I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t
201
9
,
p
p
.
3
2
7
2
~3
2
7
8
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v9
i
4
.
p
p
3
2
7
2
-
3278
3272
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
Relia
bility esti
m
a
tion for
the
ra
ndo
m
ly
ce
nso
red
pa
reto d
istri
butio
n
M
a
h
m
o
ud
M
.
S
m
a
d
i
1
,
S
a
if
ul
I
s
la
m
An
s
a
ri
2
,
Ah
m
e
d A.
J
a
ra
da
t
3
1,
3
De
p
a
rt
m
e
n
t
o
f
M
a
th
e
m
a
ti
c
s a
n
d
S
tatisti
c
s,
J
o
rd
a
n
Un
iv
e
rsity
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
Jo
rd
a
n
2
De
p
a
rt
m
e
n
t
o
f
S
tatisti
c
s,
Un
iv
e
rsity
o
f
T
a
b
u
k
,
KS
A
3
De
p
a
rtme
n
t
o
f
F
a
m
il
y
a
n
d
Co
m
m
u
n
it
y
M
e
d
icin
e
,
A
ra
b
ian
G
u
lf
U
n
iv
e
rsity
,
Ba
h
ra
in
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
1
7
,
2
0
1
8
R
ev
i
s
ed
Ma
r
2
7
,
2
0
1
9
A
cc
ep
ted
A
p
r
7
,
2
0
1
9
W
id
e
sp
re
a
d
a
p
p
li
c
a
ti
o
n
s
o
f
ra
n
d
o
m
c
e
n
so
rin
g
in
li
f
e
tes
ti
n
g
e
x
p
e
rim
e
n
ts
to
e
sti
m
a
te
re
li
a
b
il
it
y
o
f
e
n
g
in
e
e
rin
g
p
ro
d
u
c
ts
o
r
sy
st
e
m
s
a
re
a
v
iala
b
le
.
Diff
e
r
e
n
t
p
a
ra
m
e
tri
c
sta
ti
stica
l
m
o
d
e
ls
su
c
h
a
s
e
x
p
o
n
e
n
ti
a
l
,
Ra
y
leig
h
,
W
e
ib
u
ll
a
n
d
M
a
x
w
e
ll
d
istri
b
u
ti
o
n
s
a
re
u
se
d
u
n
d
e
r
ra
n
d
o
m
c
e
n
so
rin
g
sc
h
e
m
e
.
In
th
is
p
a
p
e
r,
ra
n
d
o
m
c
e
n
so
rin
g
u
n
d
e
r
P
a
re
to
d
istri
b
u
t
io
n
is
c
o
n
sid
e
re
d
.
T
h
e
m
a
x
i
m
u
m
li
k
e
li
h
o
o
d
e
stim
a
to
rs
(M
L
E’s)
o
f
th
e
m
o
d
e
l
p
a
ra
m
e
ters
a
n
d
su
rv
iv
a
l
f
u
n
c
ti
o
n
w
e
re
d
e
riv
e
d
a
lo
n
g
w
it
h
F
ish
e
r
in
f
o
rm
a
ti
o
n
m
a
tri
x
a
n
d
a
s
y
m
p
to
ti
c
c
o
n
f
id
e
n
c
e
in
terv
a
ls.
A
si
m
u
latio
n
stu
d
y
wa
s
p
e
r
f
o
r
m
e
d
to
o
b
se
rv
e
th
e
b
e
h
a
v
io
r
o
f
th
e
M
L
E
’s.
T
h
e
si
m
u
latio
n
re
su
lt
s
s
h
o
w
e
d
th
a
t
th
e
b
ias
a
n
d
MSE
w
e
re
re
a
so
n
a
b
ly
s
m
a
ll
in
a
ll
c
a
se
s
.
K
ey
w
o
r
d
s
:
M
a
x
i
m
u
m
li
k
e
li
h
o
o
d
e
stim
a
ti
o
n
P
a
re
to
d
istri
b
u
ti
o
n
Ra
n
d
o
m
c
e
n
so
rin
g
Re
li
a
b
il
it
y
S
u
rv
iv
a
l
a
n
a
ly
sis
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Ma
h
m
o
u
d
M.
S
m
ad
i
,
Dep
ar
t
m
en
t o
f
Ma
th
e
m
at
ics a
n
d
Statis
tics
,
J
o
r
d
an
Un
iv
er
s
it
y
o
f
Scie
n
ce
a
n
d
T
ec
h
n
o
lo
g
y
,
I
r
b
id
,
J
o
r
d
an
.
E
m
ail: s
m
ad
i
@
j
u
s
t.e
d
u
.
j
o
1.
I
NT
RO
D
UCT
I
O
N
I
n
s
u
r
v
i
v
al
an
al
y
s
i
s
an
d
r
elia
b
ilit
y
t
h
eo
r
y
,
it
is
d
if
f
ic
u
lt
to
co
llect
lif
e
ti
m
e
d
ata
f
o
r
all
th
e
s
u
b
j
ec
ts
u
n
d
er
s
t
u
d
y
b
ec
au
s
e
o
f
ti
m
e
an
d
co
s
t
co
n
s
tr
ain
t
s
.
T
h
e
p
r
ac
tio
n
er
s
b
ased
o
n
th
e
m
o
d
el
a
n
d
av
ailab
le
in
f
o
r
m
atio
n
u
s
e
v
ar
io
u
s
t
y
p
es
o
f
ce
n
s
o
r
i
n
g
s
c
h
e
m
es.
C
o
n
v
en
tio
n
al
T
y
p
e
I
an
d
T
y
p
e
I
I
ce
n
s
o
r
in
g
ar
e
co
m
m
o
n
ce
n
s
o
r
in
g
s
c
h
e
m
es
w
h
ic
h
h
a
s
b
ee
n
is
u
s
e
i
n
m
an
y
s
i
tu
at
io
n
s
in
s
u
r
v
iv
al
a
n
al
y
s
i
s
an
d
r
eli
ab
ilit
y
en
g
i
n
ee
r
in
g
.
Dif
f
er
en
t
ce
n
s
o
r
in
g
s
ch
e
m
es
ar
e
p
r
o
p
o
s
ed
an
d
s
tu
d
ied
i
n
t
h
e
liter
at
u
r
e.
R
an
d
o
m
ce
n
s
o
r
in
g
is
u
s
ed
i
n
w
h
ic
h
th
e
ti
m
e
o
f
ce
n
s
o
r
in
g
is
n
o
t
f
i
x
ed
b
u
t
tak
e
n
as
r
a
n
d
o
m
[
1
]
.
An
o
th
er
ce
n
s
o
r
in
g
s
c
h
e
m
e
is
th
e
p
r
o
g
r
ess
i
v
e
an
d
h
y
b
r
id
ce
n
s
o
r
in
g
w
h
ic
h
h
a
s
al
s
o
co
n
s
id
er
ed
in
th
e
li
ter
atu
r
e
[
2
-
3
]
.
T
h
er
e
is
a
w
id
esp
r
ea
d
ap
p
licatio
n
o
f
r
an
d
o
m
ce
n
s
o
r
in
g
i
n
li
f
e
te
s
ti
n
g
e
x
p
er
i
m
en
t
s
a
n
d
cli
n
ical
tr
ial
s
w
h
er
e
b
o
th
t
h
e
s
u
r
v
iv
al
a
n
d
c
en
s
o
r
in
g
ti
m
es
ar
e
r
an
d
o
m
,
Ab
u
-
T
aleb
et
al
[
4
]
s
tu
d
ied
r
a
n
d
o
m
ce
n
s
o
r
in
g
u
s
in
g
ex
p
o
n
en
t
ial
f
o
r
s
u
r
v
iv
a
l
an
d
ce
n
s
o
r
in
g
ti
m
e
s
.
