I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d Science
s
(
I
J
AAS)
Vo
l.
10
,
No
.
2
,
J
u
n
e
2
0
2
1
,
p
p
.
115
~
1
2
1
I
SS
N:
2
2
5
2
-
8
8
1
4
,
DOI
: 1
0
.
1
1
5
9
1
/ijaas.v
1
0
.
i
2
.
p
p
115
-
1
2
1
115
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
a
s
.
ia
esco
r
e.
co
m
Co
nfirma
tory
f
a
c
tor a
na
ly
sis
:
m
o
del t
esti
ng
of f
ina
n
cia
l
ra
tio
s
with
d
ecisio
n sup
po
rt
sy
stems a
ppr
o
a
ch
T
.
H
us
a
in
1
,
M
a
u
la
na
Ardhia
ns
y
a
h
2
,
Dedin F
a
t
hu
d
in
3
1
De
p
a
rtem
e
n
t
o
f
In
f
o
rm
a
ti
o
n
S
y
st
e
m
s,
S
TM
IK W
id
u
ri,
In
d
o
n
e
sia
2,
3
De
p
a
rtme
n
t
o
f
I
n
f
o
rm
a
ti
c
s E
n
g
i
n
e
e
rin
g
,
Un
i
v
e
rsitas
P
a
m
u
lan
g
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
5
,
2
0
20
R
ev
is
ed
No
v
2
5
,
2
0
20
Acc
ep
ted
J
an
2
3
,
2
0
2
1
Th
e
d
e
c
isio
n
s
u
p
p
o
rt
sy
ste
m
s
a
p
p
ro
a
c
h
c
a
n
b
e
d
e
v
e
lo
p
e
d
in
to
b
o
th
c
o
m
p
u
ter
-
b
a
se
d
a
n
d
q
u
a
n
ti
tativ
e
a
n
a
ly
sis
to
o
ls.
T
h
is
re
se
a
rc
h
u
se
s
a
m
o
d
e
l
tes
t
with
a
c
o
n
firma
to
r
y
fa
c
to
r
a
n
a
ly
sis
(CF
A)
tec
h
n
iq
u
e
o
n
m
a
tri
x
c
o
v
a
rian
c
e
a
g
a
in
st
str
u
c
tu
ra
l
e
q
u
a
ti
o
n
m
o
d
e
ll
i
n
g
(
S
EM
)
m
e
th
o
d
s
to
m
e
a
su
re
fin
a
n
c
ial
ra
ti
o
s
.
De
c
isio
n
s
u
p
p
o
rt
sy
ste
m
(
DSS
)
a
n
a
l
y
sis
u
se
s
n
u
m
e
rica
l
c
a
lcu
latio
n
s a
id
e
d
b
y
m
a
th
e
m
a
ti
c
a
l
m
o
d
e
ls t
h
r
o
u
g
h
si
x
p
h
a
se
s
.
Th
e
first
th
re
e
p
h
a
se
s
o
f
a
str
u
c
tu
re
d
a
p
p
r
o
a
c
h
t
o
b
u
i
ld
i
n
g
m
u
lt
iv
a
riate
m
o
d
e
ls
a
n
d
th
e
n
e
x
t
th
re
e
p
h
a
se
s,
n
a
m
e
ly
e
stim
a
ti
o
n
,
i
n
terp
re
tati
o
n
,
a
n
d
v
a
li
d
a
ti
o
n
,
a
re
d
e
v
e
lo
p
in
g
fro
m
d
a
ta
in
p
u
t
th
a
t
h
a
s
b
e
e
n
se
lec
ted
u
sin
g
LI
S
R
EL
v
e
rsio
n
8
.
7
2
.
T
h
e
fin
a
n
c
ial
ra
ti
o
’
s
tes
ti
n
g
m
o
d
e
l
wit
h
a
CF
A
a
p
p
ro
a
c
h
d
e
ri
v
e
d
i
n
to
a
m
a
th
e
m
a
ti
c
a
l
(q
u
a
n
ti
tati
v
e
)
m
o
d
e
l
c
a
n
e
x
p
la
in
t
h
e
c
o
m
p
lex
it
y
o
f
t
h
e
re
latio
n
sh
i
p
b
e
twe
e
n
t
h
e
g
o
o
d
n
e
ss
-
of
-
fit
m
o
d
e
ls
(G
OF)
with
a
d
iffere
n
t
a
p
p
ro
a
c
h
fro
m
p
ri
o
r
re
se
a
rc
h
.
T
h
e
g
o
o
d
n
e
ss
-
of
-
fi
t
tes
t
re
su
lt
s
i
n
th
is
st
u
d
y
p
ro
d
u
c
e
d
sc
o
re
s
o
n
e
a
c
h
o
f
t
h
e
fin
a
n
c
ial
ra
ti
o
m
e
a
su
re
m
e
n
t
m
o
d
e
ls
a
t
a
n
a
c
c
u
ra
c
y
le
v
e
l
o
f
CR
o
f
7
8
.
