Scribd
Upload
29 views2 pages

GHFKJF

1. This document defines several common probability distributions including the binomial, geometric, Poisson, uniform, exponential, normal, and bivariate normal distributions. 2. It also covers transformations of random variables, describing how to calculate the probability density function of Y if Y is a function of another random variable X. 3. Additionally, it states the Poisson theorem that the binomial distribution converges to the Poisson distribution as the number of trials increases, and defines the linear regression line as minimizing the sum of squared residuals between observed and predicted values of Y given X.

Uploaded by

Lolnsd
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
29 views2 pages

GHFKJF

1. This document defines several common probability distributions including the binomial, geometric, Poisson, uniform, exponential, normal, and bivariate normal distributions. 2. It also covers transformations of random variables, describing how to calculate the probability density function of Y if Y is a function of another random variable X. 3. Additionally, it states the Poisson theorem that the binomial distribution converges to the Poisson distribution as the number of trials increases, and defines the linear regression line as minimizing the sum of squared residuals between observed and predicted values of Y given X.

Uploaded by

Lolnsd
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 2

1. Bernoulli (binomial) distribution b(n,p): if X ∼ b(n,p) then SX = {0,1,...

,n} and

.
Parameters: n ∈ N, p ∈ [0,1].
Moments: EX = np, VarX = np(1 − p).

2. Geometric distribution g(p): if X ∼ g(p) then SX = N and

P(X = k) = (1 − p)k−1p.

Parameter: p ∈ (0,1).
Moments: EX = 1/p, VarX = (1 − p)/p2.

3. Poisson distribution P(λ): if X ∼ P(λ) then SX = N ∪ {0} and

.
Parameter: λ > 0.
Moments: EX = λ, VarX = λ.

4. Uniform distribution (univariate) U(a,b): if X ∼ U(a,b) then

.
Parameters: a < b.
Moments: EX = (a + b)/2, VarX = (b − a)2/12.

5. Exponential distribution Exp(λ): if X ∼ Exp(λ) then

.
Parameter: λ > 0.
Moments: EX = 1/λ, VarX = 1/λ2.

6. Normal (gaussian) distribution (univariate) N(µ,σ2): if X ∼ N(µ,σ2) then

.
Parameters: µ ∈ R i σ > 0.
Moments: EX = µ, VarX = σ2.
Distribution N(0,1) is called standard normal distribution. 7.

Uniform distribution (bivariate) U(A): if X ∼ U(A) then

Parameter: A ⊂ R2 with finite and nonzero Lebesgue measure.

8. Normal (gaussian) distribution (bivariate) N(m,Σ): if X = (X,Y )T ∼ N(m,Σ) then for x =


(x,y)T ∈ R2

f X (x,y ) = √ 1
2π detC X
√ 1 =
2π detCXCX

Parameters:
m, CX,

where = Cov(X,Y ) = ρX,Y σ1σ2.


9. X – a random variable, continuously distributed, with the density fX; Y = g(X). If g is C1 and g0(x) = 06 ∀ x ∈ D
⊂ R, where P(X ∈ D) = 1, then Y is continuously distributed too, with the density

where h(y) = g−1(y).

10. X – a continously distributed random variable, with the density fX; Y = g(X). If
n

[
P(X ∈ Dk) = 1, gdzie n ∈ N,
k=1

Dk are disjoint and g is injective in all Dk, differentiable and g0(x) 6= 0 ∀ x ∈ Dk, then Y has a continuous
distribution, with the density

where hk(y) – the inverse function of g on Dk.

11. Poisson Theorem. If (Xn)n is a sequence of random variables such that Xn ∼ b(n,pn) and there exists limit
limn→∞ npn =: λ, then

.
12. Linear regression. If X and Y are random variables with finite second moments, then

is the regression line of the random variable Y with respect to X.

You might also like