International Journal of Statistics and Applications 2016, 6(4): 189-202

DOI: 10.5923/j.statistics.20160604.01

Devya Distribution and Its Applications

Rama Shanker

Department of Statistics, Eritrea Institute of Technology, Asmara, Eritrea

Abstract A new one parameter lifetime distribution named, ‘Devya Distribution’ for modeling lifetime data from
engineering and biomedical science, has been proposed. Its statistical and mathematical properties including shape, moments,
coefficient of variation, skewness, kurtosis, hazard rate function, mean residual life function, stochastic ordering, mean
deviations, Bonferroni and Lorenz curves have been discussed. The condition under which the proposed distribution is
over-dispersed, equi-dispersed, and under-dispersed has been given along with other one parameter lifetime distributions.
The method of maximum likelihood and the method of moments have been discussed for estimating its parameter. The
goodness of fit of the proposed distribution over one parameter exponential, Lindley, Shanker, Akash, Aradhana, Sujatha,
and Amarendra distributions have been given with two real lifetime data sets.
Keywords Lifetime distributions, Moments, Mathematical and Statistical properties, Estimation of parameter, Goodness
of fit

θ + 1 + θ x −θ x
F1 ( x,θ ) =
1− e ; x > 0, θ > 0 (1.2)
1. Introduction θ +1
The important lifetime distributions for modeling lifetime The density (1.1) is a two-component mixture of an
data available in statistical literature are exponential, Lindley, exponential (θ ) distribution and a gamma ( 2,θ )
Akash, Shanker, Aradhana, Sujatha, Amarendra, gamma, θ 1
lognormal, and Weibull. The exponential, Lindley, Akash, distribution with their mixing proportions and
Shanker, Aradhana, Sujatha, Amarendra and Weibull θ +1 θ +1
respectively. Ghitany et al (2008) have discussed various
distributions are easy to apply for modeling lifetime data
properties of this distribution and showed that in many ways
than the gamma and the lognormal distributions because the
(1.1) provides a better model for some applications than the
survival functions of the gamma and the lognormal
exponential distribution. The Lindley distribution has been
distributions cannot be expressed in closed forms and both modified, extended, mixed and generalized suiting their
require numerical integration. Exponential, Lindley, Akash, applications in different fields of knowledge by many
Shanker, Aradhana, Sujatha and Amarendra distributions researchers including Sankaran (1970), Zakerzadeh and
consists of one parameter and Lindley, Akash, Shanker, Dolati (2009), Nadarajah et al (2011), Deniz and Ojeda
Aradhana, Sujatha and Amarendra distributions have (2011), Bakouch et al (2012), Shanker and Mishra (2013 a,
advantage over exponential distribution that the exponential 2013 b, 2016), Shanker and Amanuel (2013), Shanker et al
distribution has constant hazard rate whereas Lindley, Akash, (2013), Elbatal et al (2013), Ghitany et al (2013), Merovci
Shanker, Aradhana, Sujatha and Amarendra distributions (2013), Ashour and Eltehiwy (2014), Oluyede and Yang
have monotonically increasing hazard rate. Further, the (2014), Singh et al (2014), Sharma et al (2015), Shanker and
nature of Amarendra distribution is more flexible than Hagos (2015), Alkarni (2015), Pararai et al (2015),
exponential, Lindley, Akash, Shanker, Aradhana, and Abouammoh et al (2015), Shanker et al (2015, 2016 a, 2016
Sujatha distributions for modeling lifetime data. b, 2016 c) are some among others.
The probability density function (p.d.f.) and the The probability density function (p.d.f.) and the
cumulative distribution function (c.d.f.) of Lindley (1958) cumulative distribution function (c.d.f.) of Akash
distribution are given by distribution introduced by Shanker (2015 a) are given by

θ2 θ3
f1 ( x;θ=
)
θ +1
(1 + x ) e−θ x ; x > 0, θ > 0 (1.1) f 2 ( x;=
θ)
θ 2
+2
(1 + x 2 ) e −θ x ; x > 0, θ > 0 (1.3)

 θ x (θ x + 2 )  −θ x
* Corresponding author: F2 ( x;θ ) =1 − 1 + e ; x > 0, θ > 0 (1.4)
[email protected] (Rama Shanker)
 θ2 + 2 
Published online at http://journal.sapub.org/statistics
Copyright © 2016 Scientific & Academic Publishing. All Rights Reserved The density (1.3) is a two-component mixture of an
190 Rama Shanker: Devya Distribution and Its Applications

exponential (θ ) distribution and a gamma ( 3,θ ) properties, discussed the estimation of parameter and
applications for count data-sets from different fields of
θ2 knowledge.
distribution with their mixing proportions and
θ2 + 2 The probability density function (p.d.f.) and the
cumulative distribution function (c.d.f.) of Aradhana
2 distribution introduced by Shanker (2016 e) are given by
respectively. Shanker (2015 a) has discussed its
2
θ +2 3
θ
various mathematical and statistical properties including its = f 4 ( x;θ ) 2
(1 + x )2 e−θ x ; x > 0, θ > 0 (1.7)
shape, moment generating function, moments, skewness, θ + 2θ + 2
kurtosis, hazard rate function, mean residual life function,
stochastic orderings, mean deviations, distribution of order  θ x (θ x + 2θ + 2 )  −θ x
statistics, Bonferroni and Lorenz curves, Renyi entropy F4 ( x;θ ) = 1 − 1 +  e ; x > 0,θ > 0 (1.8)
 θ 2 + 2θ + 2 
measure, stress-strength reliability, estimation of parameter
and applications. Shanker et al (2016 c) has detailed and The density (1.7) is a three-component mixture of an
critical study about modeling and analyzing lifetime data exponential (θ ) distribution, a gamma ( 2,θ ) distribution,
from various fields of knowledge using one parameter Akash,
Lindley and exponential distributions. Shanker (2016 a) has and a gamma ( 3,θ ) distribution with their mixing
obtained Poisson mixture of Akash distribution named,
Poisson-Akash distribution (PAD) and discussed its various proportions
θ2 2θ 2
, and ,
2 2 2
mathematical and statistical properties, estimation of its θ + 2θ + 2 θ + 2θ + 2 θ + 2θ + 2
parameter and applications for various count data-sets. respectively. Shanker (2016 e) has discussed its various
Further, Shanker (2016 b, 2016 c) has also obtained the statistical and mathematical properties, estimation of
size-biased and zero-truncated versions of PAD, derived parameter and applications for modeling lifetime data from
their important mathematical and statistical properties, and biomedical science and engineering. Shanker (2016 f) has
discussed the estimation of parameter and applications for obtained Poisson-Aradhana distribution (PAD), a Poisson
count data-sets. mixture of Aradhana distribution and showed that PAD gives
The probability density function (p.d.f.) and the a better fit than Poisson-distribution and Poisson-Lindley
cumulative distribution function (c.d.f.) of Shanker distribution (PLD) for modeling count data. Further, Shanker
distribution introduced by Shanker (2015 b) are given by and Hagos (2016 c, 2016 d) have derived size-biased and
zero-truncated versions of PAD and discussed their
θ2 −θ x mathematical and statistical properties, estimation of
;θ )
f3 ( x= 2
(θ + x ) e ; x > 0, θ > 0 (1.5) parameter using maximum
θ +1 likelihood estimation and method
of moments and discussed their applications.