4
9
,
T
ATO
o
f
1
.
2
6
,
DER
o
f
4
1
.
4
1
,
RO
A
o
f
m
in
u
s
0
.
0
3
3
,
a
n
d
P
BV o
f
5
4
0
.
9
2
.
T
h
is me
a
n
s
th
a
t
P
BV h
a
s
th
e
h
i
g
h
e
st
s
tan
d
a
rd
ize
d
lo
a
d
i
n
g
fa
c
to
rs
t
o
d
e
term
in
e
th
e
m
e
a
su
re
m
e
n
t
o
f
fin
a
n
c
ial
ra
ti
o
s
.
Th
e
CF
A
m
e
a
su
re
m
e
n
t
b
a
se
d
o
n
S
E
M
c
a
n
b
e
u
se
d
t
o
m
a
k
e
a
p
p
r
o
p
riate
d
e
c
isio
n
s
a
n
d
c
o
m
b
in
e
a
m
o
d
e
l
c
o
m
p
a
riso
n
a
n
d
re
d
e
v
e
lo
p
m
e
n
t
o
f
th
e
CF
A
tec
h
n
i
q
u
e
a
n
d
m
o
d
e
l
tes
ti
n
g
wit
h
o
th
e
r
so
f
twa
re
su
c
h
a
s S
P
S
S
,
P
LS
,
AMOS
,
a
n
d
o
th
e
rs.
K
ey
w
o
r
d
s
:
C
o
n
f
ir
m
ato
r
y
f
ac
to
r
a
n
aly
s
is
DSS ap
p
r
o
ac
h
Go
o
d
n
ess
-
of
-
f
it
Ma
th
em
atica
l m
o
d
els
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
T
.
Hu
s
ain
Dep
ar
tem
en
t o
f
I
n
f
o
r
m
atio
n
Sy
s
tem
s
STM
I
K
W
id
u
r
i
Palm
er
ah
B
ar
at
Stre
et
No
.
3
5
3
,
So
u
th
J
ak
ar
ta
-
1
2
2
1
0
,
I
n
d
o
n
e
s
ia
E
m
ail: th
u
s
ain
0
5
0
6
8
6
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Dec
is
io
n
s
u
p
p
o
r
t
s
y
s
tem
s
(
D
SS
)
ap
p
r
o
ac
h
ca
n
b
e
d
ev
elo
p
ed
in
to
ap
p
r
o
ac
h
es
o
r
m
et
h
o
d
s
,
b
o
t
h
co
m
p
u
ter
-
b
ased
s
y
s
tem
s
o
r
b
y
d
ev
elo
p
i
n
g
m
et
h
o
d
s
o
r
s
tan
d
ar
d
s
f
o
r
q
u
a
n
titativ
e
an
aly
s
is
to
o
ls
.
T
h
is
f
u
n
ctio
n
ca
n
b
e
u
s
ed
to
s
o
lv
e
p
r
o
b
lem
s
in
m
ak
in
g
s
em
i
an
d
u
n
s
tr
u
ct
u
r
ed
d
ec
is
io
n
s
.
Acc
o
r
d
in
g
t
o
Sh
ar
d
a,
Dele
n
,
an
d
T
u
r
b
an
[
1
]
,
t
h
at
th
ese
k
ey
D
SS
ab
ilit
ies
an
d
ch
ar
ac
ter
is
tics
p
er
m
it
d
ec
is
io
n
-
m
ak
er
s
t
o
m
ak
e
b
etter
,
f
u
r
th
e
r
o
r
d
er
ly
d
ec
is
io
n
s
p
r
o
m
p
tly
.
Mo
d
elin
g
im
p
lies
tr
an
s
f
ig
u
r
in
g
th
e
r
eal
-
wo
r
ld
h
ass
le
in
to
a
r
elev
an
t
p
r
o
to
ty
p
e
s
tr
u
ctu
r
e
(
m
o
d
el)
;
T
u
r
b
an
et
a
l
.
ar
g
u
e
th
at
m
ath
em
atical
m
o
d
el
is
o
n
e
o
f
th
e
ap
p
r
o
ac
h
es
d
er
iv
ed
f
r
o
m
s
cien
tific
m
an
ag
em
en
t
p
r
o
cess
es
to
d
escrib
e
a
r
eal
-
wo
r
ld
p
r
o
b
lem
w
ith
p
r
o
to
ty
p
es
an
d
alg
e
b
r
aic
ex
p
r
ess
io
n
s
s
o
th
at
m
o
d
elin
g
s
o
lu
ti
o
n
s
can
b
e
s
o
lv
ed
u
s
i
n
g
f
ast
an
d
ef
f
icien
t
ap
p
r
o
ach
es
[
2
]
.
