Scribd
Upload
39 views2 pages

Homework For 2/10 Due 2/19: Name: ID

1. For an i.i.d. sample from a geometric distribution, the sufficient statistic is the sum of the random variables, as the factorization theorem can be applied. 2. For an i.i.d. sample from a distribution with density f(x|θ) = θ/(1+x)θ+1, the sufficient statistic is the sum of the log(1+Xi), as this distribution belongs to a one-parameter exponential family. 3. For an i.i.d. sample from a Rayleigh distribution, the sufficient statistic is the sum of the X_i^2, as the Rayleigh distribution belongs to a one-parameter exponential family with the sufficient statistic

Uploaded by

HoghunsholaStephenAdeshina
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
39 views2 pages

Homework For 2/10 Due 2/19: Name: ID

1. For an i.i.d. sample from a geometric distribution, the sufficient statistic is the sum of the random variables, as the factorization theorem can be applied. 2. For an i.i.d. sample from a distribution with density f(x|θ) = θ/(1+x)θ+1, the sufficient statistic is the sum of the log(1+Xi), as this distribution belongs to a one-parameter exponential family. 3. For an i.i.d. sample from a Rayleigh distribution, the sufficient statistic is the sum of the X_i^2, as the Rayleigh distribution belongs to a one-parameter exponential family with the sufficient statistic

Uploaded by

HoghunsholaStephenAdeshina
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

Name:

ID:

Homework for 2/10 Due 2/19


1. [8-69] Use the factorization theorem (Theorem A in Section 8.8.1) to
n
X
conclude that T =
Xi is a sufficient statistic when the Xi are an i.i.d.
i=1

sample from a geometric distribution.


The joint pmf of the random sample X1 , . . . , Xn from a geometric distribution with parameter p is
Pn

f (x1 , . . . , xn |p) = pn (1 p)

i=1

xi n

= pn (1 p)T (x1 ,...,xn )n 1.

Therefore the Factorization Theorem, with


g(t, p) = pn (1 p)tn
tells us that T =

n
X

and

h(x1 , . . . , xn ) = 1,

Xi is a sufficient statistic for the geometric distribu-

i=1

tion.

2. [8-71] Let X1 , . . . , Xn be an i.i.d. sample from a distribution with the


density function
f (x|) =

,
(1 + x)+1

0 < < and 0 x < .

Find a sufficient statistic for .


Since the pdf satisfies
f (x|) = exp { log(1 + x) + log log(1 + x)} ,

0x<

this distribution belongs to 1-parameter exponential family and a sufficient


statistics is
n
n
X
X
T (Xi ) =
log(1 + Xi ).
i=1

i=1

3. [8-73] Find a sufficient statistic for the Rayleigh density,

x ex2 /(22 ) , x 0
.
f (x|) = 2
0,
otherwise
The pdf of the Rayleigh density satisfies




exp 1 x2 2 log + log x , x 0


22
f (x|) =
.

0,
otherwise
It follows that the Rayleigh distribution is a member of 1-parameter exponential family with
1
,
22
d() = 2 log ,

c() =

T (x) = x2 ,
S(x) = log x.

It follows that a sufficient statistic is


n
n
X
X
Xi2
T (Xi ) =
i=1

i=1

for a random sample X1 , . . . , Xn .


4. [8-74] Show that the binomial distribution belongs to the exponential
family (the parameter n is assumed to be known).
The pmf of X Bin(n, p) (n is assumed to be known) is
 
n x
f (x|n, p) =
p (1 p)nx
x

 
p
n
= exp x log
+ n log(1 p) + log
.
1p
x
It follows that Bin(n, p) with known n is a member of 1-parameter exponential family with
p
c() = log
,
T (x) = x,
1p
 
n
d() = n log(1 p),
S(x) = log
.
x
Remark: 1-parameter exponential family has pdf/pmf of the form
(
exp {c()T (x) + d() + S(x)} , x A
f (x|) =
.
0,
x
/A

You might also like

pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy