Let X1, … , Xn. be a random sample from gamma (2, theta)
distribution.
a) Show that it is the regular case of the exponential class of
distributions.
b) Find a complete, sufficient statistic for theta.
c) Find the unique MVUE of theta. Justify each step.
3. Let X1...Xn be N(μX,σ) and Y1...Yn be iid N(μy,σ)
with the two samples X1...Xn, and Y1...Xn independent of each
other. Assume that the common population SD σ is known but the two
means are not. Consider testing the hypothesis null: μx = μy vs
alternative: μx ≠ μy.
d. Assume σ=1 and n=20. How large must δ be for the size
0.01 test to have power at least 0.99?
e. Assume σ=1and δ=0.2. How large must n be for...
3. Let X1...Xn be N(μX,σ) and Y1...Yn be iid N(μy,σ)
with the two samples X1...Xn, and Y1...Xn independent of each
other. Assume that the common population SD σ is known but the two
means are not. Consider testing the hypothesis null: μx = μy vs
alternative: μx ≠ μy.
a. Find the likelihood ratio test statistic Λ. Specify
which MLEs you are using and how you plug them in.
1. . Let X1, . . . , Xn, Y1, . . . , Yn be mutually independent
random variables, and Z = 1 n Pn i=1 XiYi . Suppose for each i ∈
{1, . . . , n}, Xi ∼ Bernoulli(p), Yi ∼ Binomial(n, p). What is
Var[Z]?
2. There is a fair coin and a biased coin that flips heads with
probability 1/4. You randomly pick one of the coins and flip it
until you get a...
4. (Reflected random walk) Let {Xn|n ≥ 0} be as in Q6. Show that
Xn+1 = X0 + Zn+1 − Xn m=0 min{0, Xm + Vm+1 − Um+1}, where Zn = Xn
m=1 (Vm − Um), n ≥ 1. Q5. (Extreme value process) Let {In|n ≥ 0} be
an i.i.d. sequence of Z-valued random variables such that P{I1 = k}
= pk, k ∈ Z and pk > 0 for some k > 0. Define Xn = max{I1,
I2, ·...
Let X1,...,Xn be independent random
variables,and let X=X1+...+Xn be their
sum.
1. Suppose that each Xi is geometric with respective
parameter pi. It is known that the mean of X is equal to
μ, where μ > 0. Show that the variance of X is minimized if the
pi's are all equal to n/μ.
2. Suppose that each Xi is Bernoulli with respective
parameter pi. It is known that the mean of X is equal to
μ, where μ >...
Let X1, X2, . . . , Xn be a random sample of size n from a
Poisson distribution with unknown mean µ. It is desired to test the
following hypotheses
H0 : µ = µ0
versus H1 : µ not equal to µ0
where µ0 > 0 is a given constant. Derive the likelihood ratio
test statistic
Let X1, X2, · · · , Xn (n ≥ 30)
be i.i.d observations from N(µ1,
σ12 ) and Y1, Y2, · · ·
, Yn be i.i.d observations from N(µ2,
σ22 ). Also assume that X's and Y's are
independent. Suppose that µ1, µ2,
σ12 ,
σ22 are unknown. Find an
approximate 95% confidence interval for
µ1µ2.
2. Let X1, . . . , Xn be a random sample from the distribution
with pdf given by fX(x;β) = β 1(x ≥ 1).
xβ+1
(a) Show that T = ni=1 log Xi is a sufficient statistic for β.
Hint: Use
n1n1n=exp log=exp −logxi .i=1 xi i=1 xi i=1
(b) Find the pdf of Y = logX, where X ∼ fX(x;β).
(c) Find the distribution of T . Hint: Identify the distribution of
Y and use mgfs.
(d) Find...