07. midterm practice

27
1 Probabilit 07. Midterm Practice Condition Independence 郭郭郭 2009/04/13

Upload: edythe

Post on 11-Jan-2016

33 views

Category:

Documents


0 download

DESCRIPTION

Condition Independence 郭俊利 2009/04/13. 07. Midterm Practice. 2.1 ~ 4.1. Concept.  Homework  p(n) > 1 Discrete  f ( x ) > 1 Continuous  F( x ) > 1. Basic Probability. Set P(A ∪ B ∪ C) = P(A) + P(A C ∩ B) + P(A C ∩ B C ∩C) Condition P(A∩B∩C) = P(A) P(B|A) P(C|A∩B) - PowerPoint PPT Presentation

TRANSCRIPT

Page 1: 07. Midterm Practice

1

Probability

07. Midterm Practice

ConditionIndependence

郭俊利 2009/04/13

Page 2: 07. Midterm Practice

2

ProbabilityConcept

Homework

p(n) > 1 Discrete

f (x) > 1 Continuous

F(x) > 1

2.1 ~ 4.1

Page 3: 07. Midterm Practice

3

ProbabilityBasic Probability

Set P(A∪B∪C) =

P(A) + P(AC∩B) + P(AC∩BC∩C) Condition

P(A∩B∩C) = P(A) P(B|A) P(C|A∩B) Independence

P(A∩B) = P(A) P(B)

Problem 1.31 – error bit

Page 4: 07. Midterm Practice

4

ProbabilityExpectation

E[a] = a E[aX + b] = aE[X] + b E[g(X)] = Σx g(x) px(x) E[X] = Σi E[Xi] = np (p is uniform!)

E[X] = Σi P(Ai) E[X | Ai] E[X] = E[E[X|Y]]

var(aX + b) = a2 var(X)

Page 5: 07. Midterm Practice

5

ProbabilityGraph

Mean Center (not find f(x))

Variance E[X2] – E[X]2 (need f(x) or formula)

f(x)

x

1/3

2/3

1 2

Page 6: 07. Midterm Practice

6

Probability

Page 7: 07. Midterm Practice

7

ProbabilityOther E.V.

Independence

E[XY] = E[X] E[Y] var(X + Y) = var(X) + var(Y)

Sum

E[T] = E[X] E[N] var(T) = var(X) E[N] + E2[X] var(N)

T = X1 + … + XN

f(x, y) = f(x) f(y)

Page 8: 07. Midterm Practice

8

ProbabilityConditional Sum of Independence 1st

Let X1, X2 and X3 be independent and identical binomial random variables, that is, P(Xi = k) = Cn

k pk (1 − p)n−k, 0 ≤ k ≤ n. Compute the P(Z = X1 + X2 + X3) Compute E[Z], var(Z)

E[] = np ; var() = np(1-p)

Page 9: 07. Midterm Practice

9

Probability

Page 10: 07. Midterm Practice

10

ProbabilityJoint

fX,Y(x,y) = fY(y) fX|Y(x|y)

X, Y are independent, X and Y are in [0, 2].fXY(x, y) = xy / 4, find E[f(x, y)]

Double integration or…∵ f(x, y) = f(x) f(y)

∴ f(x) = x / 2 f(y) = y / 2 or

  f(x) = x f(y) = y / 4

Page 11: 07. Midterm Practice

11

Probability

Page 12: 07. Midterm Practice

12

ProbabilityImportant Random Variable

Bernoulli pX(k) = p, 1-p

Binomial pX(k) = Cn

k pk (1 – p)n – k

Geometric pX(k) = (1 – p)k-1 p

E[X] = p var(X) = p(1-p)

E[X] = np var(X) = np(1-p)

E[X] = 1/p var(X) = (1-p)/p2

Page 13: 07. Midterm Practice

13

ProbabilityGeometric random number

Xiao-Quan plays a game rock-paper-scissors with another. He plays until he loses. Find the expectation of the number of rounds. If Xiao-Quan has won 3 times and drawn 2 times,

how many rounds will he expect to play?

Problem 2.22, 2.23 Non-memoryless

Page 14: 07. Midterm Practice

14

ProbabilityConditional Sum of Independence 2nd

Suppose that X and Y are independent and identical geometrical random variables with parameter p, that is,P(X = k) = P(Y = k) = qk−1p, k ≥ 1.

