Some Useful Distributions

Binomial Distribution
æö
n÷ k
ç
p(k ) = ç ÷ p (1 - p ) n- k
, k = 0,1,..., n Bernoulli 1720
çk
èø ÷
÷

m= np s 2 = np(1- p)
k=0:20;
k=0:20;
y=binocdf(k,20,0.5);
y=binopdf(k,20,0.5);
stairs(k,y)
stem(k,y)
grid on
n = 20 p = 0.5
 Binomial Distribution
function y=mybinomial(n,p)
for k=0:n
y(k+1)=factorial(n)/(factorial(k)*factorial(n-k))*p^k*(1-p)^(n-k)

end
k=0:20;
k=0:20; y=binopdf(k,20,0.1);
y=mybinomial(20,0.5); stem(k,y)
n = 20 p = 0.5
stem(k,y) n = 20 p = 0.1
 Geometric Distribution

p(k ) = (1- p ) k - 1 p, k =1, 2,... Warning: Matlab assumes

1 1- p p(k ) = (1- p ) k p, k = 0,1, 2,...
2
m= s = 2
p p
k=0:20;
k=0:20; y=geocdf(k,0.5);
y=geopdf(k,0.5); stairs(k,y)
stem(k,y) axis([0 20 0 1])
p = 0.5
 Geometric Distribution
function y=mygeometric(n,p)
for k=1:n
y(k)=(1-p)^(k-1)*p;
end

k=1:20; k=1:20;
y=mygeometric(20,0.5); y=mygeometric(20,0.1);
stem(k,y) stem(k,y)
p = 0.5 p = 0.1
 Poisson Distribution
l k -l
p(k ) = e , k = 0,1,... Poisson 1837
k!
m= l s 2 =l
k=0:20;
k=0:20; y=poisscdf(k,5);
y=poisspdf(k,5); stem(k,y)
stem(k,y) grid on
l =5
 Poisson Distribution
function y=mypoisson(n,lambda)
for k=0:n
y(k+1)=lambda^k/factorial(k)*exp(-lambda);
end
k=0:10; k=0:10;
y=mypoisson(10,0.1); y=mypoisson(10,2);
stem(k,y) stem(k,y)
axis([-1 10 0 1]) axis([-1 10 0 1])
l = 0.1 l =2
 Uniform Distribution
1
f ( x) = , a£ x£ b
b- a
a +b 2 (b - a) 2
m= s =
2 12
x=0:0.1:8; x=0:0.1:8;
y=unifpdf(x,2,6); y=unifcdf(x,2,6);
plot(x,y) plot(x,y)
axis([0 8 0 0.5]) axis([0 8 0 2])
 Normal Distribution
( x- m)2
1 -
f ( x) = e 2s 2
, - ¥ < x <¥ Gauss 1820
2ps
, 2)
N (ms
Warning: Matlab uses N (ms
, )
x=0:0.1:20;
x=0:0.1:20;
y=normcdf(x,10,2);
y=normpdf(x,10,2);
plot(x,y)
plot(x,y)
N (10, 4)
 Normal Distribution
function y=mynormal(x,mu,sigma2)
y=1/sqrt(2*pi*sigma2)*exp(-(x-mu).^2/(2*sigma2));

x=-6:0.1:6;
y1=mynormal(x,0,1);
y2=mynormal(x,0,4);
plot(x,y1,x,y2,'r');
legend('N(0,1)','N(0,4)')
 Exponential Distribution
f ( x ) = l e- l x , 0 £ x <¥
Warning: Matlab assumes
1 1 1 - lc
m= s2 = f ( x) = e , 0 £ x <¥
l l 2
l

x=0:0.1:5; x=0:0.1:5;
y=exppdf(x,1/2); y=expcdf(x,1/2);
plot(x,y) plot(x,y)
l =2
 Exponential Distribution
function y=myexp(x,lambda)
y=lambda*exp(-lambda*x);

x=0:0.1:10;
y1=myexp(x,2);
y2=myexp(x,0.5);
plot(x,y1,x,y2,'r')
legend('lampda=2','lambda=0.5')
 Rayleigh Distribution
x2
x -
2s 2
f ( x) = 2
e , x³ 0
s
p æ pö
m= s s 2 =ç
ç2- ÷
÷
÷s 2

2 ç
è 2ø

x=0:0.1:10;
y1=raylpdf(x,1);
y2=raylpdf(x,2);
plot(x,y1,x,y2,'r')
legend('sigma=1','sigma=2')
 Poisson Approximation to Binomial

n? 1 p=1 np = l

æö
n ÷ l k
ç
ç ÷p k
(1 - p ) n - k
; e -l

èk ÷
ç ÷
ø k!

n=100;
p=0.1;
lambda=10;
k=0:n;
y1=mybinomial(n,p);
y2=mypoisson(n,lambda);
stem(k,y1)
hold on
stem(k,y2,’r’)
 Normal Approximation to Binomial

DeMoivre – Laplace Theorem 1730

X - np
If X is a binomial RV Z= is approximately a standard
np (1- p)
normal RV
( k - np )2
æö
n÷ k 1 -
P[ X = k ] = ç
ç ÷
÷p (1 - p ) n- k
; e 2 np (1- p )
ç ÷
èk ø 2pnp(1- p)

k2 æö
n÷ k æ k - np ö ÷ æ k - np ö ÷
P[k1 £ X £ k 2 ] = å ç ÷ ç p (1 - p ) n- k
; F ç
ç 2 ÷- F ç
ç 1 ÷
ç ÷
÷ ç ÷
÷ ç ÷
÷
k =k1 èk ø ç
è np (1 - p ) ø è ç np (1 - p ) ø

A better approximation
æk + 0.5 - np ö
÷ æk - 0.5 - np ö
÷
ç
P[k1 £ X £ k2 ] ; F ç 2 ÷- F ç
ç 1 ÷
ç ÷
÷ ç ÷
÷
ç
è np(1- p) ø è ç np(1- p) ø
 Normal Approximation to Binomial

function normbin(n,p)
clf
n = 10
y1=mybinomial(n,p);
k=0:n; p = 0.5
bar(k,y1,1,'w')
hold on
x=0:0.1:n;
y2=mynormal(x,n*p,n*p*(1-p));
plot(x,y2,'r')

n = 30
p = 0.5
 Central Limit Theorem

function k=clt(n) % Central Limit Theorem for sum of dies

m=(1+6)/2; % mean (a+b)/2
s=sqrt(35/12); % standart deviation sqrt(((b-a+1)^2-1)/12)
for i=1:n
x(i,:)=floor(6*rand(1,10000)+1);
end
for i=1:length(x(1,:)) % sum of n dies
y(i)=sum(x(:,i));
z(i)=(sum(x(:,i))-n*m)/(s*sqrt(n));
end

subplot(2,1,1)
hist(y,100)
title('unormalized')
subplot(2,1,2)
hist(z,100)
title('normalized')
 Central Limit Theorem
a +b
m= = 3.5
2

(b - a +1)2 - 1 n =1
2
s = = 2.92
12

n
unormalized = å X i
i =1

å X i - nm
n=2
normalized = i =1

s n
Central Limit Theorem

n =5

n = 10