37
GG 2040C: Probability Models and Applications Andrej Bogdanov Spring 2013 4. Random variables part two

4. Random variables part two

Embed Size (px)

DESCRIPTION

4. Random variables part two. Review. A discrete random variable X assigns a discrete value to every outcome in the sample space. E [ N ]. Probability mass function of X : p ( x ) = P ( X = x ). Expected value of X : E [ X ] = ∑ x x p ( x ). N: number of heads in two coin flips. - PowerPoint PPT Presentation

Citation preview

Page 1: 4. Random variables part two

ENGG 2040C: Probability Models and Applications

Andrej Bogdanov

Spring 2013

4. Random variablespart two

Page 2: 4. Random variables part two

Review

A discrete random variable X assigns a discrete value to every outcome in the sample space.

Probability mass function of X: p(x) = P(X = x)

Expected value of X: E[X] = ∑x x p(x).

E[N]

N: number of headsin two coin flips

Page 3: 4. Random variables part two

One die

Example from last time

F = face value of fair 6-sided dieE[F] = 1 + 2 + 3 + 4 + 5 + 6 = 3.5

1616 16 16 16 16

Page 4: 4. Random variables part two

Two dice

S = sum of face values of two fair 6-sided diceSolution 1

2 3 4 5 6 7 89 10 11 12

spS(s) 1

36236

336

436

536

636

536

436

336

236

136

E[S] = 2 + 3 + … + 12

136236 136 =

7

We calculate the p.m.f. of S:

Page 5: 4. Random variables part two

Two dice again

S = sum of face values of two fair 6-sided dice

F1 F2

S = F1 + F2

F1 = outcome of first dieF2 = outcome of second die

Page 6: 4. Random variables part two

Sum of random variables

Let X, Y be two random variables.

X + Y is the random variable that assigns value X(w) + Y(w) to outcome w.

X assigns value X(w) to outcome wY assigns value Y(w) to outcome w

Page 7: 4. Random variables part two

Sum of random variables

F1 F2 S = F1 + F2

11 1 1 212 1 2 3

21 2 1 3

… …

66 6 6 12

… …

Page 8: 4. Random variables part two

Linearity of expectation

E[X + Y] = E[X] + E[Y]

For every two random variables X and Y

Page 9: 4. Random variables part two

Two dice again

S = sum of face values of two fair 6-sided diceSolution 2

E[S] = E[F1] + E[F2]

= 3.5 + 3.5 = 7

F1 F2

S = F1 + F2

Page 10: 4. Random variables part two

Balls

We draw 3 balls without replacement from this urn:

-1

1

11

-1

-1

0

What is the expected sum of values on the 3 balls?

0

-1

Page 11: 4. Random variables part two

Balls

-1

1

11

-1

-1

00

-1S = B1 + B2

+ B3where Bi is the value of i-th ball.E[S] = E[B1] + E[B2] + E[B3]

p.m.f of B1:

-1 01

xp(x) 4

9 29

39

E[B1] = -1 (4/9) + 0 (2/9) + 1 (3/9) = -1/9same for B2, B3E[S] = 3 (-1/9) = -1/3.

Page 12: 4. Random variables part two

Three dice

E[N] = E[I1] + E[I2] + E[I3]

Solution I1 I2 I3

N = I1 + I2 + I3

E[I1] = 1 (1/6) + 0(5/6) = 1/6E[I2], E[I3] = 1/6

= 3 (1/6)

= 1/2

Ik =1 if face value of kth die equals

0 if not

N = number of s. Find E[N].

Page 13: 4. Random variables part two

Problem for you to solve

Five balls are chosen without replacement from an urn with 8 blue balls and 10 red balls.

What is the expected number of blue balls that are chosen?

What if the balls are chosen with replacement?

(a)

(b)

Page 14: 4. Random variables part two

The indicator (Bernoulli) random variablePerform a trial that succeeds with probability p and fails with probability 1 – p.

01p(x) 1 – p p

x

p = 0.5

p(x)

p = 0.4

p(x)E[X] = p

If X is Bernoulli(p) then

Page 15: 4. Random variables part two

The binomial random variable

Binomial(n, p): Perform n independent trials, each of which succeeds with probability p.

X = number of successes

ExamplesToss n coins. (# heads) is Binomial(n, ½). Toss n dice. (# s) is Binomial(n, 1/6).

Page 16: 4. Random variables part two

A less obvious example

Toss n coins. Let C be the number of consecutive changes (HT or TH).

w C(w)

HTHHHHT 3THHHHHTHHHHHHH

20

Examples:

Then C is Binomial(n – 1, ½).

Page 17: 4. Random variables part two

A non-example

Draw 10 cards from a 52-card deck.Let N = number of aces among the drawn cards

Is N a Binomial(10, 1/13) random variable?

No!

Different trial outcomes are not independent.

Page 18: 4. Random variables part two

Properties of binomial random variablesIf X is Binomial(n, p), its p.m.f. is

p(k) = P(X = k) = C(n, k) pk (1 - p)n-k

We can write X = I1 + … + In, where Ii is an indicator random variable for the success of the i-th trial E[X] = E[I1] + … + E[In]

= p + … + p = np.

E[X] = np

Page 19: 4. Random variables part two

Probability mass functionBinomial(10, 0.5) Binomial(50, 0.5)

Binomial(10, 0.3) Binomial(50, 0.3)

Page 20: 4. Random variables part two

Investments

You have two investment choices:A: put $25 in one stock B: put $½ in each of 50 unrelated stocks Which do you prefer?

