.

Parameter Real number 0 < p ≤ 1.

Sample Space The non-negative integers 0, 1, . . . .

Probability Mass Function

f (x) = p(1 − p)x x = 0, 1, . . .

Moments
1−p
E(X) =
p
1−p
var(X) =
p2

Addition Rule If X1 , . . ., Xk are IID Geo(p) random variables, then

X1 + · · · + Xk is a NegBin(k, p) random variable.

8
Theorem The fact that the probability mass function sums to one is
equivalent to the geometric series: for any real number s such that |s| < 1
∞
X 1
sk = .
1−s
k=0

Degeneracy If p = 1 the distribution is concentrated at 0.

10 Negative Binomial Distribution

Abbreviation NegBin(r, p).

Type Discrete.

Rationale
• Sum of IID geometric random variables.

• Inverse sampling.

• Gamma mixture of Poisson distributions.

Parameters Real number 0 < p ≤ 1. Integer r ≥ 1.

Sample Space The non-negative integers 0, 1, . . . .

Probability Mass Function

 
r+x−1 r
f (x) = p (1 − p)x , x = 0, 1, . . .
x

Moments
r(1 − p)
E(X) =
p
r(1 − p)
var(X) =
p2

Addition Rule If X1 , . . ., Xk are independent random variables, Xi being

NegBin(ri , p) distributed, then X1 + · · · + Xk is a NegBin(r1 + · · · + rk , p)
random variable.

9
Normal Approximation If r(1 − p) is large, then
 
r(1 − p) r(1 − p)
NegBin(r, p) ≈ N ,
p p2

Degeneracy If p = 1 the distribution is concentrated at 0.

Extended Definition The definition makes sense for noninteger r if bi-

nomial coefficients are defined by
 
r r · (r − 1) · · · (r − k + 1)
=
k k!

which for integer r agrees with the standard definition.

Also    
r+x−1 x −r
= (−1) (10.1)
x x
which explains the name “negative binomial.”

Theorem The fact that the probability mass function sums to one is
equivalent to the generalized binomial theorem: for any real number
s such that −1 < s < 1 and any real number m
∞  
X m k
s = (1 + s)m . (10.2)
k
k=0

If m is a nonnegative integer, then m

k is zero for k > m, and we get the
ordinary binomial theorem.
Changing variables from m to −m and from s to −s and using (10.1)
turns (10.2) into
∞   ∞  
X m+k−1 X −m
k
s = (−s)k = (1 − s)−m
k k
k=0 k=0

which has a more obvious relationship to the negative binomial density sum-
ming to one.

11 Normal Distribution
Abbreviation N (µ, σ 2 ).

10
Type Continuous.

Rationale
• Limiting distribution in the central limit theorem.
• Error distribution that turns the method of least squares into maxi-
mum likelihood estimation.

Parameters Real numbers µ and σ 2 > 0.

Sample Space The real numbers.

Probability Density Function

1 2 2
f (x) = √ e−(x−µ) /2σ , −∞ < x < ∞
2πσ

Moments
E(X) = µ
var(X) = σ 2
E{(X − µ)3 } = 0
E{(X − µ)4 } = 3σ 4

Linear Transformations If X is N (µ, σ 2 ) distributed, then aX + b is

N (aµ + b, a2 σ 2 ) distributed.

Addition Rule If X1 , . . ., Xk are independent random variables, Xi being

N (µi , σi2 ) distributed, then X1 + · · · + Xk is a N (µ1 + · · · + µk , σ12 + · · · + σk2 )
random variable.

Theorem The fact that the probability density function integrates to one
is equivalent to the integral
Z ∞
2 √
e−z /2 dz = 2π
−∞

Relation to Other Distributions If Z is N (0, 1) distributed, then Z 2

is Gam( 12 , 21 ) = chi2 (1) distributed. Also related to Student t, Snedecor F ,
and Cauchy distributions (for which see).