T
h
e
class
ical
s
tati
s
tical
ap
p
r
o
ac
h
h
as
f
o
cu
s
ed
o
n
p
r
ed
ictin
g
o
b
s
er
v
a
tio
n
s
th
r
o
u
g
h
q
u
an
titativ
e
a
n
a
ly
s
is
,
in
p
ar
ticu
lar
,
m
ath
em
ati
ca
l
m
o
d
elin
g
b
ased
o
n
th
e
r
elatio
n
s
h
ip
o
f
f
ac
to
r
s
.
[
3
]
.
Facto
r
an
aly
s
is
is
a
s
ta
t
is
tical
ap
p
r
o
ac
h
with
a
d
u
al
v
ar
iab
le
in
s
p
ec
tio
n
tech
n
iq
u
e
t
h
at
d
eter
m
in
es
th
e
m
ain
co
m
p
o
n
e
n
ts
an
d
m
an
if
e
s
ts
th
e
in
ter
r
elatio
n
s
am
o
n
g
v
ar
iab
les.
Acc
o
r
d
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
: 2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
10
,
No
.
2
,
J
u
n
e
2
0
2
1
:
1
1
5
–
1
2
1
116
to
Hair
et
a
l
.
,
f
ac
to
r
an
aly
s
is
h
as
th
e
m
ain
o
b
jectiv
e
t
o
d
is
co
v
er
a
s
ch
em
e
d
esig
n
ate
th
e
o
u
tp
u
t
ca
r
r
ied
in
th
e
q
u
an
tity
o
f
th
e
n
ativ
e
v
ar
iab
le
s
in
s
id
e
a
r
ec
en
t in
f
o
r
m
atio
n
a
s
s
em
b
lag
e
o
f
r
ef
in
e
[
4
]
.
Fu
r
th
er
m
o
r
e,
to
ca
r
r
y
o
u
t
a
co
n
f
ir
m
ato
r
y
f
ac
to
r
an
aly
s
is
,
it
ca
n
u
s
e
r
aw
d
ata
as
i
n
p
u
t
d
ata
in
th
e
f
o
r
m
o
f
co
v
ar
ian
t
m
atr
ices
o
r
tem
p
o
r
ar
y
co
r
r
elatio
n
m
atr
ice
s
to
co
n
f
ir
m
th
e
f
ac
to
r
m
u
s
t f
ir
s
t
d
ef
in
e
laten
t
co
n
s
titu
en
ts
b
ec
au
s
e
th
ese
f
ac
to
r
s
ca
n
n
o
t b
e
m
ea
s
u
r
ed
d
ir
ec
tly
b
u
t th
r
o
u
g
h
in
d
icato
r
s
o
r
m
ea
s
u
r
em
en
ts
th
at
r
ep
r
esen
t th
e
co
n
s
tr
u
ct
[
5
]
.
Sev
er
al
r
ec
en
t
s
tu
d
ies
[6
]
-
[
9
]
h
av
e
s
u
g
g
ested
th
at
th
is
r
esear
ch
is
a
m
u
ltiv
ar
iate
m
o
d
el
u
s
in
g
th
e
Pair
-
C
o
p
u
la
ap
p
r
o
ac
h
th
at
f
u
n
ctio
n
s
o
f
two
v
ar
iab
les
s
im
u
ltan
eo
u
s
ly
u
s
in
g
a
h
ier
ar
c
h
ical
m
o
d
el
co
n
s
tr
u
ct
,
b
iv
ar
iate
co
p
u
lae
,
an
d
co
p
u
la
m
o
d
els
(
R
-
v
in
e)
.
C
o
n
d
itio
n
i
n
g
u
s
in
g
s
im
p
le
b
u
ild
in
g
b
lo
ck
s
,
th
en
ca
n
o
n
ical
v
in
e
co
p
u
las
in
v
o
lv
in
g
b
o
t
h
o
b
s
er
v
ed
an
d
laten
t
v
a
r
i
ab
les
allo
ws
tail,
asy
m
m
etr
ic,
an
d
n
o
n
-
lin
ea
r
d
ep
en
d
e
n
ce
.
Usi
n
g
a
g
o
o
d
n
es
s
-
of
-
f
it
in
d
e
x
f
o
r
th
e
lea
st
-
s
q
u
ar
es
m
o
d
elin
g
to
s
im
u
late
an
d
co
m
p
ar
e
th
e
in
d
ex
with
th
e
m
o
d
el
f
it
in
th
e
s
tr
u
c
tu
r
al
eq
u
atio
n
m
o
d
el
an
d
also
a
n
ew
g
o
o
d
n
ess
-
of
-
f
it
ap
p
r
o
ac
h
o
f
s
im
u
latio
n
R
-
v
in
e
s
p
ec
if
icatio
n
s
.
Acc
o
r
d
in
g
to
Hen
s
eler
an
d
Sar
s
ted
t,
th
e
r
esu
lts
ca
n
v
alid
ate
h
o
w
we
ll
a
m
o
d
el
ex
p
lain
s
d
ata
d
if
f
er
en
ce
s
[
10
]
.