F3 ( x;θ ) = 1−
( )
θ 2 +1 +θ x
e −θ x
; x > 0, θ > 0
The probability density function (p.d.f.) and the
(1.6) cumulative distribution function (c.d.f.) of Sujatha
θ 2 +1 distribution introduced by Shanker (2016 g) are given by
The density (1.5) is a two-component mixture of an
θ3
exponential (θ ) distribution and a gamma ( 2,θ ) = f5 ( x;θ ) ( )
1 + x + x 2 e−θ x ; x > 0, θ > 0 (1.9)
θ 2 +θ + 2
2
θ
distribution with their mixing proportions and  θ x (θ x + θ + 2 )  −θ x
θ 2 +1 F5 ( x,θ ) =1 − 1 + e ; x > 0,θ > 0 (1.10)
1  θ 2 +θ + 2 
respectively. Shanker (2015 b) has discussed its
2
θ +1 The density (1.9) is a three-component mixture of an
various mathematical and statistical properties including its exponential (θ ) distribution. a gamma ( 2,θ ) distribution,
shape, moment generating function, moments, skewness,
kurtosis, hazard rate function, mean residual life function, and a gamma ( 3,θ ) distribution with their mixing
stochastic orderings, mean deviations, distribution of order θ2 θ 2
statistics, Bonferroni and Lorenz curves, Renyi entropy proportions , and
2 2 2
measure, stress-strength reliability, estimation of parameter θ +θ + 2 θ +θ + 2 θ +θ + 2
and applications. Shanker (2016 d) has obtained Poisson respectively. Shanker (2016 g) has discussed its various
mixture of Shanker distribution named Poisson-Shanker mathematical and statistical properties including its shape,
distribution (PSD) and discussed its various mathematical moment generating function, moments, skewness, kurtosis,
and statistical properties, estimation of its parameter and hazard rate function, mean residual life function, stochastic
applications for various count data-sets. Shanker and Hagos orderings, mean deviations, Bonferroni and Lorenz curves,
(2016 a, 2016 b) have obtained the size-biased and stress-strength reliability, some amongst others. Further,
zero-truncated versions of Poisson-Shanker distribution Shanker (2016 h) has obtained Poisson mixture of Sujatha
(PSD), derived their interesting mathematical and statistical distribution named Poisson-Sujatha distribution (PSD) and
 International Journal of Statistics and Applications 2016, 6(4): 189-202 191

discussed its various mathematical and statistical properties, extensive study on comparative study of zero-truncated
estimation of its parameter and applications for various count Poisson, Poisson-Lindley and Poisson-Sujatha distribution
data-sets. Shanker and Hagos (2016 e, 2016 f) have obtained and shown that in most of the data-sets from demography
the size-biased and zero-truncated versions of and biological sciences zero-truncated Poisson-Sujatha
Poisson-Sujatha distribution (PSD), derived their interesting distribution gives much closer fit.
mathematical and statistical properties, and discussed their The probability density function and the cumulative
estimation of parameter and applications for count data-sets. distribution function of Amarendra distribution introduced
Shanker and Hagos (2016 g) has detailed study about by Shanker (2016 i) are given by
applications of PSD for modeling count data from biological
sciences. Shanker and Hagos (2016 h) has also done an

θ4
f 6 ( x;θ )
= 3
θ +θ 2
+ 2θ + 6
(1 + x + x 2 + x3 ) e−θ x ; x > 0, θ > 0 (1.11)

 θ 3 x3 + θ 2 (θ + 3) x 2 + θ θ 2 + 2θ + 6 x 
F6 ( x,θ ) =1 − 1 +
( )
 e −θ x ; x > 0,θ > 0 (1.12)
 3 2
θ + θ + 2θ + 6 
 
Shanker (2016 i) has shown that the Amarendra distribution is a four component mixture of exponential (θ ) distribution,
a gamma ( 2,θ ) distribution, a gamma ( 3,θ ) distribution and a gamma ( 4,θ ) distribution with their mixing proportions
θ3 θ2 2θ 6
, , , and respectively. Shanker (2016 i) has
3 2 3 2 3 2 3 2
θ + θ + 2θ + 6 θ + θ + 2θ + 6 θ + θ + 2θ + 6 θ + θ + 2θ + 6
done a detailed study of its various mathematical and statistical properties, estimation of its parameter and its applications. It
has been observed that it provides a better model than exponential, Lindley and Sujatha distributions for modeling lifetime
data. Shanker (2016 j) has also obtained a Poisson mixture of Amarendra distribution and named it ‘Poisson-Amarendra
distribution’ and discussed its various properties, estimation of its parameter and its applications. Further, Shanker and Hagos
(2016 i, 2016 j) have obtained size-biased and zero-truncated versions of Poisson-Amarendra distribution and discussed their
properties, estimation of their parameter and its applications in different fields of knowledge.
The Probability density function (p.d.f.)of new one parameter lifetime distribution can be introduced as

θ5
=f 7 ( x;θ ) 4 3 2
θ + θ + 2θ + 6θ + 24
(
1 + x + x 2 + x3 + x 4 e −θ x ; x > 0, θ > 0 ) (1.13)

We would name this distribution as, ‘Devya distribution’. It can be easily shown that Devya distribution is a five
component mixture of exponential (θ ) distribution, a gamma ( 2,θ ) distribution, a gamma ( 3,θ ) distribution, a gamma

θ4
( 4,θ ) distribution and a gamma ( 5,θ ) distribution with their mixing proportions
,
θ 4 + θ 3 + 2θ 2 + 6θ + 24
θ3 2θ 2 6θ 24
, , , and
4 3 2
4 3 2 4 3 2
θ + θ + 2θ + 6θ + 24 θ + θ + 2θ + 6θ + 24 θ + θ + 2θ + 6θ + 24 θ + θ + 2θ 2 + 6θ + 24
4 3
respectively.
The corresponding cumulative distribution function (c.d.f) of Devya distribution (1.13) can be obtained as

( ) ( )
 θ 4 x 4 + x3 + x 2 + x + θ 3 4 x3 + 3 x 2 + 2 x + 6θ 2 2 x 2 + x + 24θ x 
F7 ( x,θ ) =1 − 1 +
( )
 e −θ x ; x > 0,θ > 0 (1.14)
 4 3 2
θ + θ + 2θ + 6θ + 24 
 
The graphs of the p.d.f. and the c.d.f. of Devya distribution for different values of θ are shown in figures 1(a) and 1(b).
 192 Rama Shanker: Devya Distribution and Its Applications

θ=0.2 θ=0.5 θ=0.8 θ=1 θ=1.5 θ=2 θ=2.5 θ=3

0.2 1.6

0.15 1.2

f(x)
0.8
f(x)

0.1

0.05 0.4

0 0
0 2 4 6 8 10 12 14 0 2 4 6 8 10 12 14
x x

Figure 1(a). Graphs of the p.d.f. of Devya distribution for selected values of the parameter θ

θ=0.2 θ=0.5 θ=0.8 θ=1 θ=1.5 θ=2 θ=2.5 θ=3

1 1

0.8 0.8

0.6 0.6
F(x)

F(x)

0.4 0.4
0.2 0.2
0 0
0 2 4 6 8 10 12 14 0 2 4 6 8 10 12 14
x x

Figure 1(b). Graphs of the c.d.f. of Devya distribution for selected values of the parameter θ

2. Moments and Related Measures

The moment generating function of Devya distribution (1.13) can be obtained as
∞
θ5
=M X (t ) 4 3 2 ∫
θ + θ + 2θ + 6θ + 24 0
(
e ( ) 1 + x + x 2 + x3 + x 4 dx
− θ −t x
)
θ5  1 1 2 6 24 
=  + + + + 
θ 4 + θ 3 + 2θ 2 + 6θ + 24 θ − t (θ − t )2 (θ − t )3 (θ − t )4 (θ − t )5 

 1 ∞  t  k 1 ∞  k + 1  t  k 2 ∞  k + 2   t  k 
 ∑  + 2 ∑   + 3 ∑    
θ5 =  θ k 0=
 θ  θ k 0  k =  θ  θ k 0 k  θ  
= 4  
θ + θ 3 + 2θ 2 + 6θ + 24  6 ∞  k + 3   t k 24 ∞  k + 4   t k 
+ 4 ∑  k   θ  + 5 ∑  k   θ  
=  θ k 0=    θ k 0   
θ 4 + ( k + 1)θ 3 + ( k + 1)( k + 2 )θ 2 + ( k + 1)( k + 2 )( k + 3)θ 
 
∞ + ( k + 1)( k + 2 )( k + 3)( k + 4 ) k
   t 
=∑  
k =0 (
θ 4 + θ 3 + 2θ 2 + 6θ + 24 ) θ 
 International Journal of Statistics and Applications 2016, 6(4): 189-202 193

tr
The r the moment about origin, µr ′ of Devya distributon (1.13), obtained as the coefficient of in M X ( t ) , can be
r!
given by
θ 4 + ( r + 1)θ 3 + ( r + 1)( r + 2 )θ 2 + ( r + 1)( r + 2 )( r + 3)θ 
r ! 
 + ( r + 1)( r + 2 )( r + 3)( r + 4 ) 
µr′ = ; r 1, 2,3,...
r
( 4 3 2
θ θ + θ + 2θ + 6θ + 24 )
Thus the first four moments about origin of Devya distribution (1.13) can be obtained as

µ1′ =
θ 4 + 2θ 3 + 6θ 2 + 24θ + 120
, µ2′ =
(
2 θ 4 + 3θ 3 + 12θ 2 + 60θ + 360 ),
( )
θ θ 4 + θ 3 + 2θ 2 + 6θ + 24 (
θ 2 θ 4 + θ 3 + 2θ 2 + 6θ + 24 )
6 (θ 4 + 4θ 3 + 20θ 2 + 120θ + 840 ) (
24 θ 4 + 5θ 3 + 30θ 2 + 210θ + 1680 )
′
µ3 = , µ4′ =
θ 3 (θ 4 + θ 3 + 2θ 2 + 6θ + 24 ) θ 4
(θ 4 3 2
)
+ θ + 2θ + 6θ + 6 24

Using the relationship between moments about mean and moments about origin, the moments about mean of Devya
distribution (1.13) are obtained as

θ 8 + 4θ 7 + 18θ 6 + 96θ 5 + 600θ 4 + 480θ 3 + 720θ 2 + 1440θ + 2880

µ2 =
( )
2
θ 2 θ 4 + θ 3 + 2θ 2 + 6θ + 24

 θ 12 + 6θ 11 + 36θ 10 + 242θ 9 + 1836θ 8 + 2628θ 7 + 4128θ 6 + 6624θ 5 

2 
 +9360θ 4 + 17280θ 3 + 30240θ 2 + 51840θ + 69120 
µ3 =  
( )
3
θ 3 θ 4 + θ 3 + 2θ 2 + 6θ + 24

 3θ 16 + 24θ 15 + 172θ 14 + 1312θ 13 + 11032θ 12 + 26784θ 11 + 65136θ 10 + 170880θ 9 

 
3  +454032θ 8 + 844416θ 7 + 1731072θ 6 + 3658752θ 5 + 6768000θ 4 + 6428160θ 3 
 
 +8570880θ 2 + 11612160θ + 11612160 
µ4 =  
( )
4
θ 4 θ 4 + θ 3 + 2θ 2 + 6θ + 24

The coefficient of variation ( C.V ) , coefficient of skewness ( )

β1 , coefficient of kurtosis ( β 2 ) and index of dispersion
(γ ) of Devya distribution (1.13) are thus obtained as
σ θ 8 + 4θ 7 + 18θ 6 + 96θ 5 + 600θ 4 + 480θ 3 + 720θ 2 + 1440θ + 2880
C=
.V =
µ1′ θ 4 + 2θ 3 + 6θ 2 + 24θ + 120
 θ 12 + 6θ 11 + 36θ 10 + 242θ 9 + 1836θ 8 + 2628θ 7 + 4128θ 6 + 6624θ 5 
2 
µ3  +9360θ 4 + 17280θ 3 + 30240θ 2 + 51840θ + 69120 
β1 =
=  
( )
3/2 32
µ2 8 7 6 5 4 3 2
θ + 4θ + 18θ + 96θ + 600θ + 480θ + 720θ + 1440θ + 2880
194 Rama Shanker: Devya Distribution and Its Applications

 3θ 16 + 24θ 15 + 172θ 14 + 1312θ 13 + 11032θ 12 + 26784θ 11 + 65136θ 10 + 170880θ 9 

 
3  +454032θ 8 + 844416θ 7 + 1731072θ 6 + 3658752θ 5 + 6768000θ 4 + 6428160θ 3 
 2

µ4  +8570880 θ + 11612160 θ + 11612160 
β2 =
=  
µ22
( )
8 7 6 5 4 3 2 2
θ + 4θ + 18θ + 96θ + 600θ + 480θ + 720θ + 1440θ + 2880

σ2 θ 8 + 4θ 7 + 18θ 6 + 96θ 5 + 600θ 4 + 480θ 3 + 720θ 2 + 1440θ + 2880

γ
= =
µ1′ ( )(
θ θ 4 + θ 3 + 2θ 2 + 6θ + 24 θ 4 + 2θ 3 + 6θ 2 + 24θ + 120 )
The condition under which Devya distribution is over-dispersed, equi-dispersed, and under-dispersed has been given along
with conditions under which Amarendra, Sujatha, Aradhana, Akash, Shanker, Lindley and exponential distributions are
over-dispersed, equi-dispersed, and under-dispersed in table 1.

Table 1. Over-dispersion, equi-dispersion and under-dispersion of Devya, Amarendra, Sujatha, Aradhana, Akash, Shanker, Lindley and exponential

distributions for varying values of their parameter θ

Over-dispersion Equi-dispersion Under-dispersion

Distribution
(µ < σ )
2
(µ = σ )
2
(µ > σ )
2

Devya θ < 1.451669994 θ = 1.451669994 θ > 1.451669994

Amarendra θ < 1.525763580 θ = 1.525763580 θ > 1.525763580
Sujatha θ < 1.364271174 θ = 1.364271174 θ > 1.364271174
Aradhana θ < 1.283826505 θ = 1.283826505 θ > 1.283826505
Akash θ < 1.515400063 θ = 1.515400063 θ > 1.515400063
Shanker θ < 1.171535555 θ = 1.171535555 θ > 1.171535555
Lindley θ < 1.170086487 θ = 1.170086487 θ > 1.170086487
Exponential θ <1 θ =1 θ >1

3. Hazard Rate Function and Mean Residual Life Function

Let X be a continuous random variable with p.d.f. f ( x ) and c.d.f. F ( x ) . The hazard rate function (also known as the
failure rate function) and the mean residual life function of X are respectively defined as
P ( X < x + ∆x X > x ) f ( x)
=h( x) lim
= (3.1)
∆x →0 ∆x 1 − F ( x)
1 ∞
and m (=
x ) E  X − x X >=
x  1 − F ( t )  dt
∫ (3.2)
1 − F ( x) x 

The corresponding hazard rate function, h ( x ) and the mean residual life function, m ( x ) of Devya distribution are thus
given by

h( x) =
(
θ 5 1 + x + x 2 + x3 + x 4 )
( ) ( ) (
θ 4 x 4 + x3 + x 2 + x + θ 3 4 x3 + 3 x 2 + 2 x + 6θ 2 2 x 2 + x + 24θ x 
  ) (3.3)
 
 (
4 3 2
+ θ + θ + 2θ + 6θ + 24 ) 

 International Journal of Statistics and Applications 2016, 6(4): 189-202 195

θ 4 + θ 3 + 2θ 2 + 6θ + 24
m ( x) =
θ ( x + x + x + x + 1) + θ ( 4 x + 3 x + 2 x + 1) + 2θ ( 6 x + 3 x + 1) + 6θ ( 4 x + 1) + 24  e
4 4 3 2 3 3 2 2 2 −θ x

( ) ( ) ( )
×∫ θ 4 t 4 + t 3 + t 2 + t + 1 + θ 3 4t 3 + 3t 2 + 2t + 1 + 2θ 2 6t 2 + 3t + 1 + 6θ ( 4t + 1) + 24  e −θ t dt
x

θ 4 ( x 4 + x 3 + x 2 + x + 1) + 2θ 3 ( 4 x 3 + 3 x 2 + 2 x + 1) + 6θ 2 ( 6 x 2 + 3 x + 1) + 24θ ( 4 x + 1) + 120
= (3.4)
θ θ 4 ( x 4 + x 3 + x 2 + x + 1) + θ 3 ( 4 x 3 + 3 x 2 + 2 x + 1) + 2θ 2 ( 6 x 2 + 3 x + 1) + 6θ ( 4 x + 1) + 24 

θ5 θ 4 + 2θ 3 + 6θ 2 + 24θ + 120
can be seen that h ( 0 ) =
It = = f ( 0 ) and m ( 0 ) = µ1′ . The
θ 4 + θ 3 + 2θ 2 + 6θ + 24 θ (θ 4 + θ 3 + 2θ 2 + 6θ + 24 )
graphs of h ( x ) and m ( x ) of Devya distribution (1.13) for different values of its parameter are shown in figures 3(a) and
3(b), respectively.

θ=0.2 θ=0.5 θ=0.8 θ=1 θ=1.5 θ=2 θ=2.5 θ=3

0.8 3
2.5
0.6
2
h(x)

0.4
h(x)

1.5
0.2 1
0.5
0 0
0 2 4 6 8 10 12 14 0 2 4 6 8 10 12 14
x x

Figure 2(a). Graphs of h( x) of Devya distribution for selected values of the parameter θ

θ=0.2 θ=0.5 θ=0.8 θ=1 θ=1.5 θ=2 θ=2.5 θ=3

25 2
20
1.5
15
m(x)

m(x)

1
10
5 0.5
0 0
0 2 4 6 8 10 12 14 0 2 4 6 8 10 12 14
x x

Figure 2(b). Graphs of m( x) of Devya distribution for selected values of the parameter θ
It is also obvious from the graphs of h ( x ) and m ( x ) that h ( x ) is decreasing function of x for 0 < x < 1 and
θ = 1.5 and 2 and is monotonically increasing function of other values of x and θ , whereas m ( x ) is monotonically
decreasing function of x and θ .
 196 Rama Shanker: Devya Distribution and Its Applications

