SAMPLE EXAM QUESTIONS - SOLUTION

As you might have gathered if you attempted these problems, they are quite long relative to the 24
minutes you have available to attempt similar questions in the exam; I am aware of this. However, these
questions were designed to cover as many of the topics we studied in the course.

M3S3 SAMPLE EXAM SOLUTIONS - page 1 of 20

 SAMPLE EXAM QUESTION 1 - SOLUTION

(a) State Cramer’s result (also known as the Delta Method) on the asymptotic normal distribution
of a (scalar) random variable Y defined in terms of random variable X via the transformation
Y = g(X), where X is asymptotically normally distributed
¡ ¢
X ∼ AN µ, σ 2 .

This is bookwork. If the derivative, ġ, of g is non-zero, then

Y ∼ AN (g(µ), {ġ(µ)}2 σ 2 )

We saw this result in a slightly different form in the lectures, stated as

√ L √ L
n(Xn − µ) −→ N (0, σ 2 ) =⇒ n(g(Xn ) − g(µ)) −→ N (0, {ġ(µ)}2 σ 2 )

and these two results are equivalent.

[4 MARKS]

(b) Suppose that X1 , ..., Xn are independent and identically distributed P oisson (λ) random variables.
Find the maximum likelihood (ML) estimator, and an asymptotic normal distribution for the
estimator, of the following parameters

(i) λ,
(ii) exp {−λ}.

(i) By standard theory, log-likelihood is

à n !
Y
l(λ) = −nλ + sn log λ − log xi !
i=1
Pn Pn
where sn = i=1 xi (with corresponding random variable Sn = i=1 Xi ) so

˙ sn
l(λ) = −n +
λ
so equating this to zero yields λ̂ = sn /n = x̄. Using the Central Limit Theorem,
(Sn − nλ) L
√ −→ N (0, λ)
n
as E[X] = Var[X] = λ. Hence
Sn
Sn ∼ AN (nλ, nλ) =⇒ X̄ = ∼ AN (λ, λ/n)
n
[3 MARKS]
(ii) By invariance of ML estimators to reparameterization, or from first principles, the ML estimator of
φ = exp(−λ) is φ̂ = exp(−X̄) = Tn , say.
For Cramer’s Theorem (Delta Method), let g(t) = exp(−t), so that ġ(t) = − exp(−t). Thus

Tn ∼ AN (exp(−λ), exp(−2λ)λ/n)

[3 MARKS]

M3S3 SAMPLE EXAM SOLUTIONS - page 2 of 20

 (c) Suppose that, rather than observing the random variables in (b) precisely, only the events
Xi = 0 or Xi > 0
for i = 1, ..., n are observed.

(i) Find the ML estimator of λ under this new observation scheme.

(ii) In this new scheme, when does the ML estimator not exist (at a finite value in the parameter
space) ? Justify your answer.
(iii) Compute the probability that the ML estimator does not exist for a finite sample of size n,
assuming that the true value of λ is λ0 .
(iv) Construct a modified estimator that is consistent for λ .

(i) We now effectively have a Bernoulli sampling model; let Yi be a random variable taking the value
0 if Xi = 0, and 1 otherwise; note that P [Yi = 0] = P [Xi = 0] = exp(−λ) = θ, say, so that the log
likelihood is
l(θ) = (n − m) log θ + m log(1 − θ)
Pn
where m = i=1 yi , the number of times that Yi , and hence Xi , is greater than zero. From this
likelihood, the ML estimate of θ is θ̂ = (n − m)/n, and hence the ML estimate of λ is
λ̂ = − log(θ̂) = − log((n − m)/n)
P
and the estimator is Tn = − log(n−1 ni=1 Yi )
[2 MARKS]

(ii) This
P estimate is not finite if m = n, that is, if we never observe Xi =0 in the sample, so that
m = ni=1 yi = n.
[2 MARKS]

(iii) The event of interest from (ii) occurs with the following probability:
" n # n n
X Y Y
P Yi = n = P [Yi = 1] = [1 − exp(−λ0 )] = (1 − exp(−λ0 ))n
i=1 i=1 i=1

which, if λ0 is not large, can be appreciable. Thus, for a finite value of n, there is a non-zero probability
that the estimator is not finite.
[3 MARKS]

(iv) Consistency (weak or strong) for λ will follow from the consistency of the estimator of θ, as we
have, from the Strong Law Pn
i=1 Yi a.s.
−→ θ
n
The only slight practical problem is that raised in (ii) and (iii), the finiteness of the estimator. We can
overcome this by defining the estimator as follows; estimate λ by
 Pn
 − log(n−1 i=1 Yi ) if max{Y1 , . . . , Yn } > 0
Tn0 =

k if max{Y1 , . . . , Yn } = 0
where k is some constant value. As the event (max{Y1 , . . . , Yn } = 0) occurs with probability (1 − exp(−λ0 ))n
which converges to 0 as n −→ ∞, this adjustment does not disrupt the strong convergence. Note that
6
we could choose k = 1, or k = 1010 , and consistency would be preserved.
[3 MARKS]

M3S3 SAMPLE EXAM SOLUTIONS - page 3 of 20

 SAMPLE EXAM QUESTION 2 - SOLUTION

(a) Suppose that X(1) < . . . < X(n) are the order statistics from a random sample of size n from a
distribution FX with continuous density fX on R. Suppose 0 < p1 < p2 < 1, and denote the
quantiles of FX corresponding to p1 and p2 by xp1 and xp2 respectively.