T
h
e
m
o
d
el
,
s
tr
u
ctu
r
al
eq
u
atio
n
m
o
d
ellin
g
(
SEM
),
with
m
ax
im
u
m
lik
elih
o
o
d
esti
m
atio
n
(
ML
E
)
ap
p
r
o
ac
h
ac
co
r
d
in
g
to
with
s
tan
d
ar
d
er
r
o
r
(
SE)
o
p
e
r
ates
a
m
o
d
el
s
p
ec
if
icatio
n
test
an
d
in
f
o
r
m
atio
n
m
atr
ix
with
th
e
lik
elih
o
o
d
r
atio
(
L
R
)
s
tati
s
tic
f
r
o
m
Alb
er
to
Ma
y
d
eu
-
Oliv
ar
es
r
esear
ch
,
th
ese
f
in
d
in
g
th
at
is
o
p
tim
izin
g
th
e
SE'
s
ca
lcu
lated
in
co
n
ce
r
n
a
m
ea
n
-
an
d
v
ar
ia
n
ce
alter
L
R
s
cr
ip
t
s
tatis
tic
f
o
r
th
e
lo
o
k
ah
ea
d
to
in
f
o
r
m
atio
n
m
atr
ix
[
11
]
.
T
h
e
cu
s
to
m
er
s
atis
f
ac
tio
n
m
o
d
el
o
f
leasin
g
en
ter
p
r
is
e
u
s
er
s
to
e
n
tail
5
0
r
esp
o
n
d
e
n
ts
o
f
th
e
tem
p
t
a
s
am
p
le
in
c
o
n
j
u
n
ctio
n
with
th
e
p
u
r
p
o
s
e
o
f
Pil
ai,
L
am
b
d
a,
F,
a
n
d
W
ilk
’
s
test
with
th
e
ass
is
t
o
f
SP
SS
f
r
o
m
R
izk
ian
a
a
n
d
Hen
d
ik
awa
ti
r
esear
ch
,
th
ese
f
in
d
i
n
g
s
th
at
th
r
ee
-
f
ac
t
o
r
o
f
d
is
cr
i
m
in
an
t
a
n
aly
s
is
f
ar
s
id
e
o
f
th
e
z
-
s
co
r
e
p
r
o
ce
ed
s
o
f
th
e
attestatio
n
wh
ich
ap
p
ea
r
ed
th
e
p
r
ec
is
io
n
s
co
r
e
o
f
th
e
m
o
d
el
wh
ich
s
o
m
ewh
at
u
p
p
er
at
5
4
p
er
ce
n
t
[
12
]
.
T
h
e
u
s
e
o
f
co
v
ar
ian
ce
-
b
ased
s
im
u
latio
n
m
o
d
els
in
v
o
lv
es
9
5
p
er
ce
n
t
c
o
n
f
i
d
en
ce
in
te
r
v
als
with
s
am
p
le
n
=1
0
0
u
s
e
d
ep
e
n
d
en
t
v
ar
iab
les
in
p
air
s
in
d
eter
m
in
in
g
c
o
v
ar
ian
ce
s
,
s
u
ch
as
th
e
Vale
–
Ma
u
r
elli
ap
p
r
o
ac
h
th
at
f
o
cu
s
es
o
n
id
en
tify
in
g
an
d
im
p
r
o
v
in
g
s
k
ewn
ess
s
co
r
es
an
d
u
n
iv
ar
iate
k
u
r
to
s
is
w
ith
co
v
ar
ian
ce
s
tr
u
ctu
r
es
f
r
o
m
Gr
ø
n
n
eb
er
g
a
n
d
Fo
ld
n
es
r
esear
ch
,
th
ese
f
i
n
d
in
g
s
th
at
wh
en
co
v
a
r
ian
ce
is
wea
k
ly
co
r
r
elate
d
,
r
esu
lts
b
ased
o
n
th
e
m
eth
o
d
o
th
er
s
im
u
latio
n
s
will
p
o
te
n
tially
g
iv
e
s
im
ilar
r
esu
lts
[
13
]
.
C
o
m
p
u
tatio
n
al
co
g
n
itiv
e
e
n
g
in
ee
r
in
g
m
o
d
e
l
co
m
p
a
r
es
d
if
f
e
r
en
ce
s
in
m
o
d
els
th
r
o
u
g
h
cr
iter
ia
b
a
s
ed
o
n
p
r
e
d
ictiv
e
p
er
f
o
r
m
an
ce
an
d
g
en
er
ativ
e
m
o
d
els
to
s
ee
f
ea
s
ib
ilit
y
an
d
s
im
u
latio
n
s
with
a
co
g
n
itiv
e
s
cien
tific
ap
p
r
o
a
ch
f
r
o
m
Palm
in
ter
i
et
a
l
.
,
r
esear
c
h
.