4. Stochastic Orderings
Stochastic ordering of positive continuous random variables is an important tool for judging the comparative behaviour of
continuous distributions. A random variable X is said to be smaller than a random variable Y in the

(i) stochastic order ( X ≤ st Y ) if FX ( x ) ≥ FY ( x ) for all x

(ii) hazard rate order ( X ≤ hr Y ) if hX ( x ) ≥ hY ( x ) for all x
(iii) mean residual life order ( X ≤ mrl Y ) if m X ( x ) ≤ mY ( x ) for all x
f X ( x)
(iv) likelihood ratio order ( X ≤lr Y ) if decreases in x .
fY ( x )

The following results due to Shaked and Shanthikumar (1994) are well known for establishing stochastic ordering of
continuous distributions
X ≤lr Y ⇒ X ≤ hr Y ⇒ X ≤ mrl Y
⇓
X ≤ st Y

The Devya distribution is ordered with respect to the strongest ‘likelihood ratio’ ordering as shown in the following
theorem:
Theorem: Let X ∼ Devya distributon (θ1 ) and Y ∼ Devya distribution (θ 2 ) . If θ1 > θ 2 , then X ≤lr Y and hence
X ≤ hr Y , X ≤ mrl Y and X ≤ st Y .
Proof: We have

=
f X ( x) ( ) e−(θ −θ )x ; x > 0
θ15 θ 2 4 + θ 23 + 2θ 2 2 + 6θ 2 + 24
1 2
fY ( x )
θ 25 (θ14 + θ13 + 2θ12 + 6θ1 + 24 )
Now

=
f ( x)
log X log 
1 (
 θ 5 θ 4 + θ 3 + 2θ 2 + 6θ + 24
2 2 2 2 )  − (θ − θ ) x .
( ) 
fY ( x )  θ 5 θ 4 + θ 3 + 2θ 2 + 6θ + 24 1 2
 2 1 1 1 1

d f X ( x)
This gives log − (θ1 − θ 2 )
=
dx fY ( x )

d f X ( x)
Thus for θ1 > θ 2 , log < 0 . This means that X ≤lr Y and hence X ≤ hr Y , X ≤ mrl Y and X ≤ st Y .
dx fY ( x )

5. Mean Deviations
The amount of scatter in a population is evidently measured to some extent by the totality of deviations from the mean and
the median. These are known as the mean deviation about the mean and the mean deviation about the median and are defined
by
∞ ∞
δ1 ( X=) ∫ x − µ f ( x ) dx and δ 2 ( X
= ) ∫ x − M f ( x ) dx , respectively,
0 0

where µ = E ( X ) and M = Median ( X ) .

The expressions for δ1 ( X ) and δ 2 ( X ) , can be calculated using the following relationships
 International Journal of Statistics and Applications 2016, 6(4): 189-202 197

µ ∞
δ1 ( X ) = ∫ ( µ − x ) f ( x ) dx + ∫ ( x − µ ) f ( x ) dx
0 µ
µ ∞
= µ F ( µ ) − ∫ x f ( x ) dx − µ 1 − F ( µ )  + ∫ x f ( x ) dx
0 µ
∞
= 2 µ F ( µ ) − 2 µ + 2 ∫ x f ( x ) dx
µ
µ
= 2 µ F ( µ ) − 2 ∫ x f ( x ) dx (5.1)
0
and
M ∞
δ2 ( X ) = ∫ ( M − x ) f ( x ) dx + ∫ ( x − M ) f ( x ) dx
0 M
M ∞
= M F (M ) − ∫ x f ( x ) dx − M 1 − F ( M )  + ∫ x f ( x ) dx
0 M
∞
=− µ + 2 ∫ x f ( x ) dx
M
M
= µ − 2 ∫ x f ( x ) dx (5.2)
0

Using p.d.f. (1.13) and the mean of Devya distribution, we get

( )
θ 5 µ 5 + µ 4 + µ 3 + µ 2 + µ + θ 4 5µ 4 + 4 µ 3 + 3µ 2 + 2 µ + 1
 ( )


3 3
( 2 2 2
+2θ 10 µ + 6 µ + 3µ + 1 + 6θ 10 µ + 4 µ + 1 + ) ( )  −θ µ
e
 (5.3)
µ 24θ ( 5µ + 1) + 120 
 
∫ x f7 ( x,θ ) dx= µ −
0 (
θ θ 4 + θ 3 + 2θ 2 + 6θ + 24 )
(
θ 5 M 5 + M 4 + M 3 + M 2 + M + θ 4 5M 4 + 4 M 3 + 3M 2 + 2 M + 1 
  ) ( )


3 3
( 2 2 2
+2θ 10 M + 6 M + 3M + 1 + 6θ 10 M + 4 M + 1 + )
 −θ M
e
 (5.4)
( )
M 24θ ( 5M + 1) + 120 
 
∫ x f7 ( x,θ ) dx= µ −
0
4 3 2
θ θ + θ + 2θ + 6θ + 24 ( )
Using expressions (5.1), (5.2), (5.3), and (5.4), the expressions for δ1 ( X ) and δ 2 ( X ) of Devya distribution, after
some algebraic simplification, are obtained as

( )
 θ 4 µ 4 + µ 3 + µ 2 + µ + 1 + 2θ 3 4 µ 3 + 3µ 2 + 2 µ + 1
 ( ) 

(
 +6θ 6 µ + 3µ + 1 + 24θ ( 4 µ + 1) + 120
δ1 ( X ) = 2 
2 2
) 
 −θ µ
e (5.5)


(
θ θ 4 + θ 3 + 2θ 2 + 6θ + 24 ) 

 
 
198 Rama Shanker: Devya Distribution and Its Applications

and

( ) (
θ 5 M 5 + M 4 + M 3 + M 2 + M + θ 4 5M 4 + 4 M 3 + 3M 2 + 2 M + 1


 −θ M )
2 e

δ2 ( X )  ( ) (
+2θ 3 10 M 3 + 6 M 2 + 3M + 1 + 6θ 2 10 M 2 + 4 M + 1 + 24θ ( 5M + 1) + 120 
 −µ
)(5.6)

(
θ θ 4 + θ 3 + 2θ 2 + 6θ + 24 )
6. Bonferroni and Lorenz Curves
The Bonferroni and Lorenz curves (Bonferroni, 1930) and Bonferroni and Gini indices have applications not only in
economics to study income and poverty, but also in other fields like reliability, demography, insurance and medicine. The
Bonferroni and Lorenz curves are defined as

1   1  
q ∞ ∞ ∞
1
B ( p ) =∫ x f ( x ) dx = ∫ x f ( x ) dx − ∫ x f ( x ) dx = µ − ∫ x f ( x ) dx 
 (6.1)
pµ 0 pµ  0  pµ  
 q   q 

1  1 
q ∞ ∞ ∞
1
and L ( p ) =x f ( x ) dx = x f ( x ) dx − x f ( x ) dx  =µ −
∫ ( ) 
µ ∫0 µ  ∫0 ∫ x f x dx (6.2)
 µ
 q   q 
respectively or equivalently
p
1
B ( p) = F −1 ( x ) dx
p µ ∫0
(6.3)

p
1
L( p) = F −1 ( x ) dx
µ ∫0
and (6.4)

respectively, where µ = E ( X ) and q = F −1 ( p ) .