11
12 Exponential Distribution
Abbreviation Exp(λ).

Type Continuous.

Rationales

• Lifetime of object that does not age.

• Waiting time or interarrival time in Poisson process.

• Continuous analog of the geometric distribution.

Parameter Real number λ > 0.

Sample Space The interval (0, ∞) of the real numbers.

Probability Density Function

f (x) = λe−λx , 0<x<∞

Cumulative Distribution Function

F (x) = 1 − e−λx , 0<x<∞

Moments
1
E(X) =
λ
1
var(X) = 2
λ

Addition Rule If X1 , . . ., Xk are IID Exp(λ) random variables, then

X1 + · · · + Xk is a Gam(k, λ) random variable.

Relation to Other Distributions Exp(λ) = Gam(1, λ).

13 Gamma Distribution
Abbreviation Gam(α, λ).

12
Type Continuous.

Rationales
• Sum of IID exponential random variables.
• Conjugate prior for exponential, Poisson, or normal precision family.

Parameter Real numbers α > 0 and λ > 0.

Sample Space The interval (0, ∞) of the real numbers.

Probability Density Function

λα α−1 −λx
f (x) = x e , 0<x<∞
Γ(α)
where Γ(α) is defined by (13.1) below.

Moments
α
E(X) =
λ
α
var(X) = 2
λ

Addition Rule If X1 , . . ., Xk are independent random variables, Xi being

Gam(αi , λ) distributed, then X1 +· · ·+Xk is a Gam(α1 +· · ·+αk , λ) random
variable.

Normal Approximation If α is large, then

 
α α
Gam(α, λ) ≈ N ,
λ λ2

Theorem The fact that the probability density function integrates to one
is equivalent to the integral
Z ∞
Γ(α)
xα−1 e−λx dx = α
0 λ
the case λ = 1 is the definition of the gamma function
Z ∞
Γ(α) = xα−1 e−x dx (13.1)
0

13
Relation to Other Distributions

• Exp(λ) = Gam(1, λ).

• chi2 (ν) = Gam( ν2 , 21 ).

• If X and Y are independent, X is Γ(α1 , λ) distributed and Y is Γ(α2 , λ)

distributed, then X/(X + Y ) is Beta(α1 , α2 ) distributed.

• If Z is N (0, 1) distributed, then Z 2 is Gam( 12 , 12 ) distributed.

Facts About Gamma Functions Integration by parts in (13.1) estab-

lishes the gamma function recursion formula

Γ(α + 1) = αΓ(α), α>0 (13.2)

The relationship between the Exp(λ) and Gam(1, λ) distributions gives

Γ(1) = 1

and the relationship between the N (0, 1) and Gam( 12 , 12 ) distributions gives
√
Γ( 12 ) = π

Together with the recursion (13.2) these give for any positive integer n

Γ(n + 1) = n!

and √
Γ(n + 12 ) = n − 1 3
· · · 32 · 1



2 n− 2 2 π

14 Beta Distribution
Abbreviation Beta(α1 , α2 ).

Type Continuous.

Rationales

• Ratio of gamma random variables.

• Conjugate prior for binomial or negative binomial family.

14
Parameter Real numbers α1 > 0 and α2 > 0.

Sample Space The interval (0, 1) of the real numbers.

Probability Density Function

Γ(α1 + α2 ) α1 −1
f (x) = x (1 − x)α2 −1 0<x<1
Γ(α1 )Γ(α2 )

where Γ(α) is defined by (13.1) above.

Moments
α1
E(X) =
α1 + α2
α1 α2
var(X) = 2
(α1 + α2 ) (α1 + α2 + 1)

Theorem The fact that the probability density function integrates to one
is equivalent to the integral
Z 1
Γ(α1 )Γ(α2 )
xα1 −1 (1 − x)α2 −1 dx =
0 Γ(α1 + α2 )

Relation to Other Distributions

• If X and Y are independent, X is Γ(α1 , λ) distributed and Y is Γ(α2 , λ)

distributed, then X/(X + Y ) is Beta(α1 , α2 ) distributed.