T
h
e
r
esu
lts
o
f
co
m
p
u
tatio
n
al
en
g
in
ee
r
in
g
m
o
d
els
ca
n
ass
is
t
in
r
ea
lizin
g
th
e
m
ec
h
an
is
m
s
th
at
m
an
ag
e
th
o
u
g
h
ts
an
d
b
eh
a
v
io
r
to
th
e
o
t
h
er
s
id
e
o
f
th
e
g
en
er
atio
n
o
f
alg
o
r
ith
m
s
in
th
e
r
ep
r
o
d
u
ctio
n
o
f
t
h
e
im
p
ac
t
o
f
co
g
n
itiv
e
a
s
p
ec
ts
v
iz.
o
n
e'
s
b
eh
av
io
r
[
14
]
.
B
o
tes
et
a
l
.
ar
g
u
e
th
at
ar
r
an
g
ed
d
ec
is
io
n
s
u
p
p
o
r
t sy
s
tem
s
to
g
et
a
m
eter
o
f
b
ac
k
d
ated
e
n
er
g
y
ef
f
icien
cy
m
o
d
elin
g
o
p
tio
n
s
o
b
jectiv
ely
o
p
er
ate
d
to
ass
is
t
in
th
e
p
r
o
ce
s
s
o
f
c
o
n
s
id
er
atio
n
in
th
e
d
ec
is
io
n
-
m
ak
in
g
u
s
in
g
th
e
weig
h
ted
-
s
u
m
m
eth
o
d
.
T
h
ese
f
in
d
in
g
s
o
f
th
e
f
i
n
an
cial
co
m
p
ar
is
o
n
ap
p
ea
r
e
d
th
at
s
ec
tio
n
1
2
L
tax
in
ce
n
tiv
e
o
f
t
h
e
m
o
n
etar
y
wo
r
th
o
f
th
e
ascen
d
an
cy
am
o
u
n
t
o
f
1
0
p
er
ce
n
t
also
3
3
p
er
ce
n
t
if
n
o
m
e
d
iu
m
wer
e
o
n
h
an
d
t
o
o
b
tain
th
e
last
m
o
d
el
[
15
]
.
Sh
k
ee
r
an
d
Awa
n
g
ar
g
u
e
th
at
th
e
Ma
r
k
etin
g
I
n
f
o
r
m
atio
n
Sy
s
tem
s
et
u
p
with
a
f
ac
to
r
an
aly
s
is
s
tu
d
y
in
v
o
l
v
in
g
1
0
0
r
esp
o
n
d
e
n
ts
th
r
o
u
g
h
KM
O
an
d
B
ar
tlett'
s
te
s
t
an
d
c
o
m
p
o
n
en
t
m
atr
ices
f
r
o
m
ea
c
h
item
an
d
in
ter
n
al
r
eliab
ilit
y
to
m
ea
s
u
r
e
in
s
tr
u
m
en
ts
in
th
e
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
r
esu
ltin
g
in
ef
f
ec
tiv
en
ess
in
m
ea
s
u
r
in
g
m
ar
k
etin
g
d
ec
is
io
n
s
u
p
p
o
r
t
s
y
s
tem
s
[
16
]
.
T
.
Hu
s
ain
a
n
d
Ma
u
lan
a
Ar
d
h
ian
s
y
ah
a
r
g
u
e
th
at
th
e
s
im
u
latio
n
m
o
d
el
o
f
Fin
an
cial
R
atio
ca
n
ex
p
lain
th
e
co
m
p
a
r
is
o
n
o
f
th
e
in
teg
r
ated
m
o
d
el
test
in
g
with
DSS
a
p
ar
ticu
lar
s
tatis
t
ical
ap
p
r
o
ac
h
,
i.e
.
,
Pair
-
Sam
p
le
T
-
T
est
[
17
]
.
I
n
th
e
p
r
esen
t
s
tu
d
y
,
th
e
m
at
h
em
atica
l
m
o
d
elin
g
b
ased
o
n
th
e
r
elatio
n
s
h
ip
o
f
f
ac
to
r
s
th
r
o
u
g
h
C
FA
tech
n
iq
u
e
an
d
SEM
m
eth
o
d
s
u
s
es
to
co
n
f
ir
m
wh
eth
er
th
e
c
o
n
s
tr
u
ct
test
ed
h
as
a
s
tan
d
ar
d
ized
lo
ad
in
g
f
ac
to
r
(
SLF)
s
co
r
e
th
at
m
ee
ts
th
e
r
eq
u
ir
em
en
ts
f
o
r
d
ec
is
io
n
-
m
ak
in
g
.
T
h
is
s
tu
d
y
u
s
es
a
d
i
f
f
er
en
t a
p
p
r
o
ac
h
f
r
o
m
p
r
io
r
s
tu
d
ies,
wh
er
e
f
ac
to
r
an
aly
s
is
b
ased
o
n
SEM
h
as
n
o
t
b
ee
n
u
s
ed
in
p
r
ev
io
u
s
s
tu
d
ies.
T
h
is
m
o
d
el
is
co
n
s
id
er
ed
p
o
wer
f
u
l,
wh
ich
ca
n
ex
p
lain
th
e
m
o
d
el'
s
as
s
es
s
m
en
t
th
r
o
u
g
h
th
e
s
tag
es
o
f
th
e
SL
F
an
d
g
o
o
d
n
ess
-
of
-
f
it
(
Go
F)
test
.