The Bonferroni and Gini indices are thus defined as
1
B = 1 − ∫ B ( p ) dp (6.5)
0
1
and G = 1 − 2 L ( p ) dp
∫ (6.6)
0
respectively.
Using p.d.f. of Devya distribution (1.13), we get

( ) (
θ 5 q5 + q 4 + q3 + q 2 + q + θ 4 5q 4 + 4q3 + 3q 2 + 2q + 1


 −θ q )
 e
∞
 ( 2 2 2
) (
+2θ 10q + 6q + 3q + 1 + 6θ 10q + 4q + 1 + 24θ ( 5q + 1) + 120 
3 3
 ) (6.7)
∫ x f ( x ) dx =
q
4 3 2
(
θ θ + θ + 2θ + 6θ + 24 )
Now using equation (6.7) in (6.1) and (6.2), we get
 International Journal of Statistics and Applications 2016, 6(4): 189-202 199

 θ 5 ( q 5 + q 4 + q 3 + q 2 + q ) + θ 4 ( 5q 4 + 4q 3 + 3q 2 + 2q + 1)  
   e −θ q

B (=
p)
1   +2θ 3
(10 q 3
+ 6 q 2
+ 3q + 1 ) + 6θ 2
(10 q 2
+ 4 q + 1) + 24θ ( 5 q + 1) + 120 
 
1 −  (6.8)
p (θ + 2θ + 6θ + 24θ + 120 )
4 3 2

 
 
and
θ 5 ( q 5 + q 4 + q 3 + q 2 + q ) + θ 4 ( 5q 4 + 4q 3 + 3q 2 + 2q + 1) 
−θ q
 e
+2θ (10q + 6q + 3q + 1) + 6θ (10q + 4q + 1) + 24θ ( 5q + 1) + 120 
3 3 2 2 2
(6.9)
L ( p )= 1 − 
(θ 4 + 2θ 3 + 6θ 2 + 24θ + 120 )
Now using equations (6.8) and (6.9) in (6.5) and (6.6), the Bonferroni and Gini indices of Devya distribution are obtained
as
θ 5 ( q 5 + q 4 + q 3 + q 2 + q ) + θ 4 ( 5q 4 + 4q 3 + 3q 2 + 2q + 1) 
−θ q
 e
+2θ (10q + 6q + 3q + 1) + 6θ (10q + 4q + 1) + 24θ ( 5q + 1) + 120 
3 3 2 2 2
(6.10)
B= 1− 
(θ 4 + 2θ 3 + 6θ 2 + 24θ + 120 )
θ 5 ( q 5 + q 4 + q 3 + q 2 + q ) + θ 4 ( 5q 4 + 4q 3 + 3q 2 + 2q + 1) 
−θ q
2 e
+2θ (10q + 6q + 3q + 1) + 6θ (10q + 4q + 1) + 24θ ( 5q + 1) + 120 
3 3 2 2 2
(6.11)
G =−1 + 
(θ 4 + 2θ 3 + 6θ 2 + 24θ + 120 )

7. Estimation of Parameter
7.1. Maximum Likelihood Estimation
Let ( x1, x2 , x3 , ... , xn )
be a random sample of size n from Devya distribution (1.13). The likelihood function, L of
Devya distribution is given by
n n
 θ5 
=L  4
 θ + θ 3 + 2θ 2 + 6θ + 24  ∏ (1 + xi + xi 2 + xi3 + xi 4 ) e−n θ x
  i =1
and so the natural log likelihood function as
 θ5  n
=
 θ + θ 3 + 2θ 2 + 6θ + 24  ∑
ln L n ln  4

+ ln 1 + xi + xi 2 + xi 3 + xi 4 − n θ x
 i =1
( )
where x is the sample mean. Now
3
( 2
d ln L 5n n 4θ + 3θ + 4θ + 6
= − − nx
)
dθ θ θ 4 + θ 3 + θ 2 + 6θ + 24
d ln L
The maximum likelihood estimate (MLE), θˆ of θ is the solution of the equation = 0 and is given by the
dθ
solution of the following fifth degree polynomial equation

xθ 5 + ( x − 1)θ 4 + 2 ( x − 1)θ 3 + 6 ( x − 1)θ 2 + 24 ( x − 1)θ − 120 =

0 (7.1.1)
200 Rama Shanker: Devya Distribution and Its Applications

7.2. Method of Moment Estimation

Equating the population mean to the sample mean x , the method of moment estimate (MOME) θ of θ of Devya
distribution is found as the solution of the same fifth degree polynomial equation (7.1.1), confirming that the MLE and
MOME of θ for Devya distribution are the same.