Page 21: 4. Random variables part two

Investments

Probability model

Each stock

doubles in value with probability ½ loses all value with probability ½

Different stocks perform independently

Page 22: 4. Random variables part two

Investments

NA = amount on choice A

NB = amount on choice B 50 × Bernoulli(½)

A: put $50 in one stock B: put $½ in each of 50 stocks

Binomial(50, ½)

E[NA] E[NB]

Page 23: 4. Random variables part two

Variance and standard deviation

Let m = E[X] be the expected value of X.

The variance of X is the quantityVar[X] = E[(X –

m)2]The standard deviation of X is s = √Var[X]

They measure how close X and m are typically.

Page 24: 4. Random variables part two

Calculating variancem = E[NA]

y 252q(y) 1

p.m.f of (NA – m)2

Var[NA] = E[(NA – m)2]

x 050p(x) ½½ p.m.f of NA

= 252

s = std. dev. of NA = 25

m – s m + s

Page 25: 4. Random variables part two

Another formula for variance

Var[X] = E[(X – m)2]

= E[X2 – 2mX + m2]= E[X2] + E[–2mX] + E[m2]= E[X2] – 2m E[X] + m2

= E[X2] – 2m m + m2

= E[X2] – m2

for constant c, E[cX] = cE[X]

for constant c, E[c] = c

Var[X] = E[X2] – E[X]2

Page 26: 4. Random variables part two

Variance of binomial random variableSuppose X is Binomial(n, p).Then X = I1 + … + In, where Ii =

1, if trial i succeeds0, if trial i fails

Var[X] = E[X2] – m2 = E[X2] – (np)2

m = E[X] = np

E[X2]= E[(I1 + … + In)2]= E[I1

2 + … + In2 + I1I2 + … + In-1In]

= E[I12] + … + E[In

2] + E[I1I2] + … + E[In-

1In]

E[Ii2] = E[Ii] = p E[Ii Ij] = P(Ii = 1 and Ij = 1)

= P(Ii = 1) P(Ij = 1) = p2

= n p = n(n-1) p2

= np + n(n-1) p2 – (np)2

Page 27: 4. Random variables part two

Variance of binomial random variable

Suppose X is Binomial(n, p).

Var[X] = np + n(n-1) p2 – (np)2

m = E[X] = np

= np – p2 = np(1-p)

Var[X] = np(1-p)

s = √np(1-p).

The standard deviation of X is

Page 28: 4. Random variables part two

Investments

NA = amount on choice A

NB = amount on choice B 50 × Bernoulli(½)

A: put $50 in one stock B: put $½ in each of 50 stocks

Binomial(50, ½)m m

s = 25 s = √50 ½ ½ = 3.536…

m – s m + s

Page 29: 4. Random variables part two

Apples

About 10% of the apples on your farm are rotten.You sell 10 apples. How many are rotten?

Probability modelNumber of rotten apples you sold isBinomial(n = 10, p = 1/10).

E[N] = np = 1

Page 30: 4. Random variables part two

Apples

You improve productivity; now only 5% apples rot.You can now sell 20 apples and only one will be rotten on average.N is now Binomial(20, 1/20).

Page 31: 4. Random variables part two

Binomial(10, 1/10).349

.387

.194

.001

10-

10

Binomial(20, 1/20).354

.377

.189

.002

10-8 10-

26

.367

.367

.183

.003

10-7 10-

19

Page 32: 4. Random variables part two

The Poisson random variable

A Poisson(m) random variable has this p.m.f.:

p(k) = e-m mk/k!

k = 0, 1, 2, 3, …

Poisson random variables do not occur “naturally” in the sample spaces we have seen.They approximate Binomial(n, p) random variables when m = np is fixed and n is large (so p is small)

pPoisson(m)(k) = limn → ∞ pBinomial(n, m/n)(k)

Page 33: 4. Random variables part two

Rain is falling on your head at an average speed of 2.8 drops/second.

Divide the second evenly in n intervals of length 1/n.

Raindrops

Let Ei be the event “raindrop hits during interval i.”Assuming E1, …, En are independent, the number of drops in the second N is a Binomial(n, p) r.v.Since E[N] = 2.8, and E[N] = np, p must equal 2.8/n.

0 1

Page 34: 4. Random variables part two

Raindrops

Number of drops N is Binomial(n, 2.8/n)

0 1

As n gets larger, the number of drops within the second “approaches” a Poisson(2.8) random variable:

Page 35: 4. Random variables part two

Expectation and variance of Poisson

If X is Binomial(n, p) then E[X] = np Var[X] = np(1-

p)When p = m/n, we get

E[X] = m Var[X] = m(1-m/n)

As n → ∞, E[X] → m and Var[X] → m. This suggests

When X is Poisson(m), E[X] = m and Var[X] = m.

Page 36: 4. Random variables part two

Problem for you to solve

Rain falls on you at an average rate of 3 drops/sec.

You walk for 30 sec from MTR to bus stop.

When 100 drops hit you, your hair gets wet.

What is the probability your hair got wet?

Page 37: 4. Random variables part two

Problem for you to solve

SolutionOn average, 90 drops fall in 30 seconds.

So we model the number of drops N you receive as a Poisson(90) random variable.

Using the online Poisson calculator at or the poissonpmf(n, L) function in 13L07.py we get

P(N > 100) = 1 - ∑i = 0 P(N = i) ≈ 13.49%99