Salee
m
an
d
A
s
la
m
[
5
]
s
tu
d
ied
B
a
y
esi
an
an
al
y
s
i
s
o
f
th
e
R
a
y
l
e
ig
h
s
u
r
v
iv
al
ti
m
e
ass
u
m
in
g
r
a
n
d
o
m
ce
n
s
o
r
ti
m
e.
Dan
i
s
h
a
n
d
A
s
la
m
[
6
]
s
tu
d
ied
B
a
y
esian
i
n
f
er
en
ce
f
o
r
r
an
d
o
m
l
y
ce
n
s
o
r
ed
W
eib
u
ll
d
is
tr
ib
u
tio
n
.
Kr
is
h
n
a
et
al.
[
7
]
s
tu
d
ied
esti
m
at
io
n
i
n
Ma
x
w
el
l
d
is
tr
ib
u
tio
n
w
it
h
r
an
d
o
m
l
y
ce
n
s
o
r
ed
d
ata.
T
h
e
P
a
r
eto
d
is
tr
ib
u
tio
n
h
as
b
ee
n
w
id
el
y
u
s
ed
in
a
n
al
y
s
i
s
o
f
li
f
e
ti
m
e
d
ata
f
r
o
m
r
eliab
ilit
y
s
u
r
v
i
v
al
an
d
en
g
in
ee
r
i
n
g
p
o
in
t
o
f
v
ie
w
[
8
]
.
Sin
d
h
u
et
al.
[
9
]
co
n
s
id
er
ed
B
ay
esia
n
esti
m
atio
n
o
f
t
h
e
lef
t
ce
n
s
o
r
ed
d
ata
f
r
o
m
th
e
P
ar
eto
ty
p
e
I
I
d
is
tr
ib
u
tio
n
.
A
s
g
h
ar
za
d
eh
et
al.
[
1
0
]
p
e
r
f
o
r
m
ed
esti
m
atio
n
an
d
r
ec
o
n
s
tr
u
ct
io
n
b
ased
o
n
lef
t
ce
n
s
o
r
ed
d
ata
f
r
o
m
P
ar
eto
m
o
d
el.
Ust
a
a
n
d
Gez
er
[
1
1
]
s
tu
d
ied
r
eliab
ilit
y
es
t
i
m
atio
n
i
n
P
ar
eto
-
I
d
is
tr
ib
u
tio
n
b
ased
o
n
p
r
o
g
r
ess
iv
el
y
t
y
p
e
I
I
ce
n
s
o
r
ed
s
a
m
p
le
w
it
h
b
in
o
m
ia
l
r
e
m
o
v
al
s
.
Sh
o
u
[
1
2
]
s
tu
d
ied
esti
m
atio
n
f
o
r
th
e
t
w
o
-
p
ar
a
m
eter
P
ar
et
o
d
is
tr
ib
u
tio
n
u
n
d
er
p
r
o
g
r
ess
iv
e
c
en
s
o
r
i
n
g
w
i
th
u
n
i
f
o
r
m
r
e
m
o
v
al
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
R
elia
b
ilit
y
e
s
tima
tio
n
fo
r
th
e
r
a
n
d
o
mly
ce
n
s
o
r
ed
p
a
r
eto
d
is
tr
ib
u
tio
n
(
Ma
h
mo
u
d
M.
S
ma
d
i
)
3273
W
u
an
d
C
h
an
g
[
1
3
]
s
t
u
d
ied
i
n
f
er
e
n
ce
i
n
th
e
P
ar
eto
d
is
tr
ib
u
tio
n
b
ased
o
n
p
r
o
g
r
ess
i
v
e
t
y
p
e
I
I
ce
n
s
o
r
in
g
w
i
th
r
an
d
o
m
r
e
m
o
v
al
s
.
P
ar
s
i
et
al.
[
1
4
]
s
tu
d
ied
s
i
m
u
lta
n
eo
u
s
co
n
f
id
e
n
ce
in
ter
v
al
f
o
r
th
e
p
a
r
a
m
eter
s
o
f
P
ar
eto
d
is
tr
ib
u
tio
n
u
n
d
er
p
r
o
g
r
ess
i
v
e
ce
n
s
o
r
in
g
.
I
n
th
i
s
p
ap
er
th
e
esti
m
atio
n
p
r
o
b
lem
f
o
r
r
an
d
o
m
ce
n
s
o
r
in
g
u
n
d
er
P
ar
eto
d
is
tr
ib
u
tio
n
is
co
n
s
id
er
ed
,
th
e
s
u
r
v
i
v
al
ti
m
e
s
Xi
’
s
a
n
d
th
e
ce
n
s
o
r
in
g
ti
m
es
T
i
‘
s
f
o
llo
w
P
ar
et
o
d
is
tr
ib
u
tio
n
s
.
T
h
e
m
ax
i
m
u
m
li
k
eli
h
o
o
d
esti
m
ato
r
s
f
o
r
th
e
m
o
d
el
p
ar
a
m
eter
s
a
n
d
th
e
s
u
r
v
i
v
al
f
u
n
ctio
n
s
ar
e
d
er
iv
ed
alo
n
g
w
it
h
Fis
h
er
i
n
f
o
r
m
atio
n
m
atr
i
x
an
d
as
y
m
p
to
tic
co
n
f
id
en
ce
in
ter
v
als,
T
h
e
esti
m
ates
o
f
th
e
s
u
r
v
i
v
al
f
u
n
ctio
n
an
d
as
y
m
p
to
tic
p
r
o
p
er
ties
ar
e
g
iv
e
n
alo
n
g
w
it
h
Fi
s
h
er
in
f
o
r
m
atio
n
m
atr
i
x
an
d
as
y
m
p
to
tic
co
n
f
id
en
ce
i
n
ter
v
a
ls
.
T
h
e
r
esu
lts
o
f
t
h
e
s
i
m
u
lat
io
n
s
t
u
d
y
ar
e
p
r
esen
ted
an
d
d
is
cu
s
s
ed
.
2.
E
S
T
I
M
AT
I
O
N
O
F
T
H
E
P
A
RAM
E
T
E
RS A
ND
ASYM
P
T
O
T
I
C
P
RO
P
E
R
T
I
E
S
L
et
1
,
2
,
…
,
b
e
i
.
i
.
d
.
p
o
s
itiv
e
r
a
n
d
o
m
v
ar
iab
les
(
s
u
r
v
i
v
al
ti
m
es)
w
it
h
th
e
u
n
k
n
o
w
n
s
u
r
v
i
v
al
f
u
n
ctio
n
1
(
)
=
(
1
>
)
.
A
l
s
o
,
let
1
,
2
,
…
,
b
e
i
.
i
.
d
.
p
o
s
itiv
e
r
an
d
o
m
v
ar
iab
les
(
ce
n
s
o
r
in
g
ti
m
es)
w
it
h
th
e
u
n
k
n
o
w
n
s
u
r
v
i
v
al
f
u
n
ctio
n
2
(
)
=
(
1
>
)
;
T
is
c
alled
a
ce
n
s
o
r
i
n
g
v
ar
iab
le.