8. Goodness of Fit and Applications

In this section, the goodness of fit and applications of Devya distribution to two real data sets using maximum likelihood
estimate has been presented and the fit has been compared with one parameter exponential, Lindley, Shanker, Akash,
Aradhana, Sujatha and Amarendra distributions. The following two real lifetime data-sets, first from medical science and the
second from engineering has been considered.
Data set 1: The first data set represents the lifetime’s data relating to relief times (in minutes) of 20 patients receiving an
analgesic and reported by Gross and Clark (1975, P. 105). The data are as follows:
1.1, 1.4, 1.3, 1.7, 1.9, 1.8, 1.6, 2.2, 1.7, 2.7, 4.1, 1.8,
1.5, 1.2, 1.4, 3.0, 1.7, 2.3, 1.6, 2.0
Data set 2: The second data set is the strength data of glass of the aircraft window reported by Fuller et al (1994):
18.83, 20.80, 21.657, 23.03, 23.23, 24.05, 24.321, 25.50, 25.52, 25.80, 26.69,
26.77, 26.78, 27.05, 27.67, 29.90, 31.11, 33.20, 33.73, 33.76,
33.89, 34.76, 35.75, 35.91, 36.98, 37.08, 37.09, 39.58, 44.045, 45.29, 45.381
In order to compare the goodness of fit of these distributions, −2ln L , AIC (Akaike Information Criterion), AICC (Akaike
Information Criterion Corrected), BIC (Bayesian Information Criterion), and K-S Statistics ( Kolmogorov-Smirnov Statistics)
for two real data sets have been computed and presented in table 2. The formulae for computing AIC, AICC, BIC, and K-S
Statistics are as follows:
2k ( k + 1)
AIC =
−2ln L + 2k , AICC
= AIC + , BIC =
−2ln L + k ln n and
( n − k − 1)
K − S Sup Fn ( x ) − F0 ( x ) , where k = the number of parameters, n = the sample size and F ( x ) is the empirical
=
n
x
distribution function.
The best is the distribution which corresponds to the lower values of −2ln L , AIC, AICC, BIC, and K-S statistics.

Table 2. MLE’s, −2ln L , AIC, AICC, BIC, and K-S Statistics of the fitted distributions of data sets 1 and 2
Parameter
Model
estimate −2ln L AIC AICC BIC K-S Statistics

Devya 1.841946 54.50 56.50 56.72 57.49 0.268

Amarendra 1.480769 55.64 57.64 57.86 58.63 0.286
Sujatha 1.136745 57.50 59.50 59.72 60.49 0.309
Aradhana 1.123193 56.37 58.37 58.59 59.36 0.302
Data 1 Akash 1.156923 59.52 61.52 61.74 62.51 0.320
Shanker 0.803867 59.78 61.78 61.22 62.77 0.315
Lindley 0.816118 60.50 62.50 62.72 63.49 0.341
Exponential 0.526316 65.67 67.67 67.90 68.67 0.389
Devya 0.160872 227.68 229.68 229.82 231.11 0.193
Amarendra 0.128292 233.41 235.41 235.55 236.84 0.225
Sujatha 0.095610 241.50 243.50 243.64 244.94 0.270
Aradhana 0.094318 242.23 244.23 244.37 245.66 0.274
Data 2 Akash 0.097062 240.68 242.68 242.82 244.11 0.266
Shanker 0.064712 252.35 254.35 254.49 255.78 0.326
Lindley 0.062988 253.99 255.99 256.13 257.42 0.333
Exponential 0.032455 274.53 276.53 276.67 277.96 0.426
 International Journal of Statistics and Applications 2016, 6(4): 189-202 201

It is obvious from above table that Devya distribution [6] Deniz, E. and Ojeda, E. (2011): The discrete Lindley
gives much closer fit than exponential, Lindley, Shanker, distribution-Properties and Applications, Journal of Statistical
Computation and Simulation, 81, 1405 – 1416.
Akash, Aradhana, Sujatha and Amarendra distributions and
hence it may be preferred to exponential, Lindley, Shanker, [7] Elbatal, I., Merovi, F. and Elgarhy, M. (2013): A new
Akash, Aradhana, Sujatha and Amarendra distributions for generalized Lindley distribution, Mathematical theory and
modeling various lifetime data. Modeling, 3 (13), 30-47.
[8] Fuller, E.J., Frieman, S., Quinn, J., Quinn, G., and Carter, W.
(1994): Fracture mechanics approach to the design of glass
9. Concluding Remarks aircraft windows: A case study, SPIE Proc 2286, 419-430.
[9] Ghitany, M.E., Atieh, B. and Nadarajah, S. (2008): Lindley
A lifetime distribution named, ‘Devya distribution’ has distribution and its Application, Mathematics Computing and
been introduced to model lifetime data from biomedical Simulation, 78, 493 – 506.
science and engineering. Its moment generating function,
[10] Ghitany, M., Al-Mutairi, D., Balakrishnan, N. and Al-Enezi, I.
moments about origin and moments about mean and (2013): Power Lindley distribution and associated inference,
expressions for skewness and kurtosis have been obtained. Computational Statistics and Data Analysis, 64, 20 – 33.
Other interesting properties of the distribution such as its
[11] Gross, A.J. and Clark, V.A. (1975): Survival Distributions:
hazard rate function, mean residual life function, stochastic
Reliability Applications in the Biometrical Sciences, John
ordering, mean deviations, Bonferroni and Lorenz curves, Wiley, New York.
have been discussed. The estimation of its parameter has
been discussed using maximum likelihood estimation and [12] Lindley, D.V. (1958): Fiducial distributions and Bayes’
theorem, Journal of the Royal Statistical Society, Series B, 20,
the method of moments. Two examples of real lifetime data - 102- 107.
sets have been presented to show the goodness of fit of
Devya distribution over one parameter exponential, [13] Merovci, F. (2013): Transmuted Lindley distribution,
Lindley, Shanker, Akash, Aradhana, Sujatha and Amarendra International Journal of Open Problems in Computer Science
and Mathematics, 6, 63 – 72.
distributions.
NOTE: The paper is named in the name of Devya, [14] Nadarajah, S., Bakouch, H.S. and Tahmasbi, R. (2011): A
a lovely grand child of my eldest brother Professor generalized Lindley distribution, Sankhya Series B, 73, 331 –
Shambhu Sharma, Department of Mathematics, Dayalbagh 359.
Educational institute, Dayalbagh, Agra, India. [15] Oluyede, B.O. and Yang, T. (2014): A new class of
generalized Lindley distribution with applications, Journal of
Statistical Computation and Simulation, 85 (10), 2072 – 2100.
ACKNOWLEDGEMENTS [16] Pararai, M., Liyanage, G.W. and Oluyede, B.O. (2015): A
The authors would like to thank the Editor-In-Chief and new class of generalized Power Lindley distribution with
applications to lifetime data, Theoretical Mathematics &
the referee for careful reading, constructive comments and Applications, 5(1), 53 – 96.
suggestions which improved the quality of the paper.
[17] Sankaran, M. (1970): The discrete Poisson-Lindley
distribution, Biometrics, 26(1), 145 – 149.
[18] Shaked, M. and Shanthikumar, J.G. (1994): Stochastic Orders
REFERENCES and Their Applications, Academic Press, New York.

