1. Recall the setting of Question 1 in Assignment 2. That is that we have an iid sample assumed to come from an exponential distribution where the true rate parameter is unknown i.e. X₁,..., Xn~ Exponential(o) such that fo(x) = Ao exp(-x) for x>0 You may cite any answers to anything from assignment 2 to avoid re-calculating things here. (a) Assume that the sample size n is very large. State the asymptotic distri- bution that the MLE À takes as a function of Xo. (b) Notice that the Variance of this asymptotic distribution is a function of the true parameter Ao. State an appropriate approximation that we can make and the resulting (approximate) asymptotic distribution of Â. (c) By using the large sample approximate sampling distribution from the previous question for Â, provide an expression as a function of n and  for Pxo (A - Ao|> 0.5)

MATLAB: An Introduction with Applications
6th Edition
ISBN:9781119256830
Author:Amos Gilat
Publisher:Amos Gilat
Chapter1: Starting With Matlab
Section: Chapter Questions
Problem 1P
icon
Related questions
Question

please answer follow questions

1. Recall the setting of Question 1 in Assignment 2. That is that we have an iid
sample assumed to come from an exponential distribution where the true rate
parameter is unknown i.e. X₁,..., Xn~ Exponential (Ao) such that
fao(x)= Ao exp(-Xox) for x>0
You may cite any answers to anything from assignment 2 to avoid re-calculating
things here.
(a) Assume that the sample size n is very large. State the asymptotic distri-
bution that the MLE À takes as a function of Xo.
(b) Notice that the Variance of this asymptotic distribution is a function of
the true parameter Ao. State an appropriate approximation that we can
make and the resulting (approximate) asymptotic distribution of Â.
(c) By using the large sample approximate sampling distribution from the
previous question A, provide an expression as a function of n and  for
PA, (|Â - Ao > 0.5)
(d) Suppose that a reparametrisation is made such that µ = g(X) = 1/λ. By
using the Delta method derive an expression for the approximate large
sample distribution of in terms of û and n.
û
(e) Similarly to (c) but now in terms of the new reparametrisation find an
expression for the following in terms of û and n
PHO (μ- Mol 0.5)
(f) You may use without proof that the sum of n independent Exponential(3)
random variables is distributed as a Gamma(n, 3) with density:
xn-le-Bx for x > 0
f(x) =
Bn
T(n)
(i) State the MLE û for u.
(ii) Identify the true distribution for û in terms of μo.
(iii) Suppose that an oracle tells you that po = 25 and you are seeing a
sample of size n = 100. Calculate the TRUE value of
Po (Hol> 0.5)
You may find the command pgamma(.) in R to be useful.
(iv) However, we don't know Ho in practice so you wouldn't actually be
able to make that calculation in (iii).
Using the result in (e) and assuming that the observed MLE was μ =
21.79 find an (approximate) value for
Po (μ- Ho|> 0.5)
(v) It is proposed that the true value of µ is 23. Construct an appropriate
hypothesis test to assess this conjecture and evaluate the correspond-
ing p-value.
(g) Assume that you are working again in the parametrisation of A. Suppose
that the sample size is large and that the asymptotic normality of the MLE
applies. Using your working from (c) (so that you don't need to repeat
calculations) Find (as a function of A and n) the value of the constant a
such that
P(|Â A₂ > a) = 0.05
Transcribed Image Text:1. Recall the setting of Question 1 in Assignment 2. That is that we have an iid sample assumed to come from an exponential distribution where the true rate parameter is unknown i.e. X₁,..., Xn~ Exponential (Ao) such that fao(x)= Ao exp(-Xox) for x>0 You may cite any answers to anything from assignment 2 to avoid re-calculating things here. (a) Assume that the sample size n is very large. State the asymptotic distri- bution that the MLE À takes as a function of Xo. (b) Notice that the Variance of this asymptotic distribution is a function of the true parameter Ao. State an appropriate approximation that we can make and the resulting (approximate) asymptotic distribution of Â. (c) By using the large sample approximate sampling distribution from the previous question A, provide an expression as a function of n and  for PA, (| - Ao > 0.5) (d) Suppose that a reparametrisation is made such that µ = g(X) = 1/λ. By using the Delta method derive an expression for the approximate large sample distribution of in terms of û and n. û (e) Similarly to (c) but now in terms of the new reparametrisation find an expression for the following in terms of û and n PHO (μ- Mol 0.5) (f) You may use without proof that the sum of n independent Exponential(3) random variables is distributed as a Gamma(n, 3) with density: xn-le-Bx for x > 0 f(x) = Bn T(n) (i) State the MLE û for u. (ii) Identify the true distribution for û in terms of μo. (iii) Suppose that an oracle tells you that po = 25 and you are seeing a sample of size n = 100. Calculate the TRUE value of Po (Hol> 0.5) You may find the command pgamma(.) in R to be useful. (iv) However, we don't know Ho in practice so you wouldn't actually be able to make that calculation in (iii). Using the result in (e) and assuming that the observed MLE was μ = 21.79 find an (approximate) value for Po (μ- Ho|> 0.5) (v) It is proposed that the true value of µ is 23. Construct an appropriate hypothesis test to assess this conjecture and evaluate the correspond- ing p-value. (g) Assume that you are working again in the parametrisation of A. Suppose that the sample size is large and that the asymptotic normality of the MLE applies. Using your working from (c) (so that you don't need to repeat calculations) Find (as a function of A and n) the value of the constant a such that P(| A₂ > a) = 0.05
Expert Solution
steps

Step by step

Solved in 5 steps with 34 images

Blurred answer
Recommended textbooks for you
MATLAB: An Introduction with Applications
MATLAB: An Introduction with Applications
Statistics
ISBN:
9781119256830
Author:
Amos Gilat
Publisher:
John Wiley & Sons Inc
Probability and Statistics for Engineering and th…
Probability and Statistics for Engineering and th…
Statistics
ISBN:
9781305251809
Author:
Jay L. Devore
Publisher:
Cengage Learning
Statistics for The Behavioral Sciences (MindTap C…
Statistics for The Behavioral Sciences (MindTap C…
Statistics
ISBN:
9781305504912
Author:
Frederick J Gravetter, Larry B. Wallnau
Publisher:
Cengage Learning
Elementary Statistics: Picturing the World (7th E…
Elementary Statistics: Picturing the World (7th E…
Statistics
ISBN:
9780134683416
Author:
Ron Larson, Betsy Farber
Publisher:
PEARSON
The Basic Practice of Statistics
The Basic Practice of Statistics
Statistics
ISBN:
9781319042578
Author:
David S. Moore, William I. Notz, Michael A. Fligner
Publisher:
W. H. Freeman
Introduction to the Practice of Statistics
Introduction to the Practice of Statistics
Statistics
ISBN:
9781319013387
Author:
David S. Moore, George P. McCabe, Bruce A. Craig
Publisher:
W. H. Freeman