A
s
s
u
m
e
th
a
t
all
’s
an
d
’s
ar
e
in
d
ep
en
d
en
t
v
ar
iab
les.
A
r
an
d
o
m
l
y
ce
n
s
o
r
ed
d
ata
s
et
co
n
s
is
ts
o
f
i.i.
d
.
p
air
s
(
,
)
,
w
h
er
e
=
(
,
)
an
d
is
a
b
in
ar
y
r
an
d
o
m
v
ar
iab
le
=
(
,
)
;
=
1
,
2
,
…
,
;
=
1
if
it
is
o
b
s
er
v
ed
th
at
≤
an
d
=
0
if
it
is
o
b
s
er
v
ed
th
at
>
;
is
ca
lled
a
ce
n
s
o
r
ed
s
u
r
v
i
v
a
l
o
r
f
ailu
r
e
ti
m
e
r
an
d
o
m
v
ar
iab
le
.
Ass
u
m
i
n
g
,
th
e
s
u
r
v
i
v
al
ti
m
e,
i
=1
,
…,
n
,
an
d
,
ce
n
s
o
r
in
g
ti
m
e,
ar
e
i
n
d
ep
en
d
en
t
P
ar
eto
d
is
tr
ib
u
tio
n
s
w
it
h
p
r
o
b
ab
ilit
y
d
en
s
it
y
f
u
n
ctio
n
s
g
i
v
e
n
b
y
:
i
i
X
x
x
f
i
1
x
)
(
1
i
(
1
)
a
nd
i
i
T
t
t
f
i
1
t
)
(
1
i
(
2
)
T
h
e
s
u
r
v
i
v
al
f
u
n
ctio
n
i
s
s
s
s
x
x
X
P
x
S
1
)
(
)
(
(3
)
C
o
m
p
ar
ed
to
th
e
ex
p
o
n
en
tial
d
is
t
r
ib
u
tio
n
,
th
e
P
ar
eto
tail
r
etain
m
u
ch
m
o
r
e
p
r
o
b
a
b
ilit
y
;
an
d
th
e
s
u
r
v
iv
al
f
u
n
ctio
n
w
ill
d
ec
a
y
s
lo
w
l
y
to
ze
r
o
;
an
d
it
co
u
ld
b
e
a
g
o
o
d
m
o
d
el
to
d
escr
ib
e
s
u
ch
d
ata
w
it
h
h
ea
v
y
tailed
b
eh
av
io
r
.
[
I
f
(
,
)
;
i=1
,
…,
n
]
is
o
b
s
er
v
ed
,
th
en
th
e
d
is
tr
ib
u
tio
n
o
f
t
h
e
B
er
n
o
u
lli
r
an
d
o
m
v
ar
iab
le
o
f
is
1
1
1
)
(
)
1
(
i
x
i
i
i
i
i
i
i
dx
dt
t
x
T
X
P
D
P
(4
)
h
en
ce
)
0
(
i
D
P
I
t c
an
b
e
s
h
o
w
n
t
h
at
t
h
e
j
o
in
t p
r
o
b
a
b
ilit
y
d
en
s
i
t
y
f
u
n
ct
io
n
o
f
(
,
)
is
g
i
v
en
b
y
0
,
,
0
,
)
(
)
,
,
,
(
1
1
)
(
2
1
,
i
d
d
i
i
i
D
Y
y
y
d
y
f
i
i
i
i
(5
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t 2
0
1
9
:
3
2
7
2
-
3278
3274
Hav
i
n
g
i
n
m
in
d
t
h
at,
h
av
e
a
P
ar
eto
d
is
tr
ib
u
tio
n
w
it
h
p
ar
am
eter
(
α
+β)
,
t
o
d
er
iv
e
th
e
m
ax
i
m
u
m
lik
eli
h
o
o
d
esti
m
ato
r
s
f
o
r
α
an
d
β,
th
e
lik
el
ih
o
o
d
f
u
n
ctio
n
s
h
o
u
ld
b
e
u
s
ed
an
d
is
is
g
i
v
en
b
y
n
i
i
n
i
i
d
n
d
n
i
i
n
n
n
y
d
d
y
y
L
1
1
1
1
)
(
1
1
)
(
)
,
..
.,
,
,
..
.,
|
,
(
(6
)
)
(
)
,
..
.,
,
,
..
.,
|
,
(
1
1
1
)
(
1
1
n
d
n
i
i
n
n
n
n
i
i
y
d
d
y
y
L
(7
)
T
ak
in
g
lo
g
ar
it
h
m
o
f
b
o
th
s
id
es
1
1
)
(
1
1
*
ln
ln
ln
)
l
n
(
)
,
..
.,
,
,
..
.,
|
,
(
1
n
d
n
i
i
n
n
n
n
i
i
y
d
d
y
y
L
n
i
i
n
i
i
n
i
i
n
n
n
d
d
y
1
1
1
1
)
(
)
l
n
(
ln
ln
)
(
ln
)
(
)
l
n
(
)
l
n
(
(8
)
T
ak
in
g
p
ar
tial
d
er
iv
ati
v
es
o
f
l
o
g
lik
eli
h
o
o
d
f
u
n
ctio
n
w
i
th
r
e
s
p
ec
t
to
α
an
d
β,
eq
u
atin
g
to
ze
r
o
,
an
d
ch
ec
k
i
n
g
t
h
e
s
ec
o
n
d
p
ar
tial d
er
iv
ati
v
es to
b
e
less
t
h
an
ze
r
o
,
t
h
e
f
o
llo
w
i
n
g
m
a
x
i
m
u
m
l
ik
el
ih
o
o
d
esti
m
a
to
r
s
ca
n
b
e
o
b
tain
ed
:
n
i
i
n
i
i
y
d
1
1
ln
n
i
i
n
i
i
y
d
n
1
1
ln
T
h
e
ab
o
v
e
esti
m
ato
r
s
ar
e
r
atio
esti
m
ato
r
s
.
T
h
e
m
ea
n
s
an
d
v
ar
ian
ce
s
o
f
t
h
e
s
e
es
ti
m
a
to
r
s
ar
e
d
if
f
ic
u
lt
to
b
e
o
b
tain
;
th
u
s
,
an
d
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
esti
m
ato
r
s
w
i
l
l
b
e
in
v
esti
g
ated
v
ia
s
i
m
u
lati
o
n
.
T
h
e
in
f
o
r
m
atio
n
m
atr
i
x
is
g
iv
e
n
b
y
:
)
(
n
0
0
)
(
)
(
n
I
T
h
er
ef
o
r
e,
th
e
as
y
m
p
to
tic
v
a
r
ian
ce
-
co
v
ar
ian
ce
m
atr
i
x
,
i.e
.
th
e
i
n
v
er
s
e
o
f
t
h
e
i
n
f
o
r
m
ati
o
n
ca
n
b
e
ex
p
r
ess
ed
as:
n
n
I
)
(
0
0
)
(
)
(
1
T
h
e
asy
m
p
to
tic
d
is
tr
ib
u
ti
o
n
o
f
ML
E
’
s
o
f
t
h
e
p
ar
a
m
eter
s
α
an
d
β ca
n
b
e
w
r
itte
n
as
))
(
,
0
(
)
,
(
1
3
I
N
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
R
elia
b
ilit
y
e
s
tima
tio
n
fo
r
th
e
r
a
n
d
o
mly
ce
n
s
o
r
ed
p
a
r
eto
d
is
tr
ib
u
tio
n
(
Ma
h
mo
u
d
M.