Regarding xp1 and xp2 as unknown parameters, natural estimators of these quantities are X(dnp1 e)
and X(dnp2 e) respectively, where dxe is the smallest integer not less than x. Show that
µ ¶
√ X(dnp1 e) − xp1 L
n −→ N (0, Σ)
X(dnp2 e) − xp2

where  
p1 (1 − p1 ) p1 (1 − p2 )
 {fX (xp1 )}2 fX (xp1 )fX (xp2 ) 
 
Σ=



 p1 (1 − p2 ) p2 (1 − p2 ) 
fX (xp1 )fX (xp2 ) {fX (xp2 )} 2

State the equivalent result for a single quantile xp corresponding to probability p.

This is bookwork, from the handout that I gave out in lectures. In solving the problem, it is legitimate
to state without proof some of the elementary parts; in terms of the handout, after describing the set
up, you would be allowed to quote without proof Results 1 through 3, and would only need to give the
full details for the final parts.
For the final result, for a single quantile xp , we have that
µ ¶
√ ¡ ¢ L p(1 − p)
n X(dnpe) − xp −→ N 0,
{fX (xp )}2

[10 MARKS]

(b) Using the results in (a), find the asymptotic distribution of

(i) The sample median estimator of the median FX (corresponding to p = 0.5), if FX is a Normal
distribution with parameters µ and σ 2 .
(ii) The upper and lower quartile estimators (corresponding to p1 = 0.25 and p2 = 0.75) if FX is
an Exponential distribution with parameter λ

(i) Here we have p = 0.5, and xp = µ, as the Normal distribution is symmetric about µ.
µ ¶ µ ¶
√ ¡ ¢ L (1/2)(1/2) πσ 2
n X(dn/2e) − µ −→ N 0, ≡ N 0,
{φ(0)}2 2
√
as φ(0) = 1/ 2πσ 2 and hence X(dn/2e) ∼ AN (µ, πσ 2 /2n).
[3 MARKS]
(ii) For probability p the corresponding quantile is given by

p = FX (x; λ) = 1 − e−λxp =⇒ xp = − log(1 − p)/λ

M3S3 SAMPLE EXAM SOLUTIONS - page 4 of 20

and fX (x; λ) = λe−λx . Let p1 = 1/4, p2 = 3/4, and c1 = − log(1 − 1/4)/λ and c2 = − log(1 − 3/4)/λ.
Then the key asymptotic covariance matrix is
   
(1/4)(3/4) (1/4)(1/4) 1 1
 λ2 e−2λc1 λ2 e−λ(c1 +c2 )   2
9λ2 
   3λ 
Σ= = 
 (1/4)(1/4) (3/4)(1/4)   1 3 
λ2 e−λ(c1 +c2 ) λ2 e−2λc2 9λ2 λ2
which gives that   
1 1
µ ¶ · ¸ 
X(dn/4e)  c  3nλ
2
9nλ2 

∼ AN  1 ,  
X(d3n/4e)  c2  1 3 
9nλ2 nλ2
[3 MARKS]

(c) The results in (a) and (b) describe convergence in law for the estimators concerned. Show how
the form of convergence may be strengthened using the Strong Law for any specific quantile xp .

The standard Strong Law result says, effectively, that for i.i.d. random variables X1 , X2 , . . ., for arbitrary
function G
n
1X a.s.
G(Xi ; θ) −→ EX|θ [G(X)].
n
i=1

So, here, if we define G(Xi ; θ) = 1 if Xi ≤ xp , and zero otherwise, then

n
1X a.s.
Un = G(Xi ; θ) −→ EX|θ [G(X)] = P [X ≤ xp ] = p
n
i=1

and we have strong convergence of the statistic on the left-hand side to p. Now FX−1 is a continuous,
monotone increasing function, so we can map both sides of the last result by FX−1 to obtain the result
a.s.
FX−1 (Un ) −→ FX−1 (p) = xp .

