Professional Documents
Culture Documents
ABSTRACT
In this paper, the double Pareto distribution is considered for Bayesian analysis. The expressions for Bayes estimators of
the parameter have been derived under squared error, precautionary, entropy, K-loss, and Al-Bayyati’s loss functions by
using quasi and gamma priors.
KEYWORDS: Bayesian Method, Double Pareto Distribution, Quasi and Gamma Priors, Squared Error, Precautionary,
Entropy, K-Loss, and Al-Bayyati’s Loss Functions
Article History
Received: 18 Aug 2020 | Revised: 26 Aug 2020 | Accepted: 02 Sep 2020
1. INTRODUCTION
The double Pareto distribution has been proposed by Reed [1] as a model for heavy-tailed phenomena. Al-Athari [2]
considered the parameter estimation for this distribution. The probability density function of double Pareto distribution is
given by
θ +1
θ a
f ( x;θ ) = θ x −( a +1) e−θ x
−a
; x ≥ a. (1)
2a x
n
x
− (θ +1) ∑ log ai
f ( x;θ ) = ( 2a ) θ e
−n n i =1
(2)
n
x
log f ( x;θ ) = − n log 2a + n log θ − (θ + 1) ∑ log i . (3)
i =1 a
Differentiating (3) with respect to θ and equating to zero, we get the maximum likelihood estimator of θ which is
given as
∧ n
θ= . (4)
n
x
∑
i =1
log i
a
www.iaset.us editor@iaset.us
32 Arun Kumar Rao & Himanshu Pandey
The Bayesian inference procedures have been developed generally under squared error loss function
2
∧ ∧
L θ ,θ = θ − θ . (5)
∧
The Bayes estimator under the above loss function, say, θ s is the posterior mean, i.e.,
∧
θ S = E (θ ) . (6)
Zellner [3] and Basu & Ebrahimi [4] have recognized that the inappropriateness of using symmetric loss function.
Norstrom [5] introduced precautionary loss function is given as
2
∧
θ − θ
∧ .
L θ ,θ = ∧
(7)
θ
∧
The Bayes estimator under this loss function is denoted by θP and is given by
∧
θ P = E (θ 2 )
1
2
. (8)
Calabria and Pulcini [6] points out that a useful asymmetric loss function is the entropy loss
∧
θ ∧
Where δ = , and whose minimum occurs at θ = θ . Also, the loss function L (δ ) has been used in Dey et al.
θ
[7] and Dey and Liu [8], in the original form having p = 1. Thus L (δ ) can written be as
∧
The Bayes estimator under entropy loss function is denoted by θE and is obtained by solving the following
equation
−1
∧ 1
θ E = E . (10)
θ
2
∧
∧ θ − θ
L θ ,θ = ∧ . (11)
θθ
∧
Under K-loss function the Bayes estimator of θ is denoted by θK and is obtained as
1
∧ E (θ ) 2
θK = . (12)
E (1 θ )
Al-Bayyati[10] introduced a new loss function which is given as
2
∧ ∧
L θ ,θ = θ c θ − θ . (13)
∧
Under Al-Bayyati’s loss function the Bayes estimator of θ is denoted by θ Al and is obtained as
∧
θ Al =
( ).
E θ c +1
E (θ ) c
(14)
• Quasi-prior: For the situation where we have no prior information about the parameter θ, we may use the quasi
density as given by
1
g1 (θ ) = ; θ > 0, d ≥ 0, (15)
θd
Where d = 0 leads to a diffuse prior and d = 1, a non-informative prior.
• Gamma prior: Generally, the gamma density is used as prior distribution of the parameter θ given by
β α α −1 − βθ
g 2 (θ ) = θ e ; θ > 0. (16)
Γ (α )
n
x
−(θ +1) ∑ log ai
( 2a ) θ
−n n
e i =1
θ −d
f (θ x ) = n
x
∞ − (θ +1) ∑ log ai
∫ ( 2a )
−n
θ e
n i =1
θ − d dθ
0
www.iaset.us editor@iaset.us
34 Arun Kumar Rao & Himanshu Pandey
n
x
−θ ∑ log ai
θ n−d
e i =1
= n
x
∞ −θ ∑ log ai
∫θ dθ
n−d i =1
e
0
n − d +1
n xi
∑ log a
n
x
−θ ∑ log ai
= i =1 θ n−d
e i =1
(17)
Γ ( n − d + 1)
Γ ( n − d + c + 1) n
−c
xi
E θ( )c
= ∑ log .