S
ma
d
i
)
3275
Sin
ce
I
-
1
(
)
in
v
o
l
v
e
t
h
e
u
n
k
n
o
w
n
p
ar
a
m
eter
s
,
t
h
e
y
ca
n
b
e
r
ep
lace
d
b
y
t
h
e
co
r
r
esp
o
n
d
in
g
M
L
e
s
ti
m
ate
s
.
T
h
u
s
,
th
e
ap
p
r
o
x
i
m
a
te
(
1
-
α
)
1
0
0
% c
o
n
d
id
en
ce
in
ter
v
al
s
f
o
r
α
an
d
β,
r
esp
ec
ti
v
el
y
,
ar
e
22
2
/
11
2
/
a
n
d
V
Z
V
Z
.
v
a
r
i
a
n
c
e
s
e
s
t
i
m
a
t
e
d
t
h
e
a
r
e
V
a
n
d
V
w
h
e
r
e
22
11
3.
E
S
T
I
M
AT
I
O
N
O
F
T
H
E
S
U
RVIVA
L
F
UNC
T
I
O
N
AND
ASYM
P
T
O
T
I
C
P
RO
P
E
R
T
I
E
S
T
o
o
b
tain
th
e
m
ax
i
m
u
m
li
k
eli
h
o
o
d
esti
m
ato
r
s
o
f
th
e
s
u
r
v
i
v
al
f
u
n
ct
io
n
s
,
1
(
)
an
d
2
(
)
.
T
h
e
f
o
llo
w
i
n
g
a
n
al
y
s
i
s
ca
n
b
e
p
er
f
o
r
m
ed
.
T
o
f
ix
an
d
let
)]
(
),
(
[
)]
(
),
(
[
)
(
1
1
2
1
y
Y
P
x
X
P
y
S
x
S
H
Usi
n
g
i
n
v
ar
ia
n
ce
p
r
o
p
er
ty
o
f
t
h
e
M
L
E
,
th
e
M
L
E
o
f
1
(
)
an
d
2
(
)
ca
n
b
e
ex
p
r
ess
ed
as:
x
x
dz
z
x
X
P
1
1
)
(
ˆ
(9
)
an
d
)
(
1
)
(
1
)
(
)
(
ˆ
y
dz
z
y
Y
P
y
(
1
0
)
T
h
u
s
th
e
M
L
E
o
f
)
(
,
)
(
y
x
H
ca
n
b
e
ex
p
r
ess
ed
as:
)
(
,
)
(
ˆ
y
x
H
T
h
e
ab
o
v
e
esti
m
ato
r
s
ar
e
r
atio
esti
m
ato
r
s
;
m
ea
n
s
an
d
v
ar
i
an
ce
s
o
f
t
h
ese
est
i
m
a
to
r
s
ar
e
d
if
f
ic
u
lt
to
o
b
tain
,
th
u
s
,
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
esti
m
ato
r
s
w
i
ll
b
e
in
v
e
s
ti
g
ated
v
ia
s
i
m
u
latio
n
.
Un
d
er
c
er
tain
r
eg
u
lar
i
t
y
co
n
d
itio
n
s
,
t
h
e
as
y
m
p
to
tic
d
is
t
r
ib
u
tio
n
ca
n
b
e
g
iv
e
n
b
y
[
1
4
]
)
)
)
(
(
)
(
,
0
(
)]
(
)
(
[
T
H
H
N
H
H
n
T
h
e
m
atr
i
x
o
f
p
ar
tial d
er
iv
ati
v
es
)
(
-
)
-(
-
y
0
y
x
)
(
B
B
A
H
y
B
x
A
l
o
g
1
a
n
d
l
o
g
1
w
h
e
r
e
T
h
u
s
th
e
a
s
y
m
p
to
tic
v
ar
ia
n
ce
-
co
v
ar
ian
ce
m
atr
ix
o
f
)
(
ˆ
H
is
g
iv
e
n
b
y
)
(
2
2
)
(
2
2
)
(
2
2
)
2(
-
2
2
-
2
)
(
B
)
(
B
)
(
B
)
y
B
x
(A
y
y
y
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t 2
0
1
9
:
3
2
7
2
-
3278
3276
4.
SI
M
UL
AT
I
O
N
A
Mo
n
te
C
ar
lo
s
i
m
u
la
tio
n
was
u
s
ed
to
in
v
esti
g
ate
t
h
e
p
e
r
f
o
r
m
an
ce
o
f
t
h
e
m
ax
i
m
u
m
l
ik
eli
h
o
o
d
esti
m
ato
r
s
o
f
α
,
β,
a
n
d
th
e
s
u
r
v
iv
a
l
f
u
n
ctio
n
(
1
>
)
d
ev
elo
p
ed
in
t
h
e
p
r
ev
io
u
s
s
ec
tio
n
s
.
Fo
r
t
h
e
s
u
r
v
iv
a
l
f
u
n
ctio
n
th
e
v
al
u
e
o
f
x
s
,
w
a
s
co
n
s
id
er
ed
as
th
e
m
ea
n
o
f
th
e
s
u
r
v
iv
al
ti
m
e.
T
h
e
s
i
m
u
la
tio
n
s
tu
d
y
w
a
s
co
n
d
u
cted
u
s
i
n
g
d
if
f
er
en
t
c
o
m
b
i
n
atio
n
s
o
f
p
ar
a
m
eter
v
alu
es
an
d
s
a
m
p
le
s
izes
o
f
5
0
,
1
5
0
,
an
d
3
0
0
.
T
h
e
s
i
m
u
latio
n
r
es
u
lt
s
w
er
e
b
ased
o
n
1
0
0
0
r
ep
licates.
T
h
e
m
ea
n
s
a
n
d
r
o
o
t
m
ea
n
s
q
u
ar
e
e
r
r
o
r
s
(
R
MSE
)
o
f
t
h
e
m
ax
i
m
u
m
li
k
eli
h
o
o
d
esti
m
ato
r
s
w
er
e
ca
lc
u
lated
.
W
ith
co
m
b
i
n
a
tio
n
o
f
d
if
f
er
en
t
s
etti
n
g
s
o
f
α
,
β
a
n
d
s
a
m
p
le
s
ize
n
,
in
ev
er
y
ca
s
e
w
e
th
e
f
o
llo
w
in
g
a
lg
o
r
ith
m
w
as
u
s
ed
to
o
b
tain
t
h
e
s
i
m
u
latio
n
r
es
u
lt
s
:
Step
1
: G
en
er
ate
x
1
,x
2
,
…,
x
n
f
r
o
m
P
ar
eto
(
α
)
Step
2
: G
en
er
ate
T
1
,T
2
,
…,
T
n
f
r
o
m
P
ar
eto
(
β)
Step
3
: Set
Y
i
=
m
i
n
(
X
i
,T
i
)
,
I
=
1
,
2
,
…,
n
Step
4
: Fo
r
i=1
,
2
,
…,
n
,
s
et
i
T
T
i
i
i
i
X
if
0
X
if
1
D
Step
5
: Set
th
e
m
a
x
i
m
u
m
lik
e
l
ih
o
o
d
esti
m
ate
s
as
f
o
llo
w
s
n
i
i
n
i
i
y
d
1
1
ln
n
i
i
n
i
i
y
d
n
1
1
ln
S6
:
R
ep
ea
t
s
tep
s
S1
-
S5
f
o
r
1
0
0
0
iter
atio
n
s
,
co
m
p
u
te
t
h
e
m
ea
n
a
n
d
m
ea
n
s
q
u
ar
e
er
r
o
r
o
f
th
e
m
a
x
i
m
u
m
lik
eli
h
o
o
d
esti
m
a
tes
f
o
r
α
a
n
d
β
.