[1] Abouammoh, A.M., Alshangiti, A.M. and Ragab, I.E. (2015): [19] Shanker, R. (2015 a): Akash distribution and Its Applications,
A new generalized Lindley distribution, Journal of Statistical International Journal of Probability and Statistics, 4(3), 65 –
Computation and Simulation, preprint http://dx.doi.org/10.1 75.
080/ 00949655.2014.995101.
[20] Shanker, R. (2015 b): Shanker distribution and Its
[2] Alkarni, S. (2015): Extended Power Lindley distribution-A Applications, International Journal of Statistics and
new Statistical model for non-monotone survival data, Applications, 5(6), 338 – 348.
European journal of statistics and probability, 3(3), 19 – 34.
[21] Shanker, R. (2016 a): The discrete Poisson-Akash distribution,
[3] Ashour, S. and Eltehiwy, M. (2014): Exponentiated Power Communicated.
Lindley distribution, Journal of Advanced Research, preprint
[22] Shanker, R. (2016 b): Size-biased Poisson-Akash distribution
http://dx.doi.org/10.1016/ j.jare. 2014.08.005.
and its Applications, Communicated.
[4] Bakouch, H.S., Al-Zaharani, B. Al-Shomrani, A., Marchi, V.
[23] Shanker, R. (2016 c): Zero-truncated Poisson-Akash
and Louzad, F. (2012): An extended Lindley distribution,
distribution and its Applications, Communicated.
Journal of the Korean Statistical Society, 41, 75 – 85.
[24] Shanker, R. (2016 d): The discrete Poisson-Shanker
[5] Bonferroni, C.E. (1930): Elementi di Statistca generale,
distribution, Communicated.
Seeber, Firenze.
202 Rama Shanker: Devya Distribution and Its Applications

[25] Shanker, R. (2016 e): Aradhana distribution and Its [41] Shanker, R. and Hagos, F. (2016 j): Zero-truncated Poisson-
Applications, International Journal of Statistics and Amarendra distribution and its Applications, communicated.
Applications, 6(1), 23 – 34.
[42] Shanker, R. and Mishra, A. (2013 a): A two-parameter
[26] Shanker, R. (2016 f): The discrete Poisson-Aradhana Lindley distribution, Statistics in Transition-new series, 14
distribution, Communicated. (1), 45- 56.
[27] Shanker, R. (2016 g): Sujatha distribution and Its [43] Shanker, R. and Mishra, A. (2013 b): A quasi Lindley
Applications, to appear in “Statistics in Transition new series, distribution, African Journal of Mathematics and Computer
17 (3). Science Research, 6(4), 64 – 71.
[28] Shanker, R. (2016 h): The discrete Poisson-Sujatha [44] Shanker, R. and Mishra, A. (2016): A quasi Poisson-Lindley
distribution, International Journal of Probability and Statistics, distribution, To appear in, “Journal of Indian Statistical
5(1), 1 - 9. Association”.
[29] Shanker, R. (2016 i): Amarendra distribution and Its [45] Shanker, R. and Amanuel, A.G. (2013): A new quasi Lindley
Applications, American Journal of Mathematics and Statistics, distribution, International Journal of Statistics and Systems, 8
6(1), 44 – 56. (2), 143 – 156.
[30] Shanker, R. (2016 j): The discrete Poisson-Amarendra [46] Shanker, R., Sharma, S. and Shanker, R. (2013): A
distribution, Appear in, “International Journal of Statistical two-parameter Lindley distribution for modeling waiting and
Distributions and Applications. survival times data, Applied Mathematics, 4, 363 – 368.
[31] Shanker, R. and Hagos, F. (2015): On Poisson-Lindley [47] Shanker, R., Hagos, F, and Sujatha, S. (2015): On modeling
distribution and its Applications to Biological Sciences, of Lifetimes data using exponential and Lindley distributions,
Biometrics and Biostatistics International Journal, 2(4), 1-5. Biometrics & Biostatistics International Journal, 2 (5), 1-9.
[32] Shanker, R. and Hagos, F. (2016 a): Size-biased Poisson- [48] Shanker, R., Hagos, F. and Sharma, S. (2016 a): On two
Shanker distribution and its Applications, Communicated. parameter Lindley distribution and Its Applications to model
Lifetime data, Biometrics & Biostatistics International
[33] Shanker, R. and Hagos, F. (2016 b): Zero-truncated Poisson- Journal, 3(1), 1 – 8.
Shanker distribution and Its Applications, Communicated.
[49] Shanker, R., Hagos, F. and Sharma, S. (2016 b): On Quasi
[34] Shanker, R. and Hagos, F. (2016 c): Size-biased Poisson- Lindley distribution and Its Applications to model Lifetime
Aradhana distribution and Its Applications, Communicated. data, International Journal of Statistical distributions and
Applications, 2(1), 1 -7.
[35] Shanker, R. and Hagos, F. (2016 d): Zero-truncated Poisson-
Aradhana distribution and its Applications, Communicated. [50] Shanker, R., Hagos, F, and Sujatha, S. (2016 c): On modeling
of Lifetimes data using one parameter Akash, Lindley and
[36] Shanker, R. and Hagos, F. (2016 e): Size-Biased exponential distributions, Biometrics & Biostatistics
Poisson-Sujatha distribution with Applications, To appear in, International Journal, 3(2), 1 -10.
“American Journal of Mathematics and Statistics”, 6(4).
[51] Sharma, V., Singh, S., Singh, U. and Agiwal, V. (2015): The
[37] Shanker, R. and Hagos, F. (2016 f): Zero-Truncated Poisson- inverse Lindley distribution- A stress-strength reliability
Sujatha distribution with Applications, Communicated. model with applications to head and neck cancer data, Journal
[38] Shanker, R. and Hagos, F. (2016 g): On Poisson - Sujatha of Industrial & Production Engineering, 32 (3), 162 – 173.
distributions and Its applications to model count data from [52] Singh, S.K., Singh, U. and Sharma, V. K. (2014): The
biological sciences, Biometrics & Biostatistics International Truncated Lindley distribution- inference and Application,
Journal, 3(4), 1 – 7. Journal of Statistics Applications& Probability, 3(2), 219 –
[39] Shanker, R. and Hagos, F. (2016 h): On Zero-Truncation of 228.
Poisson, Poisson-Lindley, and Poisson –Sujatha distributions [53] Zakerzadeh, H. and Dolati, A. (2009): Generalized Lindley
and their Applications, Biometrics & Biostatistics distribution, Journal of Mathematical extension, 3 (2), 13 –
International Journal, 3(5), 1 – 13. 25.
[40] Shanker, R. and Hagos, F. (2016 i): Size-biased Poisson-
Amarendra distribution and its Applications, Communicated.