• Beta(1, 1) = Unif(0, 1).

15 Multinomial Distribution
Abbreviation Multi(n, p).

Type Discrete.

Rationale Multivariate analog of the binomial distribution.

15
Parameters Real vector p in the parameter space
k
( )
X
p ∈ Rk : 0 ≤ pi , i = 1, . . . , k, and pi = 1 (15.1)
i=1

(real vectors whose components are nonnegative and sum to one).

Sample Space The set of vectors

k
( )
X
S= x ∈ Zk : 0 ≤ xi , i = 1, . . . , k, and xi = n (15.2)
i=1

(integer vectors whose components are nonnegative and sum to n).

Probability Mass Function

k
 Y
n
f (x) = pxi i , x∈S
x
i=1

where  
n n!
= Qk
x i=1 xi !
is called a multinomial coefficient.

Moments

E(Xi ) = npi
var(Xi ) = npi (1 − pi )
cov(Xi , Xj ) = −npi pj , i 6= j

Moments (Vector Form)

E(X) = np
var(X) = nM

where

M = P − ppT

where P is the diagonal matrix whose vector of diagonal elements is p.

16
Addition Rule If X1 , . . ., Xk are independent random vectors, Xi being
Multi(ni , p) distributed, then X1 + · · · + Xk is a Multi(n1 + · · · + nk , p)
random variable.

Normal Approximation If n is large and p is not near the boundary of

the parameter space (15.1), then

Multi(n, p) ≈ N (np, nM)

Theorem The fact that the probability mass function sums to one is
equivalent to the multinomial theorem: for any vector a of real num-
bers
X n Y k
axi i = (a1 + · · · + ak )n
x
x∈S i=1

Degeneracy If a vector a exists such that Ma = 0, then var(aT X) = 0.

In particular, the vector u = (1, 1, . . . , 1) P
always satisfies Mu = 0, so
var(uT X) = 0. This is obvious, since uT X = ki=1 Xi = n by definition of
the multinomial distribution, and the variance of a constant is zero. This
means a multinomial random vector of dimension k is “really” of dimension
no more than k − 1 because it is concentrated on a hyperplane containing
the sample space (15.2).

Marginal Distributions Every univariate marginal is binomial

Xi ∼ Bin(n, pi )

Not, strictly speaking marginals, but random vectors formed by col-

lapsing categories are multinomial. If A1 , . . ., Am is a partition of the set
{1, . . . , k} and
X
Yj = Xi , j = 1, . . . , m
i∈Aj
X
qj = pi , j = 1, . . . , m
i∈Aj

then the random vector Y has a Multi(n, q) distribution.

17
Conditional Distributions If {i1 , . . . , im } and {im+1 , . . . , ik } partition
the set {1, . . . , k}, then the conditional distribution of Xi1 , . . ., Xim given
Xim+1 , . . ., Xik is Multi(n − Xim+1 − · · · − Xik , q), where the parameter
vector q has components
p ij
qj = , j = 1, . . . , m
pi1 + · · · + pim

Relation to Other Distributions

• Each marginal of a multinomial is binomial.


• If X is Bin(n, p), then the vector (X, n − X) is Multi n, (p, 1 − p) .

16 Bivariate Normal Distribution

Abbreviation See multivariate normal below.

Type Continuous.

Rationales See multivariate normal below.

Parameters Real vector µ of dimension 2, real symmetric positive semi-

definite matrix M of dimension 2 × 2 having the form
 2 
σ1 ρσ1 σ2
M=
ρσ1 σ2 σ22
where σ1 > 0, σ2 > 0 and −1 < ρ < +1.

Sample Space The Euclidean space R2 .