T
h
e
r
esu
lts
ar
e
d
is
p
la
y
ed
in
T
ab
les 1
-
3
.
T
h
e
f
o
llo
w
i
n
g
r
e
m
ar
k
s
ca
n
b
e
d
r
a
wn
b
ased
o
n
th
ese
r
es
u
lts
:
T
h
e
r
esu
lts
i
n
d
icate
th
at
t
h
e
b
i
as
an
d
MSE
’
s
w
er
e
r
ea
s
o
n
ab
l
y
g
o
o
d
in
all
ca
s
e
s
.
As
th
e
s
h
ap
e
o
f
th
e
p
ar
am
ete
r
s
α
an
d
β
in
cr
ea
s
es
(
cu
r
v
e
s
d
ec
ay
s
f
as
ter
)
,
th
e
R
MSE
o
f
th
e
m
a
x
i
m
u
m
lik
eli
h
o
o
d
esti
m
ato
r
s
o
f
th
e
p
a
r
a
m
eter
s
α
a
n
d
β in
cr
ea
s
es.
As
th
e
s
u
r
v
iv
al
ti
m
e
s
cu
r
v
e
d
ec
r
ea
s
es
f
as
ter
(
α
in
cr
ea
s
e
s
)
an
d
ce
n
s
o
r
in
g
ti
m
es
c
u
r
v
e
d
ec
a
y
s
s
lo
w
er
(
β
d
ec
r
ea
s
es),
th
e
R
MSE
d
ec
ea
s
es.
A
s
s
u
r
v
iv
a
l
ti
m
e
s
cu
r
v
e
s
l
o
w
l
y
d
ec
r
ea
s
e
s
(
α
d
ec
r
ea
s
es)
an
d
ce
n
s
o
r
in
g
ti
m
e
s
cu
r
v
e
d
ec
a
y
s
f
aster
(
β i
n
cr
ea
s
es),
th
e
R
M
SE
in
cr
ea
s
e
s
.
As ex
p
ec
ted
th
e
b
iase a
n
d
R
M
SE
d
ec
r
ea
s
e
as th
e
s
a
m
p
le
s
iz
es in
cr
ea
s
e
s
.
Me
an
s
a
n
d
R
MSE
o
f
M
L
E
’
S
o
f
α
an
d
β,
)
(
1
s
x
X
P
,
)
(
1
s
x
X
P
,
n
=5
0
,
n
=1
5
0
,
n
=3
0
0
as
s
h
o
w
n
in
T
ab
le
s
1
,
2
an
d
3
.
T
ab
le
1
.
Me
an
s
an
d
R
MSE
o
f
ML
E
’
S o
f
α
an
d
β,
)
(
1
s
x
X
P
,
)
(
1
s
x
X
P
,
n
=5
0
R
M
S
E
R
M
S
E
)
(
1
s
x
X
P
)
(
1
s
x
X
P
R
M
S
E
2
2
.
0
2
5
3
5
0
.
4
1
4
3
9
2
2
.
0
4
5
3
6
0
.
4
2
0
4
0
0
.
2
5
0
0
0
0
.
2
5
5
3
2
0
.
0
6
8
6
0
2
2
.
0
2
7
4
2
0
.
4
9
3
9
0
4
4
.
0
8
8
6
1
0
.
7
3
8
4
0
0
.
2
5
0
0
0
0
.
2
5
9
0
6
0
.
0
8
3
3
4
4
4
.
0
6
4
6
2
0
.
7
1
4
6
2
2
2
.
0
4
3
4
6
0
.
3
1
6
4
1
0
.
3
1
6
4
1
0
.
3
1
6
9
0
0
.
0
6
1
87
4
4
.
0
5
0
7
1
0
.
8
2
8
7
8
4
4
.
0
9
0
7
2
0
.
8
4
0
8
0
0
.
3
1
6
4
1
0
.
3
2
0
3
2
0
.
0
7
1
9
0
4
4
.
0
3
6
0
1
0
.
9
1
0
2
2
6
6
.
1
4
7
5
9
1
.
6
6
6
7
7
0
.
3
1
6
4
1
0
.
3
2
3
5
0
0
.
0
8
0
3
0
4
4
.
0
5
4
8
4
0
.
9
8
7
8
0
8
8
.
1
7
7
2
3
1
.
4
7
6
7
9
0
.
3
1
6
4
1
0
.
3
2
3
5
3
0
.
0
8
6
6
5
6
6
.
1
0
1
0
8
1
.
3
3
1
4
3
4
4
.
0
7
4
3
4
0
.
9
3
1
5
4
0
.
3
3
4
9
0
0
.
3
3
5
5
2
0
.
0
6
5
8
6
8
8
.
1
2
9
2
3
1
.
4
2
9
2
4
4
4
.
0
8
6
9
2
1
.
0
2
7
5
3
0
.
3
4
3
6
1
0
.
3
4
3
6
6
0
.
0
6
2
4
5
6
6
.
0
7
6
0
7
1
.
2
4
3
1
2
6
6
.
1
2
6
0
8
1
.
2
6
1
2
0
0
.
3
3
4
9
0
0
.
3
3
8
4
3
0
.
0
7
2
3
5
6
6
.
0
5
4
0
1
1
.
3
6
5
3
4
9
9
.
2
2
1
3
9
1
.
7
5
0
1
5
0
.
3
3
4
9
0
0
.
3
4
1
5
4
0
.
0
8
0
7
1
6
6
.
0
8
2
2
6
1
.
4
8
1
7
0
12
1
2
.
2
6
5
8
3
2
.
2
1
5
1
9
0
.
3
3
4
9
0
0
.
3
4
1
4
8
0
.
0
8
7
0
6
9
9
.
1
5
1
6
2
1
.
6
9
7
1
5
6
6
.
1
1
1
4
9
1
.
3
9
7
3
1
0
.
3
4
6
4
4
0
.
3
4
6
8
6
0
.
0
6
6
0
4
12
1
2
.
1
9
3
8
4
2
.
1
4
3
8
6
6
6
.
1
7
0
3
8
1
.
5
4
1
3
0
0
.
3
5
2
0
0
0
.
3
5
1
9
2
0
.
0
6
2
5
6
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
R
elia
b
ilit
y
e
s
tima
tio
n
fo
r
th
e
r
a
n
d
o
mly
ce
n
s
o
r
ed
p
a
r
eto
d
is
tr
ib
u
tio
n
(
Ma
h
mo
u
d
M.
S
ma
d
i
)
3277
T
ab
l
e
2
.
Me
an
s
an
d
R
MSE
o
f
ML
E
’
S
o
f
α
an
d
β,
)
(
1
s
x
X
P
,
)
(
1
s
x
X
P
,
n
=1
5
0
R
M
S
E
R
M
S
E
)
(
1
s
x
X
P
)
(
1
s
x
X
P
R
M
S
E
2
2
.