[4 MARKS]

M3S3 SAMPLE EXAM SOLUTIONS - page 5 of 20

 SAMPLE EXAM QUESTION 3 : SOLUTION

(a) (i) State (without proof ) Wald’s Theorem on the strong consistency of maximum likelihood (ML)
estimators, listing the five conditions under which this theorem holds.
Bookwork (although we focussed less on strong consistency of the MLE this year, and studied
weak consistency in more detail): Let X1 , . . . , Xn be i.i.d. with pdf fX (x|θ) (with respect
to measure ν), let Θ denote the parameter space, and let θ0 denote the true value of the
parameter θ. Suppose θ is 1-dimensional. Then, if
(1) Θ is compact,
(2) fX (x|θ) is upper semi-continuous (USC) in θ on Θ for all x, that is for all θ ∈ Θ and any
sequence {θn } such that θn −→ θ

lim sup fX (x|θn ) ≤ fX (x|θ)

n−→∞

or equivalently for all θ ∈ Θ

sup fX (x|θ0 ) −→ f (x|θ) as δ −→ 0

0
|θ −θ|<δ

for all x,
(3) there exists a function M (x) with EfX|θ0 [M (x)] < ∞ and

U (x, θ) = log fX (x|θ) − log fX (x|θ0 ) ≤ M (x)

for all x and θ,

(4) for all θ ∈ Θ, and sufficiently small δ > 0,

sup fX (x|θ0 )
0
|θ −θ|<δ

is measurable (wrt ν) in x.
(5) If fX (x|θ) = fX (x|θ0 ) almost everywhere wrt ν in x, then θ = θ0 ; this is the identifia-
bility condition,
any sequence of ML estimators {θ̂n } of θ is strongly consistent for θ, that is

a.s.
θ̂n −→ θ0
as n −→ ∞.
[5 MARKS]
(ii) Verify that the conditions of the theorem hold when random variables X1 , . . . , Xn correspond
to independent observations from the Uniform density on (0, θ)
1
fX (x|θ) = 0≤x≤θ
θ
and zero otherwise, for parameter θ ∈ Θ ≡ [a, b], where [a, b] is the closed interval from a to
b, 0 < a < b < ∞.

[Hint: for x ∈ R, consider the function

fX (x|θ)
M (x) = max
θ∈Θ fX (x|θ0 )
where θ0 ∈ Θ is the true value of θ.]

M3S3 SAMPLE EXAM SOLUTIONS - page 6 of 20

The governing measure here is Lebesgue measure.

(1) Θ ≡ [a, b] is closed and bounded, therefore compact.

(2) Need to consider all possible (fixed) x ∈ R. Now, when x ≤ a,

1
fX (x|θ) =
θ
which is continuous in θ. From the second USC definition, it is easy to see that continuous
functions are USC. Similarly, when x > b,

fX (x|θ) = 0

which is continuous in θ, and hence USC. Finally, for a < x ≤ b,


 0 θ<x

fX (x|θ) =
 1 θ≥x

θ
which is not continuous at x = θ, but is USC, as for all δ > 0,
1
sup fX (x|θ0 ) = = fX (x|θ)
|θ0 −θ|<δ θ

(|θ0 − θ| < δ defines an interval centered at θ, to the left of θ the function is zero, to the right of
θ the function is 1/θ, so the supremum over the interval is always 1/θ.)

(3) If
fX (x|θ)
M (x) = max
θ∈Θ fX (x|θ0 )
then 
 θ0

 x≤a

 a



M (x) = θ0

 a < x ≤ θ0

 x




∞ x > θ0
The expectation of M (X), when θ = θ0 , is finite as the third case is excluded (P [X > θ0 ] = 0).

(4) fX is measurable (by definition), and supremum operations preserve measurability.

(5) Identifiability is assured, as different θ values yield densities with different supports.

[5 MARKS]

M3S3 SAMPLE EXAM SOLUTIONS - page 7 of 20

(b) Wald’s Theorem relates to one form of consistency; the remainder of the question focuses on
another form.
We are now dealing with weak consistency ...

Suppose that random variables X1 , . . . , Xn correspond independent observations from density (wrt
Lebesgue measure) fX (x|θ), and for θ ∈ Θ, this family of densities have common support X. Let
the true value of θ be denoted θ0 , and let Ln (θ) denote the likelihood for θ
n
Y
Ln (θ) = fX (xi |θ).
i=1

(i) Using Jensen’s inequality for the function g(x) = − log x, and an appropriate law of large
numbers, show that

Pθ0 [Ln (θ0 ) > Ln (θ)] −→ 1 as n −→ ∞

for any fixed θ 6= θ0 , where Pθ0 denotes probability under the true model, indexed by θ0 .