T
h
e
o
p
t
io
n
o
f
r
esear
ch
s
u
b
jects
is
d
r
iv
en
b
y
a
f
ew
s
tu
d
ies
o
f
th
e
C
FA
tech
n
iq
u
e
test
b
ased
o
n
th
e
d
ec
is
io
n
s
u
p
p
o
r
t
s
y
s
tem
ap
p
r
o
ac
h
in
th
e
r
esear
ch
o
f
s
o
cial
s
cien
ce
ca
teg
o
r
ies
in
I
n
d
o
n
esia.
T
h
e
p
r
ev
io
u
s
r
esear
ch
is
s
till
lim
ited
an
d
d
o
m
in
ated
b
y
r
esear
ch
o
n
th
e
e
x
ac
t
o
r
m
ath
em
atica
l
s
cien
ce
s
tu
d
ies
r
elate
d
t
o
DSS.
T
h
er
ef
o
r
e,
th
e
im
p
o
r
tan
ce
o
f
t
h
is
r
esear
ch
is
to
p
r
o
v
i
d
e
id
ea
s
to
s
p
ec
if
y
an
d
test
th
e
m
o
d
e
l
in
a
n
ew
f
r
am
ewo
r
k
f
o
r
f
u
tu
r
e
r
esear
c
h
f
o
r
a
r
esear
ch
er
.
Ho
wev
e
r
,
th
e
c
u
r
r
en
t
s
tu
d
y
tr
ies
to
a
n
o
th
er
f
o
cu
s
,
w
h
er
e
co
v
ar
ian
ce
v
alu
es th
r
o
u
g
h
t
h
e
C
FA te
ch
n
iq
u
e
s
er
v
e
as a
g
u
id
e
in
d
ev
elo
p
in
g
a
m
o
d
el
DSS.
T
h
e
r
esear
ch
aim
s
to
ad
ap
t
th
e
f
r
am
ewo
r
k
f
o
r
f
o
cu
s
in
g
o
n
s
ec
o
n
d
a
r
y
d
ata,
i.
e.
,
th
e
r
elea
s
e
o
f
th
e
I
n
d
o
n
es
ian
s
to
ck
ex
ch
an
g
e
(
I
DX)
wh
ich
c
o
m
p
a
n
ies
th
at
co
n
d
u
ct
in
itial
p
u
b
lic
o
f
f
er
i
n
g
s
(
I
PO)
as
f
if
ty
-
f
iv
e
n
ew
i
s
s
u
er
's
in
2
0
1
9
b
y
ad
d
in
g
d
ata
f
r
o
m
th
e
p
r
e
v
io
u
s
y
ea
r
'
s
,
in
2
0
1
8
[
18
]
,
wh
o
h
a
v
e
m
et
th
e
r
eq
u
ir
em
en
ts
f
o
r
u
s
in
g
th
e
m
ax
im
u
m
lik
elih
o
o
d
esti
m
atio
n
(
ML
E
)
t
ec
h
n
iq
u
e
i
n
SEM
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2
2
5
2
-
8
8
1
4
C
o
n
fir
ma
to
r
y
fa
cto
r
a
n
a
lysi
s
:
mo
d
el
test
in
g
o
f fin
a
n
ci
a
l
r
a
tio
s
w
ith
d
ec
is
io
n
s
u
p
p
o
r
t …
(
T.
Hu
s
a
in
)
117
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
is
s
tu
d
y
u
s
es
an
in
ter
d
ep
e
n
d
en
t
m
eth
o
d
th
at
aim
s
to
r
ed
u
ce
th
e
o
r
ig
in
al
v
a
r
iab
les
to
b
e
an
aly
ze
d
.
T
h
e
in
f
o
r
m
atio
n
u
s
ed
is
s
till
o
wn
ed
an
d
d
ev
elo
p
ed
,
an
d
it
is
k
n
o
wn
as
an
ab
s
tr
ac
t
c
o
n
ce
p
t
[
19
]
.
DSS
an
aly
s
is
u
tili
zin
g
n
u
m
er
al
ca
lc
u
latio
n
s
ass
is
ted
with
ar
ith
m
etic
ca
lc
u
latio
n
o
r
o
th
er
q
u
a
n
titativ
e
m
o
d
els
th
at
ca
n
b
e
ex
p
an
d
e
d
with
a
c
o
v
ar
ian
ce
m
atr
ix
an
aly
s
is
ap
p
r
o
ac
h
with
m
o
d
elin
g
.
T
h
e
d
ev
elo
p
ed
p
ar
a
d
ig
m
co
n
s
is
ts
o
f
s
ix
s
tag
es.
T
h
e
f
ir
s
t
th
r
ee
s
t
ag
es
o
f
th
e
s
tr
u
ctu
r
ed
ap
p
r
o
ac
h
ar
e
to
co
n
s
tr
u
ct
a
m
u
ltiv
ar
iate
m
o
d
el.