Compute P(X = i | X + Y = n), i = 1, 2, ..., n − 1. Compute E(X | X + Y = n), var(X | X + Y = n).

P(X = i | X + Y = n) = P(X = i ∩ X + Y = n)

P(X + Y = n)

=P(X = i ∩ Y = n – i)

P(X + Y = n)

=P(X = i) P(Y = n – i)

P(X + Y = n)= 1 / n-1

Page 15: 07. Midterm Practice

15

ProbabilityExponential random number

f(x) = λe–λx

P(x a) =∫≧ a∞ λe–λx dx

= –e–λx | a∞ = e–λa

F(x) = 1 – e–λx (Geometric F(n) = 1 – (1–p)n)

E[X] = 1 / λ var(X) = 1 / λ2 (E[X2] = 2 / λ2)

Page 16: 07. Midterm Practice

16

ProbabilityExponential Examples

The spent time of work is modeled as an exponential random variable. The average time that Xiao-Ming completes the task is 10 hours. What is the probability that Xiao-Ming has done this task early (in advance)?

f(x) = ½ λe–λx, x ≥ 0 ½ λe+λx, x < 0

F(x) = ?

Page 17: 07. Midterm Practice

17

Probability

Page 18: 07. Midterm Practice

18

ProbabilityCondition

P(A|B) = P(A∩B) / P(B) pX|A(x) = P({X = x}∩A) / P(A) fX|A(x) = f(x) / P(A)

Roll a fair die shown k points, what is the probability p(k) given some roll is even number?

Xiao-Wang arrivals is a uniform random variable from 7:10 to 7:30. The bus comes at 7:15 and 7:30. What is the waiting time f(x) of Xiao-Wang?

Show exponential random number is memoryless.

Page 19: 07. Midterm Practice

19

Probability

Page 20: 07. Midterm Practice

20

ProbabilityNormal random number

Standard normal distribution N(–a) = P(Y ≦ –a) = P(Y ≧ a) = 1 – P(Y ≦ a)

N(–a) = 1 – N(a) CDF

P(X ≦ a) = P(Y ≦ ) = N( )a – μσ

a – μσ

The grades of the exam is suitable for a normal random variable. The average of grades = 60 and the standard deviation = 20. What is the probability that Xiao-Kuo’s grade will be higher over 70?

Page 21: 07. Midterm Practice

21

ProbabilityF() and f()

Derived

Linear Y = aX + b

General y = g(x), x = h(y) y = g(h(y))

fY(y) = fX( h(y) ) |h’(y)|

Page 22: 07. Midterm Practice

22

ProbabilityDerived Distribution

Find the PDF of Z = g(X, Y) = Y/X

FZ(z) = 0 ≤ z ≤ 1 FZ(z) = z > 1

fZ(z) =

Page 23: 07. Midterm Practice

23

ProbabilityLinear Mapping

X is an exponential random variable,Y = –λX + 2, Find the PDF of Y

f(x) = λe–λx

f(y) = e–λ(y-2 / –λ)

= e y-2

λ

|-λ|

Page 24: 07. Midterm Practice

24

ProbabilityTravel Problem

Xiao-Hua is driving from Boston to New York 180 miles. His speed is uniformly distributed between 30 and 60 mph. What is the distribution of the duration of the trip?

fV(v) = 1 / 30 30 ≤ v ≤ 60

T(v) = 180 / v

fT(t) = fV(v) T(t)’ = 6 / t2

Page 25: 07. Midterm Practice

25

Probability

Page 26: 07. Midterm Practice

26

ProbabilityConvolution

W = X + Y PW(w) = Σ PX(x) PY(w – x)

W = |X| + 2Y

p(x) = 1/3, if x = –1, 0, 1

p(y) = 1/2, y = 0 1/3, y = 1 1/6, y = 2

Page 27: 07. Midterm Practice

27

ProbabilityMaximum

W = max {X, Y} (X, Y = [0, 1] uniformly)

W = max {X, Y} (X, Y = 0.1, 0.2, …, 1.0 uniformly)

P(X≦w) = P(Y≦w) = w

FW(w) = P(X≦w) P(Y≦w) = w2

fW(w) = 2w

pW(w) = FW(w) – FW(w – 0.1)

= w2 – (w–0.1)2