This follows in a similar fashion to the proof of the positivity of the Kullback-Liebler (K)
divergence;

X n
Ln (θ0 ) Ln (θ0 ) fX (Xi |θ0 )
Ln (θ0 ) > Ln (θ) ⇔ > 1 ⇔ log >0⇔ log >0 (1)
Ln (θ) Ln (θ) fX (Xi |θ)
i=1
Now, by the weak law of large numbers
n · ¸
1X fX (Xi |θ0 ) p fX (X|θ0 )
Tn (θ0 , θ) = log −→ EfX|θ0 log = K(θ0 , θ) (2)
n fX (Xi |θ) fX (X|θ)
i=1

To finish the proof we use the Kullback-Liebler proof method; from Jensen’s inequality
· ¸ · ¸ · ¸
fX (X|θ0 ) fX (X|θ) fX (X|θ)
EfX|θ0 log = −EfX|θ0 log ≥ − log EfX|θ0
fX (X|θ) fX (X|θ0 ) fX (X|θ0 )
Z
fX (x|θ)
= − log fX (x|θ0 )dν
fX (x|θ0 )
Z
= − log fX (x|θ)dν ≥ − log 1 = 0.

with equality if and only if θ = θ0 . Thus, by (1) and (2)

p
Tn (θ0 , θ) −→ K(θ0 , θ) > 0

so that
Pθ0 [Ln (θ0 ) > Ln (θ)] = Pθ0 [Tn (θ0 , θ) > 0] −→ 1
as n −→ ∞.

Which other condition from (a)(i) needs to be assumed in order for the result to hold ?
Identifiability; the strictness of the inequality relies on θ 6= θ0 .

[5 MARKS]

M3S3 SAMPLE EXAM SOLUTIONS - page 8 of 20

(ii) Suppose that, in addition to the conditions listed in (b), parameter space Θ is finite, that is,
Θ ≡ {t1 , . . . , tp } for some positive integer p.

Show that, in this case, the ML estimator θ̂n exists, and is weakly consistent for θ0 .

This follows from the result in (b)(i); the standardized log-likelihood

n
1 1 1X
l(θ; x) = log L(θ; x) = log fX (Xi |θ)
n n n
i=1

evaluated at θ = θ0 = t? ∈ Θ, say, is greater than the log-likelihood evaluated at any

n other
o
value t ∈ Θ with probability 1, as n −→ ∞. Thus the sequence of ML estimators θ̂n is
such that
lim P [θ̂n 6= θ0 ] = 0
n→∞

which is the definition for weak consistency. Note that existence of the ML estimator (as a
finite value in the parameter space) is guaranteed for every n, as Θ is finite, and uniqueness
of the ML estimator is also guaranteed, with probability tending to 1, as n → ∞.
[5 MARKS]

M3S3 SAMPLE EXAM SOLUTIONS - page 9 of 20

 SAMPLE EXAM QUESTION 4 : SOLUTION

(a) (i) Give definitions for the following modes of stochastic convergence, summarizing the relation-
ships between the various modes;
• convergence in law (convergence in distribution)
• convergence almost surely
• convergence in rth mean

Bookwork: For a sequence of rvs X1 , X2 , . . . with distribution functions FX1 , FX2 , . . . with
and common governing probability measure P on space Ω with associated sigma algebra A;

(a) Convergence in Law

L
Xn −→ X ⇐⇒ FXn (x) −→ FX (x)

for all x ∈ R at which FX is continuous, where FX is a valid cdf on R.

(b) Convergence almost surely

h i
a.s.
Xn −→ X ⇐⇒ P lim Xn (ω) = X(ω) = 1
n→∞

almost everywhere with respect to P (that is, for all ω ∈ Ω except in sets A ∈ A such that
P (A) = 0. Equivalently,
h i
a.s.
Xn −→ X ⇐⇒ P lim |Xn (ω) − X(ω)| < ² = 1, ∀² > 0, a.e. P.
n→∞

Also equivalently,
a.s.
Xn −→ X ⇐⇒ P [|Xn (ω) − X(ω)| < ² i.o.] = 1, ∀² > 0, a.e. P.

where i.o. means infinitely often.

(c) Convergence in rth mean

r
Xn −→ X ⇐⇒ E [|Xn − X|r ] −→ 0 as n −→ ∞

for some positive integer r.

In summary, convergence in law is implied by both convergence a.s. and convergence in rth
mean, but there are no general relations between the latter two modes.
[6 MARKS]

(ii) Consider the sequence of random variables X1 , X2 , . . . defined by

Xn (Z) = nI[0,n) (Z)

where Z is a single random variable having an Exponential distribution with parameter 1.

Under which modes of convergence does the sequence {Xn } converge ? Justify your answer.

In this form, this question is rather boring, as

P [Xn = 0] = exp{−n} → 0

M3S3 SAMPLE EXAM SOLUTIONS - page 10 of 20

 so the sequence converges almost surely to infinity, as Xn = n for infinitely many n; let An
be the event An > M for any finite M . Then P (An occurs i.o.) = 1. In fact Xn converges to
infinity under all modes.