T
h
e
n
ex
t
th
r
ee
s
tag
es
ar
e
to
esti
m
ate,
in
ter
p
r
et,
an
d
v
alid
ate
th
e
f
ac
t
o
r
m
o
d
e
l.
T
h
ese
ar
e
ad
d
itio
n
al
s
tep
s
to
ass
is
t
in
s
elec
tin
g
s
u
b
s
titu
te
v
ar
iab
les,
co
m
p
u
ta
tio
n
al
f
ac
to
r
s
co
r
es,
o
r
c
r
ea
tin
g
s
u
m
m
ar
y
s
ca
les,
f
o
r
ap
p
licatio
n
to
o
t
h
er
m
u
ltiv
ar
iate
tech
n
iq
u
es
[
4
]
.
T
ab
le
1
is
s
h
o
win
g
t
h
e
d
ef
i
n
itio
n
an
d
m
ea
s
u
r
em
en
t
m
o
d
el
,
Fig
u
r
e
1
is
s
h
o
win
g
th
e
f
r
am
ewo
r
k
o
f
C
FA
u
s
in
g
q
u
an
titativ
e
m
o
d
el
an
d
DSS
ap
p
r
o
ac
h
an
d
T
ab
le
2
is
s
h
o
wi
n
g
c
h
ar
ac
ter
is
tic
o
f
f
it in
d
ices
.
T
ab
le
1
.
T
h
e
d
ef
in
itio
n
an
d
m
ea
s
u
r
em
en
t m
o
d
el
[
2
0
]
D
e
f
i
n
i
t
i
o
n
M
e
a
su
r
e
me
n
t
Li
q
u
i
d
i
t
y
R
a
t
i
o
s
i
s
a
p
p
e
a
r
e
d
a
f
i
r
m's
l
i
q
u
i
d
i
t
y
i
n
g
i
v
i
n
g
s
h
o
r
t
-
r
a
n
g
e
o
b
l
i
g
a
t
i
o
n
s
o
r
i
n
d
e
b
t
e
d
n
e
ss
t
h
a
t
i
s
sch
e
d
u
l
e
d
.
CR
=
A
c
t
i
v
i
t
y
R
a
t
i
o
's
a
r
e
u
s
e
d
t
o
m
e
a
s
u
r
e
o
n
e
o
f
t
h
e
e
f
f
i
c
i
e
n
c
i
e
s
w
h
i
c
h
t
h
e
f
i
r
m
u
s
i
n
g
a
n
a
sse
t
t
o
g
e
n
e
r
a
t
e
s
a
l
e
s
TATO
=
D
e
b
t
r
a
t
i
o
s
a
r
e
u
s
e
d
t
o
m
e
a
s
u
r
e
o
n
e
o
f
t
h
e
e
n
l
a
r
g
e
m
e
n
t
s
o
f
r
i
sk
a
n
d
r
e
t
u
r
n
t
h
r
o
u
g
h
t
h
e
u
se
o
f
f
i
x
e
d
c
o
st
f
i
n
a
n
c
i
n
g
D
ER
=
ℎ
ℎ
′
P
r
o
f
i
t
a
b
i
l
i
t
y
R
a
t
i
o
's
a
r
e
u
se
d
t
o
me
a
su
r
e
o
n
e
o
f
t
h
e
e
f
f
e
c
t
i
v
e
n
e
ss
l
e
v
e
l
s
o
f
man
a
g
e
me
n
t
i
n
y
i
e
l
d
i
n
g
p
r
o
f
i
t
s
R
O
A
=
M
a
r
k
e
t
s
h
a
r
e
r
a
t
i
o
s
w
h
i
c
h
a
r
e
u
se
d
t
o
e
n
u
mera
t
e
t
h
e
c
o
n
t
e
m
p
o
r
a
r
y
sh
a
r
e
p
r
i
c
e
,
t
o
sp
e
c
i
a
l
a
c
c
o
u
n
t
i
n
g
v
a
l
u
e
s
P
ER
=
ℎ
/
ℎ
Fin
an
cial
r
atio
s
m
o
d
elin
g
with
m
atr
ix
co
v
a
r
ian
ce
ap
p
r
o
ac
h
is
co
m
p
u
te
as:
R
=
+
1
(
1
)
TATO
=
+
2
(
2
)
DE
R
=
+
3
(
3
)
R
OA
=
+
4
(
4
)
PER
=
+
5
(
5
)
Mo
d
el
esti
m
atio
n
,
in
ter
p
r
etatio
n
,
an
d
v
alid
atio
n
ar
e
d
e
v
e
lo
p
in
g
f
r
o
m
d
ata
in
p
u
t
th
at
h
as
b
ee
n
s
elec
ted
u
s
in
g
L
I
SR
E
L
v
er
s
io
n
8
.
7
2
.