Probability Density Function

1
det(M)−1/2 exp − 12 (x − µ)T M−1 (x − µ)


f (x) =
2π "
x1 − µ 1 2

1 1
= p exp −
2π 1 − ρ2 σ1 σ2 2(1 − ρ2 ) σ1
 #!
x2 − µ 2 2
   
x 1 − µ1 x2 − µ 2
−2ρ + , x ∈ R2
σ1 σ2 σ2

18
Moments

E(Xi ) = µi , i = 1, 2
var(Xi ) = σi2 , i = 1, 2
cov(X1 , X2 ) = ρσ1 σ2
cor(X1 , X2 ) = ρ

Moments (Vector Form)

E(X) = µ
var(X) = M

Linear Transformations See multivariate normal below.

Addition Rule See multivariate normal below.

Marginal Distributions Xi is N (µi , σi2 ) distributed, i = 1, 2.

Conditional Distributions The conditional distribution of X2 given X1

is  σ2 2 2

N µ2 + ρ (x1 − µ1 ), (1 − ρ )σ2
σ1

17 Multivariate Normal Distribution

Abbreviation N (µ, M)

Type Continuous.

Rationales

• Multivariate analog of the univariate normal distribution.

• Limiting distribution in the multivariate central limit theorem.

Parameters Real vector µ of dimension k, real symmetric positive semi-

definite matrix M of dimension k × k.

Sample Space The Euclidean space Rk .

19
Probability Density Function If M is (strictly) positive definite,

f (x) = (2π)−k/2 det(M)−1/2 exp − 12 (x − µ)T M−1 (x − µ) , x ∈ Rk

Otherwise there is no density (X is concentrated on a hyperplane).

Moments (Vector Form)

E(X) = µ
var(X) = M

Linear Transformations If X is N (µ, M) distributed, then a + BX,

where a is a constant vector and B is a constant matrix of dimensions
such that the vector addition and matrix multiplication make sense, has the
N (a + Bµ, BMBT ) distribution.

Addition Rule If X1 , . . ., Xk are independent random vectors, Xi being

N (µi , Mi ) distributed, then X1 +· · ·+Xk is a N (µ1 +· · ·+µk , M1 +· · ·+Mk )
random variable.

Degeneracy If a vector a exists such that Ma = 0, then var(aT X) = 0.

Partitioned Vectors and Matrices The random vector and parameters

are written in partitioned form
 
X1
X= (17.1a)
X2
 
µ1
µ= (17.1b)
µ2
 
M11 M12
M= (17.1c)
M21 M2

when X1 consists of the first r elements of X and X2 of the other k − r

elements and similarly for µ1 and µ2 .

Marginal Distributions Every marginal of a multivariate normal is nor-

mal (univariate or multivariate as the case may be). In partitioned form,
the (marginal) distribution of X1 is N (µ1 , M11 ).

20
Conditional Distributions Every conditional of a multivariate normal
is normal (univariate or multivariate as the case may be). In partitioned
form, the conditional distribution of X1 given X2 is

N (µ1 + M12 M− −
22 [X2 − µ2 ], M11 − M12 M22 M21 )

where the notation M− −

22 denotes the inverse of the matrix M22 if the matrix
is invertible and otherwise any generalized inverse.

18 Chi-Square Distribution
Abbreviation chi2 (ν) or χ2 (ν).

Type Continuous.

Rationales

• Sum of squares of IID standard normal random variables.

• Sampling distribution of sample variance when data are IID normal.

• Asymptotic distribution in Pearson chi-square test.

• Asymptotic distribution of log likelihood ratio.

Parameter Real number ν > 0 called “degrees of freedom.”

Sample Space The interval (0, ∞) of the real numbers.

Probability Density Function

( 12 )ν/2 ν/2−1 −x/2

f (x) = x e , 0 < x < ∞.
Γ( ν2 )

Moments

E(X) = ν
var(X) = 2ν

Addition Rule If X1 , . . ., Xk are independent random variables, Xi being

chi2 (νi ) distributed, then X1 +· · ·+Xk is a chi2 (ν1 +· · ·+νk ) random variable.