A more interesting question defines Xn as follows:

Xn (Z) = nI[n,∞) (Z) = n(1 − I[0,n) (Z))

in which case
P [Xn = 0] = P [Z ≤ n] = 1 − exp{−n} → 1
a.s.
as n → ∞, which makes things more interesting. Direct from the definition, we have Xn −→
0, as h i
P lim |Xn | < ² = 1
n→∞

or equivalently
lim P [|Xk | < ², ∀k ≥ n] = 1.
n→∞

To see this, for some n, n0 say, Z ∈ [0, n0 ), and thus for all k > n0 , Z ∈ [0, k) also, so
|Xk | = 0 < ².

Note that this result follows because we are considering a single Z that is used to define
the sequence {Xn }, so that the {Xn } are dependent random variables. If the {Xn } were
generated independently, using a sequence of independent rvs {Zn }, then assessment of
convergence would need use of, say, the Borel-Cantelli Lemma (b).

For convergence in rth mean for the new variable: note that

E[|Xn |r ] = nr P [Xn = n] + 0r P [Xn = 0] = nr exp{−n} + 0(1 − exp{−n}) → 0

r
as n → ∞, so Xn −→ 0 for all r > 0.
[5 MARKS]

(b) Suppose that X1 , X2 , . . . are independent, identically distributed random variables defined on R,
with common distribution function FX for which FX (x) < 1 for all finite x. Let Mn be the
maximum random variable defined for finite n by

Mn = max{X1 , X2 , . . . , Xn }

(i) Show that the sequence of random variables {Mn } converges almost surely to infinity, that is
a.s.
Mn −→ ∞

as n → ∞.

Hint: use the Borel-Cantelli lemma.

(ii) Now suppose that FX (xU ) = 1 for some xU < ∞. Find the almost sure limiting random
variable for the sequence {Mn }.

From M2S1 or first principles, the cdf of Mn is

n
Y
FMn (x) = P [Xi ≤ x, ∀i] = P [Xi ≤ x] = {FX (x)}n
i=1

M3S3 SAMPLE EXAM SOLUTIONS - page 11 of 20

(i) Now, note that, for any finite x,
∞
X ∞
X FX (x)
P [Mn ≤ x] = {FX (x)}n = <∞
1 − FX (x)
n=1 n=1

as FX (x) < 1, so we just have a geometric progression in FX (x). Now let

∞ [
\ ∞
Ax = lim sup(Mn ≤ x) = (Mk ≤ x).
n→∞
n=1 k=n

By the Borel-Cantelli Lemma (a),

· ¸
P [Mn ≤ x i.o.] = P lim sup(Mn ≤ x) = 0.
n→∞
S
Thus P (Ax ) = 0, for any finite x, and thus P ( x Ax ) = P (B) = 0 also, where the union
corresponds to an arbitrary interval in R. To complete the proof, we need to examine P (B 0 ),
and demonstrate that if ω ∈ B 0 , then

lim Mn (ω) = ∞
n→∞

that is, for all x, there exists n0 = n0 (ω, x) such that if n ≥ n0 then Mn (ω) ≥ x. Now,
∞ \
[ ∞
A0x = (Mk > x).
n=1 k=n
T
that is, if ω ∈ A0x then there exists an n such that for k ≥ n, Mn (ω) > x. Thus B 0 = 0
x Ax
has probability 1 under P , so that for all ω in sets of probability 1,

lim Mn (ω) = ∞.
n→∞

[5 MARKS]
a.s.
(ii) We demonstrate that Mn −→ xU . Fix ² > 0. Let En ≡ (Mn < xU − ²). Then
Ã∞ ∞ ! Ã∞ !
\ [ [
P [lim sup En ] = P Ek ≤ P En
n→∞
n=1 k=n n=1
∞
X
≤ P (En )
n=1
∞
X
= FX (xU − ²)n
n=1

< ∞

so by the Borel-Cantelli Lemma (a),

P [En occurs i.o.] = P [|Mn − xU | > ² i.o.] = 0

a.s.
and thus Mn −→ xU .
[5 MARKS]

M3S3 SAMPLE EXAM SOLUTIONS - page 12 of 20

 SAMPLE EXAM QUESTION 5 : SOLUTION

(a) Suppose that X1 , . . . , Xn are an independent and identically distributed sample from distribution
with density fX (x|θ), for vector parameter θ ∈ Θ ⊆ Rk . Suppose that fX is twice differentiable
with respect to the elements of θ, and let the true value of θ be denoted θ0 .

Define

(i) The Score Statistic (or Score function), S(X; θ).

(ii) The Fisher Information for a single random variable, I(θ)

(iii) The Fisher Information for the sample of size n, In (θ).

(iv) The Estimated or Observed Fisher Information, Iˆn (θ).

[I(θ) is sometimes called the unit Fisher Information; Iˆn (θ) is the estimator of I(θ)]

Give the asymptotic Normal distribution of the score statistic under standard regularity conditions,
when the data are distributed as a Normal distribution with mean zero and variance 1/θ.