Γ ( n − d + 1) i =1 a
(18)
Proof By definition,
( )
E θ c = ∫ θ c f (θ x ) dθ
n + d −1
n xi
∑ log a
n
x
∞ −θ ∑ log ai
= i =1
−( n − d + c )
Γ ( n + d − 1) ∫θ 0
e i =1
dθ
n − d +1
n xi
∑ log a Γ ( n − d + c + 1)
= i =1
Γ ( n − d + 1) n xi
n − d + c +1
∑ log a
i =1
Γ ( n − d + c + 1) n
−c
xi
= ∑ log .
Γ ( n − d + 1) i =1 a
−1
n x
E (θ ) = ( n − d + 1) ∑ log i . (19)
i =1 a
−2
n
E θ( )2 x
= ( n − d + 2 )( n − d + 1) ∑ log i
a
.
(20)
i =1
1 1 n
x
E = ∑
θ ( n − d ) i =1
log i
a
.
(21)
−( c +1)
Γ ( n − d + c + 2) n xi
(
E θ c +1 = ) ∑ log
Γ ( n − d + 1) i =1 a
. (22)
From equation (6), on using (19), the Bayes estimator of θ under squared error loss function is given by
−1
∧ n x
θ S = ( n − d + 1) ∑ log i . (23)
i =1 a
From equation (8), on using (20), the Bayes estimator of θ under precautionary loss function is obtained as
−1
∧ n x
1
θ P = ( n − d + 2 )( n − d + 1) ∑ log i .
2 (24)
i =1 a
From equation (10), on using (21), the Bayes estimator of θ under entropy loss function is given by
−1
∧ n
xi
θ E = ( n − d ) ∑ log . (25)
i =1 a
From equation (12), on using (19) and (21), the Bayes estimator of θ under K-loss function is given by
−1
∧ n x
θ K = ( n − d + 1)( n − d ) ∑ log i .
1
2
(26)
i =1 a
From equation (14), on using (18) and (22), the Bayes estimator of θ under Al-Bayyati’s loss function comes out
to be
−1
∧ n x
θ Al = ( n − d + c + 1) ∑ log i . (27)
i =1 a
www.iaset.us editor@iaset.us
36 Arun Kumar Rao & Himanshu Pandey
n
∑ log ai β α α −1 − βθ
x
− (θ +1)
( 2a ) θ
−n n
e i =1
θ e
Γ (α )
f (θ x ) = n
x
∞ −(θ +1) ∑ log ai β α α −1 − βθ
∫ ( 2a )
−n
θ e n i =1
θ e dθ
0
Γ (α )
n
x
∑
− β + log i θ
θ n +α −1 e i =1 a
=
n
x
∞
n +α −1 ∑
− β + log i θ
∫θ
a
e i =1
dθ
0
n
x
∑
− β + log i θ
θ n +α −1 e i =1 a
= n +α
n
x
Γ (n + α ) β + ∑ log i
i =1 a
n +α
n
x
β + ∑ log i
a
n
∑
x
− β + log i
θ
= i =1 n +α −1 a
θ e i =1
(28)
Γ (n + α )
Γ (n + α + c)
−c
( ) x
n
E θ c
=
Γ (n + α )
β + ∑
i =1
log i
a
.
(29)
Proof By definition,
( )
E θ c = ∫ θ c f (θ x ) dθ
n +α
n
x
β + ∑ log i
a
∞
∑
n
x
− β + log i
θ
= i =1 n +α + c −1 a
Γ (n +α ) ∫θ
0
e i =1
dθ
n +α
n
x
β + ∑ log i
a Γ (n + α + c)
= i =1
Γ (n + α ) n
xi
n +α + c
β + ∑ log a
i =1
Γ (n + α + c)
−c
n
x
=
Γ (n + α )
β + ∑
i =1
log i
a
.