0
1
4
9
9
0
.
2
3
9
6
1
2
2
.
0
1
4
1
3
0
.
2
3
1
3
5
0
.
2
5
0
0
0
0
.
2
5
0
7
6
0
.
0
4
0
5
9
2
2
.
0
1
7
5
3
0
.
2
8
9
4
9
4
4
.
0
2
0
1
4
0
.
4
0
6
7
8
0
.
2
5
0
0
0
0
.
2
5
1
8
6
0
.
0
4
9
1
8
4
4
.
0
2
5
5
8
0
.
4
1
8
2
6
2
2
.
0
2
2
0
0
0
.
2
8
6
2
6
0
.
3
1
6
4
1
0
.
3
1
6
3
3
0
.
0
3
7
3
3
4
4
.
0
2
9
9
9
0
.
4
7
9
2
2
4
4
.
0
2
8
2
6
0
.
4
6
2
7
1
0
.
3
1
6
4
1
0
.
3
1
6
6
2
0
.
0
4
6
6
2
4
4
.
0
3
1
2
5
0
.
5
3
5
9
1
6
6
.
0
3
4
2
8
0
.
6
4
4
4
6
0
.
3
1
6
4
1
0
.
3
1
7
5
2
0
.
0
4
8
0
7
4
4
.
0
3
5
0
7
0
.
5
7
8
9
9
8
8
.
0
4
0
2
9
0
.
8
1
7
5
7
0
.
3
1
6
4
1
0
.
3
1
7
5
0
0
.
0
5
1
6
0
6
6
.
0
3
4
7
9
0
.
6
5
9
8
8
4
4
.
0
4
4
4
5
0
.
5
1
7
0
1
0
.
3
3
4
9
0
0
.
3
3
4
9
0
0
.
0
3
9
5
1
8
8
.
0
5
1
1
5
0
.
8
3
6
5
2
4
4
.
0
4
4
0
0
0
.
5
7
3
5
3
0
.
3
4
3
6
1
0
.
3
4
3
3
7
0
.
0
3
7
6
5
6
6
.
0
4
4
9
8
0
.
7
1
8
8
3
6
6
.
0
4
2
3
9
0
.
6
9
4
0
6
0
.
3
3
4
9
0
0
.
3
3
4
9
7
0
.
0
4
2
9
4
6
6
.
0
4
6
8
7
0
.
8
0
3
8
7
9
9
.
0
5
1
4
4
0
.
9
6
6
6
8
0
.
3
3
4
9
0
0
.
3
3
5
5
7
0
.
0
4
8
3
5
6
6
.
0
5
2
6
1
0
.
8
6
8
4
0
12
1
2
.
0
6
0
4
2
1
.
2
2
6
3
5
0
.
3
3
4
9
0
0
.
3
3
5
7
9
0
.
0
5
1
9
2
9
6
.
0
5
2
6
1
0
.
8
6
8
4
0
6
6
.
0
6
6
6
0
0
.
7
7
5
5
1
0
.
3
4
6
4
4
0
.
3
4
6
6
2
0
.
0
3
9
6
1
12
1
2
.
0
7
6
7
3
1
.
2
5
4
7
9
6
6
.
0
6
6
0
0
0
.
8
6
0
0
0
0
.
3
5
2
0
0
0
.
3
5
1
7
1
0
.
0
3
7
7
1
T
ab
l
e
3
.
Me
an
s
an
d
R
MSE
o
f
ML
E
’
S o
f
α
an
d
β,
)
(
1
s
x
X
P
,
)
(
1
s
x
X
P
,
n
=3
0
0
R
M
S
E
R
M
S
E
)
(
1
s
x
X
P
)
(
1
s
x
X
P
R
M
S
E
2
2
.
0
0
1
2
2
0
.
1
6
2
1
1
2
2
.
0
1
4
2
0
0
.
1
7
4
4
1
0
.
2
5
0
0
0
0
.
2
5
1
3
5
0
.
0
2
7
8
0
2
2
.
0
0
1
6
0
0
.
1
9
2
9
5
4
4
.
0
2
8
5
4
0
.
3
0
4
6
2
0
.
2
5
0
0
0
0
.
2
5
1
9
2
0
.
0
3
3
0
0
4
4
.
0
0
4
7
4
0
.
2
8
2
7
6
2
2
.
0
1
4
0
1
0
.
2
0
9
4
0
0
.
3
1
6
4
1
0
.
3
1
7
0
1
0
.
0
2
5
5
3
4
4
.
0
0
2
4
4
0
.
3
2
4
2
1
4
4
.
0
2
8
4
0
0
.
3
4
8
8
1
0
.
3
1
6
4
1
0
.
3
1
7
5
5
0
.
0
2
9
2
1
4
4
.
0
0
8
0
7
0
.
3
5
4
9
1
6
6
.
0
3
7
6
4
0
.
4
7
9
5
6
0
.
3
1
6
4
1
0
.
3
1
7
3
0
0
.
0
3
1
8
9
4
4
.
0
0
3
1
9
0
.
3
8
5
8
9
8
8
.
0
5
7
0
8
0
.
6
0
9
2
4
0
.
3
1
6
4
1
0
.
3
1
8
0
4
0
.
0
3
4
6
6
6
6
.
0
0
6
1
8
0
.
4
4
7
7
2
4
4
.
0
2
6
8
2
0
.
3
8
5
2
9
0
.
3
3
4
9
0
0
.
3
3
5
6
2
0
.
0
2
7
0
3
8
8
.
0
0
9
4
9
0
.
5
6
5
5
1
4
4
.
0
2
8
0
2
0
.
4
1
8
0
1
0
.
3
4
3
6
0
0
.
3
4
4
1
4
0
.
0
2
5
7
5
6
6
.
0
0
3
6
5
0
.
4
8
6
3
2
6
6
.
0
4
2
6
0
0
.
5
2
3
2
2
0
.
3
3
4
9
0
0
.
3
3
5
9
8
0
.
0
2
9
4
0
6
6
.
0
1
2
1
0
0
.
5
3
2
3
7
9
9
.
0
5
6
4
6
0
.
7
1
9
3
4
0
.
3
3
4
9
0
0
.
3
3
5
7
2
0
.
0
3
2
0
9
6
6
.
0
0
4
7
9
0
.
5
7
8
8
4
12
1
2
.
0
8
5
6
2
0
.
9
1
3
8
6
0
.
3
3
4
9
0
0
.
3
3
6
4
4
0
.
0
3
4
8
8
9
9
.
0
0
9
2
7
0
.
6
7
1
5
0
6
6
.
0
4
0
2
3
0
.
5
7
7
9
4
0
.
3
4
6
4
4
0
.
3
4
6
4
4
0
.
3
4
7
3
1
12
1
2
.
0
1
4
2
4
0
.
8
4
8
2
7
6
6
.
0
4
2
0
3
0
.
6
2
8
2
1
0
.
3
5
2
0
0
0
.
3
5
2
5
1
0
.
0
2
5
7
0
5.
CO
NCLU
SI
O
N
T
h
e
ML
E
’
s
f
o
r
m
o
d
el
p
ar
am
eter
s
a
n
d
s
u
r
v
i
v
al
f
u
n
ctio
n
s
w
er
e
d
er
iv
ed
alo
n
g
w
i
th
t
h
e
Fi
s
h
e
r
in
f
o
r
m
atio
n
m
atr
i
x
an
d
as
y
m
p
to
tic
co
n
f
id
en
ce
in
ter
v
als.