21
Normal Approximation If ν is large, then

chi2 (ν) ≈ N (ν, 2ν)

Relation to Other Distributions

• chi2 (ν) = Gam( ν2 , 21 ).

• If X is N (0, 1) distributed, then X 2 is chi2 (1) distributed.

• If Z and Y are independent,

p X is N (0, 1) distributed and Y is chi2 (ν)
distributed, then X/ Y /ν is t(ν) distributed.

• If X and Y are independent and are chi2 (µ) and chi2 (ν) distributed,
respectively, then (X/µ)/(Y /ν) is F (µ, ν) distributed.

19 Student’s t Distribution
Abbreviation t(ν).

Type Continuous.

Rationales
√
• Sampling distribution of pivotal quantity n(X n − µ)/Sn when data
are IID normal.

• Marginal for µ in conjugate prior family for two-parameter normal

data.

Parameter Real number ν > 0 called “degrees of freedom.”

Sample Space The real numbers.

Probability Density Function

1 Γ( ν+1
2 ) 1
f (x) = √ · ν · (ν+1)/2 , −∞ < x < +∞
νπ Γ( 2 ) x2
1+ ν

22
Moments If ν > 1, then
E(X) = 0.
Otherwise the mean does not exist. If ν > 2, then
ν
var(X) = .
ν−2
Otherwise the variance does not exist.

Normal Approximation If ν is large, then

t(ν) ≈ N (0, 1)

Relation to Other Distributions

• If X and Y are independent,
p X is N (0, 1) distributed and Y is chi2 (ν)
distributed, then X/ Y /ν is t(ν) distributed.
• If X is t(ν) distributed, then X 2 is F (1, ν) distributed.
• t(1) = Cauchy(0, 1).

20 Snedecor’s F Distribution
Abbreviation F (µ, ν).

Type Continuous.

Rationale
• Ratio of sums of squares for normal data (test statistics in regression
and analysis of variance).

Parameters Real numbers µ > 0 and ν > 0 called “numerator degrees of

freedom” and “denominator degrees of freedom,” respectively.

Sample Space The interval (0, ∞) of the real numbers.

Probability Density Function

Γ( µ+ν
2 )µ
µ/2 ν ν/2
xµ/2−1
f (x) = · , 0 < x < +∞
Γ( µ2 )Γ( ν2 ) (µx + ν)(µ+ν)/2

23
Moments If ν > 2, then
ν
E(X) = .
ν−2
Otherwise the mean does not exist.

Relation to Other Distributions

• If X and Y are independent and are chi2 (µ) and chi2 (ν) distributed,
respectively, then (X/µ)/(Y /ν) is F (µ, ν) distributed.

• If X is t(ν) distributed, then X 2 is F (1, ν) distributed.

21 Cauchy Distribution
Abbreviation Cauchy(µ, σ).

Type Continuous.

Rationales

• Very heavy tailed distribution.

• Counterexample to law of large numbers.

Parameters Real numbers µ and σ > 0.

Sample Space The real numbers.

Probability Density Function

1 1
f (x) = ·
, −∞ < x < +∞
πσ 1 + x−µ 2
σ

Moments No moments exist.

Addition Rule If X1 , . . ., Xk are IID Cauchy(µ, σ) random variables,

then X n = (X1 + · · · + Xk )/n is also Cauchy(µ, σ).

24
Relation to Other Distributions

• t(1) = Cauchy(0, 1).

22 Laplace Distribution
Abbreviation Laplace(µ, σ).

Type Continuous.

Rationales The sample median is the maximum likelihood estimate of

the location parameter.

Parameters Real numbers µ and σ > 0, called the mean and standard
deviation, respectively.

Sample Space The real numbers.

Probability Density Function

√
√ x−µ
 
2
f (x) = exp − 2 , −∞ < x < ∞
2σ σ

Moments

E(X) = µ
var(X) = σ 2

25