−1
n
x
E (θ ) = ( n + α ) β + ∑ log i . (30)
i =1 a
−2
( ) x
n
E θ 2
= ( n + α + 1)( n + α ) β + ∑ log i . (31)
i =1 a
1 1 n
x
E =
θ ( n + α − 1)
β + ∑
i =1
log i
a
.
(32)
−( c +1)
Γ ( n + α + c + 1) x
( )
n
E θ c +1
=
Γ (n + α )
β + ∑
i =1
log i
a
. (33)
From equation (6), on using (30), the Bayes estimator of θ under squared error loss function is given by
−1
∧ n
x
θ S = ( n + α ) β + ∑ log i . (34)
i =1 a
From equation (8), on using (31), the Bayes estimator of θ under precautionary loss function is obtained as
−1
∧ n
x
θ P = ( n + α + 1)( n + α ) β + ∑ log i
1
2
. (35)
i =1 a
From equation (10), on using (32), the Bayes estimator of θ under entropy loss function is given by
−1
∧ n
x
θ E = ( n + α + 1) β + ∑ log i . (36)
i =1 a
From equation (12), on using (30) and (32), the Bayes estimator of θ under K-loss function is given by
−1
∧ n
x
θ K = ( n + α )( n + α − 1) 2 β + ∑ log i
1
(37)
i =1 a
From equation (14), on using (29) and (33), the Bayes estimator of θ under Al-Bayyati’s loss function comes out
to be
www.iaset.us editor@iaset.us
38 Arun Kumar Rao & Himanshu Pandey
−1
∧ n
x
θ Al = ( n + α + c ) β + ∑ log i . (38)
i =1 a
CONCLUSIONS
In this paper, we have obtained a number of estimators of parameter of double Pareto distribution. In equation (4) we have
obtained the maximum likelihood estimator of the parameter. In equation (23), (24), (25), (26) and (27) we have obtained
the Bayes estimators under different loss functions using quasi prior. In equation (34), (35), (36), (37) and (38) we have
obtained the Bayes estimators under different loss functions using gamma prior. In the above equation, it is clear that the
Bayes estimators depend upon the parameters of the prior distribution. We therefore recommend that the estimator’s choice
lies according to the value of the prior distribution which in turn depends on the situation at hand.
REFERENCES
1. Reed, W.J., (2001): “The Pareto, Zipf and other power laws”. Econ. Lett., 74: 15-19. DOI: 10.1016/S0165-
1765(01) 00524-9.
2. Al-Athari, F.M., (2011): “Parameter estimation for the double Pareto distribution”. Journal of Mathematics and
Statistics, 7(4): 289-294.
3. Zellner, A., (1986):“Bayesian estimation and prediction using asymmetric loss functions”. Jour. Amer. Stat.
Assoc., 91, 446-451.
4. Basu, A. P. and Ebrahimi, N., (1991):“Bayesian approach to life testing and reliability estimation using
asymmetric loss function”. Jour. Stat. Plann. Infer., 29, 21-31.
5. Norstrom, J. G., (1996):“The use of precautionary loss functions in Risk Analysis”. IEEE Trans. Reliab., 45(3),
400-403.
6. Calabria, R., and Pulcini, G. (1994): “Point estimation under asymmetric loss functions for left truncated
exponential samples”. Comm. Statist. Theory & Methods, 25 (3), 585-600.
7. D.K. Dey, M. Ghosh and C. Srinivasan (1987): “Simultaneous estimation of parameters under entropy loss”.
Jour. Statist. Plan. And infer., 347-363.
8. D.K. Dey, and Pei-San Liao Liu (1992): “On comparison of estimators in a generalized life Model”.
Microelectron. Reliab. 32 (1/2), 207-221.
10. Al-Bayyati, (2002): “Comparing methods of estimating Weibull failure models using simulation”. Ph.D. Thesis,
College of Administration and Economics, Baghdad University, Iraq.