Math/Stat 341 - Probability

Final Exam - Practice Problems

Problem 1. Suppose that X and Y are independent random variables uniformly dis-
tributed in [0, 2]. Compute the following probabilities:
a) P(Y ≥ X 2 ).
b) P(XY ≥ 1).

Problem 2. Suppose that X and Y are jointly continuous random variables with the
joint density function
 8x+4y2
, if 0 < y < x < 1
f (x, y) = 3
0, otherwise.

a) Find the marginal density functions fX and fY or the random variables X and Y .
b) Find Cov(X, Y ).
c) Find E(Y |X) and E(X|Y ).

Problem 3 [Uniform to Weibull]. Let X have the uniform distribution on [0, 1]. For
what function g does Y = g(X) have the Weibull distribution with parameters α = 2
and β = 2?

Problem 4. Let X and Y be two independent identically distributed

√ random variables
with uniform [0, 1] distribution. Find the density function of X + Y .

Problem 5. a) Let X and Y be independent N (0, 1) variables. Show that X + Y is

N (0, 2).
b) Show that, if X is N (µ1 , σ12 ) and Y is N (µ2 , σ22 ) and X and Y are independent, then
Z = X + Y is N (µ1 + µ2 , σ12 + σ22 ).

Problem 6. Let X1 and X2 be independent exponential variables, with the parameter

λ and let X = X1 and S = X1 + X2 .
a) Show that X and S are not independent.
b) What is the conditional distribution of X, given {S = s}?

Problem 7. n distinct random numbers X1 , X2 , . . . , Xn are independently picked from

the uniform [0, 1] distribution. We read the sequence X1 , X2 , . . . , Xn and record how
many times we encounter a number larger than the previous ones. Denote by Y this
number; for example, if n = 4 and X1 = .4, X2 = .2, X3 = .6, X4 = .3, we have Y = 2
(we get larger numbers twice, at X1 and at X3 ). Compute E(Y ).
n
1X
Problem 8. Show that the average Xk of n independent Cauchy variables has the
n k=1
Cauchy distribution too. Why does this not violate the law of large numbers?

Problem 9. Suppose that X1 , X2 , . . . , X100 are independent identically distributed ran-

dom variables with mean µ and variance 1, representing 100 measurements whose average
X = (X1 + X2 + · · · + X100 )/100 should be close to µ. Calculate P(|X − µ| ≥ .25).
 Examples of Distributions

X Values of X fX (k) Mean Variance

Uniform {x1 , . . . , xn } {x1 , . . . , xn } fX (k) = n1 m1 (U ) σ2 (U )
Bernoulli (p) {0,1} fX (0) = 1 −
p, fX (1) = p 1 − p + peit 1 − p + pet
Binomial (n, p) {0, 1, 2, . . . , n} fX (k) = nk pk (1 − p)n−k (1 − p + peit )n (1 − p + pet )n
k it t
Poisson (λ) {0, 1, 2, . . .} fX (k) = λk! e−λ eλ(e −1) eλ(e −1)
peit pet
Geometric (p) {1, 2, . . .} fX (k) = p(1 − p)k−1 1−(1−p)eit 1−(1−p)et

where, for the Uniform {x1 , . . . , xn } distribution, we have

x1 + · · · + xn
m1 (U ) =
n
n  2 !  2
1 X x1 + · · · + xn x1 + · · · + xn
σ2 (U ) = xk − −
n k=1 n n

X Density fX (x) Range for x Mean Variance

1 a+b (b−a)2
Uniform [a, b] b−a
[a, b] 2 12
−λx 1 1
Exponential (λ) λe [0, ∞) λ λ2
(x−µ)2
Normal (µ, σ 2 ) √ 1
2πσ 2
e− 2σ2 (−∞, ∞) µ σ2
Gamma (λ, t) 1
Γ(t)
λt xt−1 e−λx [0, ∞) t
λ
t
λ2
1
Cauchy π(1+x2 )
(−∞, ∞) – –
1 a ab
Beta (a, b) B(a,b)
xa−1 (1 − x)b−1 [0, 1] a+b (a+b)2 (a+b+1)
1 2
Weibull (α, β) αβx β−1 −αxβ
e [0, ∞) α− β Γ(1 + β1 ) α− β Γ(1 + β2 ) − m21

Note: In the last box, m1 denotes the mean of the Weibull distribution with parameters
1
α and β: m1 = α− β Γ(1 + β1 ).

X Density fX (x) Range for x Mean Variance

1

d
1 2 d2 −1 − x2
Chi-Squared χ2 (d) Γ( d2 ) 2
x e [0, ∞) d 2d
Γ( r+1
− r+1
2 )

x2 2 r
Student’s “t” t(r) √
πr Γ( r2 )
1+ r (−∞, ∞) 0 (r > 1) r−2
(r > 2)
“F ” F (r, s) fF (r,s) (0, ∞) m1 (F (r, s)) σ2 (F (r, s))

where, for the “F ” distribution, we have

1
r Γ( r+s2
) (rx/s) 2 r−1
fF (r,s) (x) = · , x>0
s Γ( 2r )Γ( 2s ) [1 + (rx/s)] 12 (r+s)
s
m1 (F (r, s)) = , for s > 2
s−2
2s2 (r + s − 2)
σ2 (F (r, s)) = , for s > 4
r(s − 2)2 (s − 4)
 Characteristic Functions and Moment Generating Functions

X Values of X fX (k) φX (t) MX (t)

Pn Pn
Uniform {x1 , . . . , xn } {x1 , . . . , xn } fX (k) = n1 1
nk=1 e
itxk 1
n k=1 e
txk

Bernoulli (p) {0,1} fX (0) = 1 −
p, fX (1) = p 1 − p + peit 1 − p + pet

Binomial (n, p) {0, 1, 2, . . . , n} fX (k) = nk pk (1 − p)n−k (1 − p + peit )n (1 − p + pet )n
k it t
Poisson (λ) {0, 1, 2, . . .} fX (k) = λk! e−λ eλ(e −1) eλ(e −1)
peit pet
Geometric (p) {1, 2, . . .} fX (k) = p(1 − p)k−1 1−(1−p)eit 1−(1−p)et

X Density fX (x) Range for x φX (t) MX (t)

1 eitb −eita etb −eta
Uniform [a, b] b−a
[a, b] it(b−a) t(b−a)
−λx λ λ
Exponential (λ) λe [0, ∞) λ−it λ−t
(x−µ)2 1 1
e− 2σ2
2 2 2 2
Normal (µ, σ 2 ) √ 1 (−∞, ∞) eiµt− 2 σ t eµt+ 2 σ t
2πσ 2
s λ s
1
λs xs−1 e−λx λ


Gamma (λ, s) Γ(s)
[0, ∞) λ−it λ−t
1 −|t|
Cauchy π(1+x2 )
(−∞, ∞) e –

X Density fX (x) Range for x φX (t) MX (t)

d
1 2 d2 −1 − x2 d d
Chi-Squared χ2 (d) 1
d
Γ( 2 ) 2
x e [0, ∞) (1 − 2it)− 2 (1 − 2t)− 2
r+1
Γ( 2 )
 − r+1
x2 2
Student’s “t” t(r) √ r
πr Γ( 2 )
1 + r
(−∞, ∞) complicated –
“F ” F (r, s) fF (r,s) (0, ∞) complicated –