A
s
i
m
u
latio
n
s
tu
d
y
v
er
i
f
ied
th
e
b
eh
av
io
r
o
f
th
e
ML
E
’
s
.
T
h
e
r
es
u
lts
s
h
o
w
ed
t
h
at
th
e
b
ias
a
n
d
MSE
w
er
e
r
ea
s
o
n
ab
l
y
s
m
all
i
n
all
ca
s
es
.
I
t
i
s
s
h
o
w
n
t
h
at
a
s
t
h
e
s
h
ap
e
p
ar
a
m
eter
s
f
o
r
P
ar
eto
d
is
tr
ib
u
tio
n
s
in
cr
ea
s
es
(
i.e
.
cu
r
v
e
s
d
ec
a
y
s
f
aster
)
,
th
e
R
MSE
o
f
th
e
M
L
E
’
s
in
cr
ea
s
e
s
.
A
s
th
e
s
u
r
v
i
v
al
t
i
m
es
cu
r
v
e
d
ec
r
ea
s
es
f
a
s
ter
a
n
d
ce
n
s
o
r
in
g
t
i
m
e
s
c
u
r
v
e
d
ec
a
y
s
s
lo
w
er
,
t
h
e
R
MSE
d
ec
ea
s
es a
n
d
v
ia
v
er
s
a
.
RE
F
E
R
E
NC
E
S
[1
]
L
.
M
.
L
e
e
m
i
s
,
“
Re
li
a
b
il
it
y
,
p
ro
b
a
b
il
isti
c
m
o
d
e
ls
a
n
d
sta
ti
stica
l
m
e
th
o
d
s,
”
P
re
n
ti
c
e
Ha
ll
,
En
g
lew
o
o
d
Cli
f
f
s,
Ne
w
Je
rse
y
,
1995
.
[2
]
N.
Ba
lak
risn
a
n
a
n
d
R.
A
g
g
a
r
wa
la,
“
P
r
o
g
re
ss
iv
e
Ce
n
so
rin
g
:
T
h
e
o
ry
,
M
e
th
o
d
s
a
n
d
A
p
p
li
c
a
ti
o
n
s
,
”
Birk
h
a
u
se
r,
Bo
sto
n
,
2
0
0
0
.
[3
]
N.
B
alak
r
is
h
n
a
n
,
D.
De
b
a
sis
Ku
n
d
u
,
“
Hy
b
rid
c
e
n
so
ri
n
g
:
M
o
d
e
ls,
in
f
e
re
n
ti
a
l
re
su
lt
s
a
n
d
a
p
p
li
c
a
ti
o
n
s,
”
Co
m
p
u
tatio
n
a
l
S
tatisti
c
s &
Da
ta A
n
a
l
y
si
s,
5
7
(
1
),
1
6
6
-
2
0
9
,
2
0
1
3
.
[4
]
A
.
A
.
A
b
u
-
T
a
leb
,
a
n
d
M
.
M
.
S
m
a
d
i,
“
A
s
y
m
p
to
ti
c
e
ff
icie
n
c
ies
o
f
th
e
su
rv
iv
a
l
f
u
n
c
ti
o
n
s
e
stim
a
to
rs
f
o
r
th
e
e
x
p
o
n
e
n
ti
a
l
d
istri
b
u
ti
o
n
,
”
In
ter
n
a
ti
o
n
a
l
M
a
th
e
m
a
ti
c
a
l
F
o
ru
m
,
No
.
3
8
,
1
8
6
1
-
1
8
6
9
,
2
0
0
6
.
[5
]
M
.
S
a
lee
m
a
n
d
M
.
A
sla
m
,
“
On
B
a
y
e
sia
n
a
n
a
l
y
sis
o
f
th
e
Ra
y
lei
g
h
s
u
rv
iv
a
l
ti
m
e
a
ss
u
m
in
g
th
e
ra
n
d
o
m
c
e
n
so
r
ti
m
e
,
”
Pa
k
.
J
.
S
ta
t
isti
c
s
,
V
o
l.
2
5
,
N
o
.
2
,
7
1
-
82
,
2
0
0
9
.
[6
]
M
.
Y.
Da
n
ish
a
n
d
M
.
A
sla
m
,
“
Ba
y
e
sia
n
in
f
e
re
n
c
e
f
o
r
th
e
ra
n
d
o
m
l
y
c
e
n
so
re
d
W
e
ib
u
ll
d
istri
b
u
t
io
n
,
”
J
o
u
rn
a
l
o
f
S
ta
ti
st
ica
l
C
o
mp
u
ti
n
g
a
n
d
S
im
u
la
ti
o
n
,
V
o
l
.
8
4
,
N
o
.
1
,
2
1
5
-
2
3
0
,
2
0
1
4
.
[7
]
H.
Krish
n
a
,
V
iv
e
k
a
n
a
n
d
,
K.
K
u
m
a
r,
“
Esti
m
a
ti
o
n
in
M
a
x
we
ll
d
istri
b
u
ti
o
n
w
it
h
ra
n
d
o
m
l
y
c
e
n
so
re
d
d
a
ta,
”
J
o
u
rn
a
l
o
f
S
ta
ti
st
ica
l
C
o
mp
u
ti
n
g
a
n
d
S
im
u
la
ti
o
n
,
V
o
l
.
8
5
,
N
o
.
1
7
,
3
5
6
0
-
3
5
7
8
,
2
0
1
5
.
[8
]
N.
L
.
Jo
n
n
so
n
.
,
S
.
Ko
tz,
N.
Ba
lak
rish
n
a
n
,
“
Co
n
ti
n
o
u
s
U
n
iv
a
riate
Distrib
u
ti
o
n
s
,
”
Vo
l.
1
2
nd
e
d
.
Jo
h
n
W
il
e
y
Ba
lak
rish
n
a
n
&
S
o
n
s,
Ne
w
Yo
rk
,
1
9
9
4
.
[9
]
T
.
N.
S
in
d
h
u
,
M
.
A
sa
la
m
.
,
a
n
d
A.
S
h
a
f
iq
,
“
A
n
a
l
y
sis
o
f
th
e
le
f
t
c
e
n
so
re
d
d
a
ta
f
ro
m
th
e
P
a
re
to
ty
p
e
II
d
istri
b
u
ti
o
n
,
”
Ca
sp
ia
n
J
o
u
rn
a
l
o
f
A
p
p
l
ied
S
c
ie
n
c
e
s R
e
se
a
rc
h
,
2
(7
),
5
3
-
6
2
,
2
0
1
3
.
[1
0
]
M
.
A
sg
h
a
rz
a
d
e
h
,
M
.
M
o
h
a
m
m
a
d
p
o
u
r
M
.
,
Z.
M
.
G
a
n
ji
,
“
Esti
m
a
ti
o
n
a
n
d
re
c
o
n
str
u
c
ti
o
n
b
a
se
d
o
n
lef
t
c
e
n
so
re
d
d
a
ta
f
ro
m
P
a
re
to
m
o
d
e
l
,
”
J
IRS
S
,
Vo
l.
1
3
,
N
o
.
2
,
1
5
1
-
1
7
5
,
2
0
1
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
4
,
A
u
g
u
s
t 2
0
1
9
:
3
2
7
2
-
3278
3278
[1
1
]
U
Iih
a
n
a
n
d
H.