Bookwork: Let X and x denote the vector of random variables/observations, let L denote the likelihood,
l denote the log likelihood, and let partial differentiation be denoted by dots.

(i) Score function:

n
X n
X
˙ X) = ∂ log L(θ; X) = ∂
S(X; θ) = l(θ; log fX|θ (Xi ; θ) =
∂
log fX|θ (Xi ; θ)
∂θ ∂θ ∂θ
i=1 i=1

where, by convention the partial differentiation yields a k × 1 column vector.

(ii) Unit Fisher Information:

· ½ ¾¸
∂ ∂
I(θ) = −EX1 |θ log fX|θ (X1 |θ)
∂θ ∂θ

where twice partial differentiation returns a k × k symmetric matrix. It can be shown that
£ ¤
I(θ) = EX1 |θ S(X1 ; θ)S(X1 ; θ)T

where S(X1 , θ) is the score function derived from X1 only.

(iii) Fisher Information for X1 , . . . , Xn :

· ½ ¾¸ " n ½ ¾#
∂ ∂ X ∂ ∂
In (θ) = −EX|θ log L(X; θ) = −EX|θ log fX|θ (Xi ; θ)
∂θ ∂θ ∂θ ∂θ
i=1

so it follows that £ ¤
In (θ) = nI(θ) = EX|θ S(X; θ)S(X; θ)T

M3S3 SAMPLE EXAM SOLUTIONS - page 13 of 20

(iv) Estimated/Observed Fisher Information:
n ½
X ¾ n
1 ∂ ∂ 1X
Iˆn (θ) = − log fX|θ (xi ; θ) = S(x; θ)S(x; θ)T
n ∂θ ∂θ n
i=1 i=1

where θ may be replaced by estimate b

θ if such an estimate is available. The estimated information from
ˆ
n data points is nIn (θ).
[8 MARKS]

If X1 . . . Xn ∼ N (0, θ−1 ) iid, then

µ ¶1/2 ½ ¾
θ θXi2
fX|θ (X1 |θ) = exp −
2π 2

1 1 θX12
log fX|θ (X1 |θ) = log θ − log (2π) −
2 2 2

∂ 1 X2
log fX|θ (X1 |θ) = − 1
∂θ 2θ 2

∂2 1
2 log fX|θ (X1 |θ) = −
∂θ 2θ2
Thus, as the expectation of the score function is zero, then
S(X; θ) ∼ AN (0, In (θ)) ≡ AN (0, 2n/θ2 )
where AN means asymptotically normal.
[2 MARKS]

(b) One class of estimating procedures for parameter θ involves solution of equations of the form
n
1X
Gn (θ) = Gi (Xi ; θ) = 0 (3)
n
i=1

for suitably defined functions Gi , i = 1, . . . , n.

(i) Show that maximum likelihood (ML) estimation falls into this class of estimating procedures.
For ML estimation, we find estimator b
θ, where
b
θ = arg max L(X; θ)
θ∈Θ

by, typically differentiating l(X; θ) partially in turn with respect to each component of θ, and
then setting the resulting derivative equations equal to zero, that is, we solve the system of
k equations
n n
∂ ∂ X X ∂
log l(X; θ) = log fX|θ (Xi |θ) = log fX|θ (Xi |θ) = 0
∂θ ∂θ ∂θ
i=1 i=1

which is of the same form as equation (3) with

∂
log fX|θ (Xi |θ)
Gi (Xi ; θ) ≡ n
∂θ
(Note that ML estimation does not always coincide with solving these equations,
as sometimes the arg max of the likelihood lies on the boundary of Θ).
[4 MARKS]

M3S3 SAMPLE EXAM SOLUTIONS - page 14 of 20

(ii) Suppose that θ̂n is a solution to (3) which is weakly consistent for θ.

Using a “one-step” approximation to G (motivated by a Taylor expansion of G around θ0 )

of the form
Gn (θ̂n ) = Gn (θ0 ) + (θbn − θ0 )Ġn (θ0 ),
where Ġn is the first partial derivative vector wrt the k components of θ, find an asymptotic
normal distribution of θ̂n .

State precisely the assumptions made in order to obtain the asymptotic Normal distribution.