G
e
z
e
r
,
“
Re
li
a
b
il
it
y
e
sti
m
a
ti
o
n
in
P
a
re
t
o
-
I
d
istri
b
u
ti
o
n
b
a
se
d
o
n
p
ro
g
re
ss
iv
e
l
y
t
y
p
e
II
c
e
n
so
re
d
sa
m
p
le w
it
h
b
in
o
m
ial
re
m
o
v
a
ls,”
J
o
u
rn
a
l
o
f
sc
ien
ti
fi
c
re
se
a
rc
h
a
n
d
d
e
v
e
l
o
p
me
n
t
,
V
o
l.
2
,
No
.
1
2
,
1
0
8
-
1
1
3
,
2
0
1
5
.
[1
2
]
W
.
S
h
u
o
,
“
Esti
m
a
ti
o
n
f
o
r
th
e
tw
o
-
p
a
ra
m
e
ter
P
a
re
to
d
istri
b
u
ti
o
n
u
n
d
e
r
p
ro
g
re
ss
iv
e
c
e
n
so
rin
g
w
it
h
u
n
if
o
rm
re
m
o
v
a
ls,
”
J
o
u
rn
a
l
o
f
st
a
ti
stica
l
c
o
mp
u
t
in
g
a
n
d
simu
l
a
ti
o
n
,
Vo
l.
7
3
(2
),
1
2
5
-
1
3
4
,
2
0
0
8
.
[1
3
]
W
u
S
.
a
n
d
Ch
a
n
g
C.
,
“
In
f
e
r
e
n
c
e
in
th
e
P
a
re
o
d
istri
b
u
t
io
n
b
a
se
d
o
n
p
ro
g
re
ss
iv
e
t
y
p
e
II
c
e
n
so
rin
g
w
it
h
ra
n
d
o
m
re
m
o
v
a
ls,
”
J
o
u
rn
a
l
o
f
a
p
p
li
e
d
st
a
ti
stics
,
Vo
l.
3
0
,
No
.
2
,
1
6
3
-
1
7
2
,
2
0
0
3
.
[1
4
]
S
.
P
a
rsi.
,
M
.
G
a
n
jali.
,
a
n
d
S
.
F
a
rs
ip
o
u
.
,
“
S
im
u
lt
a
n
e
o
u
s
c
o
n
f
id
e
n
c
e
in
terv
a
l
f
o
r
th
e
p
a
ra
m
e
ters
o
f
P
a
re
to
d
istri
b
u
ti
o
n
u
n
d
e
r
p
ro
g
re
ss
iv
e
c
e
n
so
rin
g
,
”
Co
m
m
u
n
ica
ti
o
n
in
S
tatisti
c
s
-
T
h
e
o
ry
a
n
d
M
e
t
h
o
d
s,
3
9
:
9
4
-
1
0
6
,
2
0
1
0
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
M
a
h
m
o
u
d
M
.
S
m
a
d
i
,
h
e
r
e
c
ie
v
e
d
h
is
B.
S
a
n
d
M
.
S
d
e
g
re
e
s
in
sta
ti
stics
f
ro
m
Ya
r
m
o
u
k
Un
iv
e
rsit
y
in
1
9
8
3
a
n
d
1
9
8
6
,
re
sp
e
c
tev
y
.
He
re
c
iev
e
d
h
is
P
h
.
D
i
n
sta
ti
stics
f
ro
m
Co
lo
ra
d
o
S
tate
Un
iv
e
rsity
in
1
9
9
7
.
S
i
n
c
e
1
9
9
7
h
e
w
o
rk
e
d
f
o
r
th
e
De
p
a
rtm
e
n
t
o
f
M
a
th
e
m
a
ti
c
s
&
S
tatisti
c
s
a
t
Jo
rd
a
n
Un
iv
e
rsit
y
o
f
S
c
ien
c
e
&
T
e
c
h
n
o
lo
g
y
,
Jo
rd
a
n
.
He
is
c
u
rre
n
tl
y
a
ss
o
c
iat
e
p
ro
f
e
ss
o
r
a
t
D
e
p
a
rt
m
e
n
t
o
f
M
a
th
e
m
a
ti
c
s
&
S
tatisti
c
s
a
t
Jo
rd
a
n
Un
iv
e
rsity
o
f
S
c
ien
c
e
&
T
e
c
h
n
o
lo
g
y
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
su
rv
iv
a
l
a
n
d
re
li
a
b
i
li
ty
a
n
a
l
y
sis,
b
io
sta
ti
stics
a
n
d
g
e
n
e
re
li
z
e
d
d
istr
ib
u
ti
o
n
s.
S
a
ifu
l
Is
la
m
Ansa
r
i
re
c
e
iv
e
d
h
i
s
M
.
P
h
i
l.
a
n
d
P
h
.
D.
i
n
2
0
0
8
a
n
d
2
0
1
1
re
sp
e
c
ti
v
e
ly
f
ro
m
A
li
g
a
rh
M
u
slim
Un
iv
e
rsit
y
,
A
li
g
a
rh
,
In
d
ia.
Cu
rre
n
tl
y
h
e
is
w
o
rk
in
g
a
s
A
ss
istan
t
P
ro
f
e
ss
o
r
in
t
h
e
d
e
p
a
rtm
e
n
t
o
f
S
tatisti
c
s
a
t
Un
iv
e
rsit
y
o
f
T
a
b
u
k
,
T
a
b
u
k
,
KS
A
.
His
re
se
a
rc
h
a
re
a
s
o
f
in
tere
st
a
re
S
to
c
h
a
stic
P
r
o
g
ra
m
m
in
g
,
Re
li
a
b
il
it
y
Op
ti
m
iz
a
ti
o
n
,
Dist
rib
u
ti
o
n
T
h
e
o
ry
,
S
tatisti
c
a
l
c
o
m
p
u
ti
n
g
e
tc.
Ahm
e
d
A.
J
a
r
a
d
a
t
,
h
e
re
c
e
i
v
e
d
h
is
B.
S
a
n
d
M
.
S
d
e
g
re
e
s
in
sta
ti
st
ics
f
ro
m
Ya
r
m
o
u
k
Un
iv
e
r
sit
y
in
1
9
8
4
a
n
d
1
9
8
6
,
re
sp
e
c
ti
v
e
l
y
.
He
re
c
e
iv
e
d
h
is
P
h
.
D.
i
n
sta
ti
stics
f
ro
m
No
rth
Da
k
o
ta
S
tate
Un
iv
e
rsit
y
,
th
e
USA
in
1
9
9
6
.
Cu
r
re
n
tl
y
,
h
e
is
w
o
rk
in
g
a
s
As
so
c
iate
P
r
o
f
e
ss
o
r
a
t
th
e
De
p
a
rt
m
e
n
t
o
f
F
a
m
il
y
a
n
d
Co
m
m
u
n
it
y
M
e
d
icin
e
a
t
A
ra
b
ian
G
u
lf
Un
iv
e
rsit
y
,
Ba
h
ra
in
.
His
re
se
a
r
c
h
in
tere
sts
in
c
l
u
d
e
Bio
sta
ti
stics
,
S
u
rv
iv
a
l
a
n
d
re
li
a
b
il
it
y
a
n
a
l
y
sis.
Evaluation Warning : The document was created with Spire.PDF for Python.