Apologies, some lax notation here; this is a vector problem, and θ, θ0 , θbn and G are conventionally
k × 1 (column) vectors, and Ġn is a k × k matrix, so it makes more sense to write

Gn (b
θn ) = Gn (θ0 ) + Ġn (θ0 )(θbn − θ0 ) (4)

although working through with the form given, assuming row rather than column vectors, is OK.
Anyway, proceeding with column vectors:

Now, b θn is a solution to equation (3) by definition of the estimator, so rearranging equation (4)
√
after setting the LHS to zero and multiplying through by n yields
√ √
n Gn (θ0 ) = − n Ġn (θ0 )(b
θn − θ0 ). (5)

But also, by the Central Limit Theorem, under the assumption that

EX|θ0 [Gn (θ0 )] = 0

(that is, the usual “unbiasedness” assumption made for score equations), we have
√ L
nGn (θ0 ) −→ Z ∼ N (0, VG (θ0 ))

where
VG (θ0 ) = V arX|θ0 [Gn (θ0 )]
But, by analogy with the standard likelihood case, a natural assumption (that can be proved
formally) is that
a.s.
−Ġn (θ0 ) −→ VG (θ0 )
akin to the likelihood result that says the Fisher Information is minus one times the expectation
of the log likelihood second derivative matrix. Thus, from equation (5), we have by rearrangement
(formally, using Slutsky’s Theorem) that
√ √ L
n (b
θn − θ0 ) = (−Ġn (θ0 ))−1 n Gn (θ0 ) −→ VG (θ0 )−1 Z ∼ N (0, VG (θ0 )−1 )

under the assumption that (−Ġn (θ0 ))−1 exists.

This result follows in the same fashion as in the Cramer’s Theorem from lectures.

[6 MARKS]

M3S3 SAMPLE EXAM SOLUTIONS - page 15 of 20

 SAMPLE EXAM QUESTION 6 SOLUTION

(a) Suppose that X1 , . . . , Xn are a finitely exchangeable sequence of random variables with (De Finetti)
representation
Z ∞Y
n
p(X1 , . . . , Xn ) = fX|θ (Xi |θ)pθ (θ)dθ
−∞ i=1

In the following cases, find the joint probability distribution p(X1 , . . . , Xn ), and give an interpre-
tation of the parameter θ in terms of a strong law limiting quantity.

(i)

fX|θ (Xi |θ) = N ormal(θ, 1)

pθ (θ) = N ormal(0, τ 2 )

for parameter τ > 0.

We have
n n ½ ¾ ( n
)
Y Y 1 1 1 X
fX|θ (Xi |θ) = 1/2
exp − (Xi − θ)2 = (2π)−n/2 exp − (Xi − θ)2
(2π) 2 2
i=1 i=1 i=1

Now, in the usual decomposition

n
X n
X
2 2
(Xi − θ) = n(X̄ − θ) + (Xi − X̄)2
i=1 i=1

so
n
(
" n
#)
Y 1 X
fX|θ (Xi |θ) = (2π)−n/2 exp − n(X̄ − θ)2 + (Xi − X̄)2
2
i=1 i=1
n n o
= K1 (X, n) exp − (X̄ − θ)2
2
where ( )
n
−n/2 1X
K1 (X, n) = (2π) exp − (Xi − X̄)2 .
2
i=1

Now ½ ¾
1 1 2
pθ (θ) = exp − 2 θ
(2πτ 2 )1/2 2τ
so
n
Y n n o ½ ¾
2 1 1 2
fX|θ (Xi |θ)pθ (θ) = K1 (X, n) exp − (X̄ − θ) exp − 2 θ
i=1
2 (2πτ 2 )1/2 2τ

and combining the terms in the exponents, completing the square, we have
µ ¶2
2 2 2 2 nX̄ n/τ 2
n(X̄ − θ) + θ /τ = (n + 1/τ ) θ − + (X̄)2
n + 1/τ 2 n + 1/τ 2

M3S3 SAMPLE EXAM SOLUTIONS - page 16 of 20

 This uses the general (and useful) completing the square identity

A(x − a)2 + B(x − b)2 = (A + B)(x − (Aa + Bb)/(A + B))2 + ((AB)/(A + B))(a − b)2

with A = n, a = X̄, B = 1/τ 2 and b = 0. Thus

n
Y n η o
fX|θ (Xi |θ)pθ (θ) = K2 (X, n, τ 2 ) exp − n (θ − µn )2
2
i=1

where
½ ¾
K1 (X, n) n/τ 2
K2 (X, n, τ 2 ) = exp − (X̄)2
(2πτ 2 )1/2 2(n + 1/τ 2 )

nX̄
µn =
n + 1/τ 2

η n = (n + 1/τ 2 )

and thus
Z ∞ n
Y Z ∞ n η o
fX|θ (Xi |θ)pθ (θ)dθ = K2 (X, n, τ 2 ) exp − n (θ − µn )2 dθ
−∞ i=1 −∞ 2
p
= K2 (X, n, τ 2 ) 2π/η n

as the integrand is proportional to a Normal pdf.

The parameter θ in the conditional distribution for the Xi is the expectation. Thus, θ has
the interpretation
a.s.
X̄ −→ θ
as n → ∞. To see this more formally, we have the posterior distribution for θ from above as
n
Y n η o
n 2
pθ|X (θ|X = x) ∝ fX|θ (Xi |θ)pθ (θ) ∝ exp − (θ − µn )
2
i=1

so pθ|X (θ|X = x) ≡ N (µn , 1/η n ). As n → ∞,

nX̄ a.s.
µn = −→ E[Xi ]
n + 1/τ 2

and 1/η n → 0.

(ii)

fX|θ (Xi |θ) = Exponential(θ)

pθ (θ) = Gamma(α, β)

for parameters α, β > 0.

M3S3 SAMPLE EXAM SOLUTIONS - page 17 of 20

 We have
n n
( n
)
Y Y X
n
fX|θ (Xi |θ) = θ exp {−θXi } = θ exp −θ Xi
i=1 i=1 i=1

and
β α α−1
pθ (θ) = θ exp {−βθ}
Γ(α)
so
n
( n
)
Y X β α α−1
fX|θ (Xi |θ)pθ (θ) = θn exp −θ Xi θ exp {−βθ}
Γ(α)
i=1 i=1
( Ã n !)
βα X
n+α−1
= θ exp −θ Xi + β
Γ(α)
i=1

which yields
Z n
∞Y
βα Γ(n + α)
fX|θ (Xi |θ)pθ (θ)dθ = Ã n !n+α
0 Γ(α) X
i=1
Xi + β
i=1

as the integrand is proportional to a Gamma pdf.

Now, as
n
( Ã n !)
Y X
pθ|X (θ|X = x) ∝ fX|θ (Xi |θ)pθ (θ) ∝ θn+α−1 exp −θ Xi + β
i=1 i=1

so à !
n
X
pθ|X (θ|X = x) ≡ Ga n + α, Xi + β .
i=1

As n → ∞, this distribution becomes degenerate at

n 1 1
limn = lim =
n→∞ X n→∞ X̄ E[Xi ]
Xi
i=1

so θ is interpreted as the strong law limit of the reciprocal of the expected value of the Xi .
[5 MARKS]

M3S3 SAMPLE EXAM SOLUTIONS - page 18 of 20

 (b) In each of the two cases of part (a), compute the posterior predictive distribution

p(Xm+1 , . . . , Xm+n |X1 , . . . , Xm )

for 0 < n, m where X1 , . . . , Xm+n are a finitely exchangeable sequence.

Find in each case the limiting posterior predictive distribution as n −→ ∞.

[5 MARKS each]
We compute
Z ∞ m+n
Y
p(Xm+1 , . . . , Xm+n |X1 , . . . , Xm ) = fX|θ (Xi |θ)pθ|X (1) (θ|X (1) = x(1) )dθ
−∞ i=m+1

where X (1) = (X1 , . . . , Xm ).

In the first example;

pθ|X (1) (θ|X (1) = x(1) ) ≡ N (µ(1) , 1/η (1) ).

m+n
Y n n o
fX|θ (Xi |θ) = K1 (X (2) , n) exp − (X̄ (2) − θ)2
2
i=m+1

where µ(1) and η (1) are as defined earlier, computed for X (1) . The posterior predictive is computed in
a fashion similar to earlier, completing the square in θ to facilitate the integral; here we have by the
previous identity
à !2
(2) 2 (1) (1) 2 (1) nX̄ (2) + η (1) µ(1) nη (1)
n(X̄ − θ) + η (θ − µ ) = (n + η ) θ− + (X̄ (2) − µ(1) )2
n + η (1) n+η (1)

Thus, on integrating out θ, and cancelling terms, we obtain the posterior predictive as
( )Ã !1/2
nη (1) η (1)
K1 (X (2) , n) exp − (X̄ (2) − µ(1) )2
2(n + η (1) ) n + η (1)

In the second example;

³ ´
pθ|X (1) (θ|X (1) = x(1) ) ≡ Ga m + α, S (1) + β .

m+n
Y n o
fX|θ (Xi |θ) = θn exp −θS (2)
i=m+1

where
m
X n
X
S (1) = Xi S (2) = Xi
i=1 i=m+1

M3S3 SAMPLE EXAM SOLUTIONS - page 19 of 20

Thus
m+n
Y n o ¡S (1) + β ¢m+α
(1) (1) n (2)
fX|θ (Xi |θ)pθ|X (1) (θ|X = x ) = θ exp −θS θm+α−1 exp{−θ(S (1) + β)}
Γ(m + α)
i=m+1
¡ (1) ¢m+α
S +β
= θn+m+α−1 exp{−θ(S (1) + S (2) + β)}
Γ(m + α)

and on integrating out θ, as this form is proportional to a Gamma pdf, we obtain the posterior predictive
as ¡ (1) ¢m+α
S +β Γ(n + m + α)
¡ ¢n+m+α
Γ(m + α) S (1) + S (2) + β

In both cases, by the general theorem from lecture notes, the limiting posterior predictive when n → ∞
is merely the posterior distribution based on the sample X1 . . . , Xm .
[5 MARKS each]

M3S3 SAMPLE EXAM SOLUTIONS - page 20 of 20