T
h
is
r
esear
ch
u
s
es
a
m
ax
im
u
m
lik
elih
o
o
d
esti
m
atio
n
(
ML
E
)
tech
n
iq
u
e,
wh
ich
r
eq
u
i
r
es
r
an
g
es
f
r
o
m
5
0
-
2
0
0
d
ata
o
b
s
er
v
atio
n
s
.
T
h
is
r
esear
ch
'
s
o
b
jectiv
e
in
v
ite
in
v
o
l
v
es
a
m
ath
em
atica
l simu
latio
n
m
o
d
el
u
s
in
g
d
ata
m
in
in
g
an
d
s
tr
u
c
tu
r
al
eq
u
atio
n
m
o
d
eli
n
g
(
SEM
)
.
Sev
er
al
g
u
id
elin
es
wer
e
u
s
ed
to
ass
ess
th
e
s
u
itab
ilit
y
in
d
ex
b
ased
o
n
th
e
r
esear
ch
m
o
d
el
with
s
ep
ar
ate
s
am
p
le
s
izes,
m
o
d
el
ch
an
g
e
s
,
an
d
er
r
o
r
r
ates
i
n
m
o
d
el
s
p
ec
if
icatio
n
s
to
id
en
tify
th
e
v
ar
io
u
s
s
u
itab
ilit
y
in
d
ices
[
4
]
.
I
f
th
e
d
ev
elo
p
e
d
m
o
d
el
h
as
a
r
ea
s
o
n
ab
le
er
r
o
r
ap
p
r
o
x
im
ate
to
r
eso
lv
e
wh
eth
er
th
e
m
o
d
el
ca
n
p
r
o
d
u
ce
th
e
m
ea
s
u
r
em
en
t o
u
tp
u
t f
u
r
th
er
test
ed
o
r
r
etu
r
n
to
th
e
p
r
e
v
io
u
s
p
h
ase
[
21
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
: 2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
10
,
No
.
2
,
J
u
n
e
2
0
2
1
:
1
1
5
–
1
2
1
118
I
n
d
e
x
C
a
p
i
t
a
l
M
a
r
k
e
t
D
i
r
e
c
t
o
r
y
(
I
C
M
D
,
I
D
X
–
2
0
1
8
-
2
0
1
9
)
D
a
t
a
S
u
m
m
a
r
i
z
a
t
i
o
n
a
n
d
I
d
e
n
t
i
f
y
i
n
g
S
t
r
u
c
t
u
r
e
s
,
D
a
t
a
R
e
d
u
c
t
i
o
n
S
t
r
u
c
t
u
r
a
l
E
q
u
a
t
i
o
n
M
o
d
e
l
i
n
g
(
S
E
M
)
C
o
n
f
i
r
m
a
t
o
r
y
T
y
p
e
o
f
F
a
c
t
o
r
A
n
a
l
y
s
i
s
(
w
h
a
t
i
s
b
e
i
n
g
g
r
o
u
p
e
d
o
r
–
v
a
r
i
a
b
l
e
s
o
r
c
a
s
e
s
?
)
E
x
p
l
o
r
a
t
o
r
y
w
h
a
t
,
h
o
w
,
a
n
d
a
m
o
u
n
t
o
f
s
a
m
p
l
e
s
i
z
e
s
R
e
s
e
a
r
c
h
D
e
s
i
g
n
1
.
S
t
a
n
d
a
r
d
i
z
e
d
L
o
a
d
i
n
g
s
F
a
c
t
o
r
s
(
S
c
o
r
e
)
2
.
G
o
o
d
n
e
s
s
-
o
f
F
i
t
(
S
t
a
t
i
s
t
i
c
s
)
M
o
d
e
l
S
p
e
c
i
f
i
c
a
t
i
o
n
a
n
d
I
n
t
e
r
p
r
e
t
i
n
g
S
e
l
e
c
t
i
o
n
,
C
o
m
p
u
t
a
t
i
o
n
a
n
d
C
r
e
a
t
i
n
g
o
f
F
i
n
a
n
c
i
a
l
R
a
t
i
o
’
s
s
c
o
r
e
a
n
d
s
c
a
l
e
s
V
a
l
i
d
a
t
i
o
n
o
f
t
h
e
F
a
c
t
o
r
M
o
d
e
l
A
n
a
l
y
s
i
s
R
e
s
p
e
s
i
f
i
c
a
t
i
o
n
c
o
m
p
o
n
e
n
t
&
c
o
m
m
o
n
f
a
c
t
o
r
s
a
n
a
l
y
s
i
s
S
e
l
e
c
t
i
n
g
a
F
a
c
t
o
r
M
o
d
e
l
Fig
u
r
e
1
.
T
h
e
f
r
a
m
ewo
r
k
o
f
C
FA u
s
in
g
q
u
an
titativ
e
m
o
d
el
a
n
d
DSS ap
p
r
o
ac
h
[
3
]
,
[
4
]
,
[
20
]
T
ab
le
2
.
C
h
ar
ac
ter
is
tic
o
f
f
it in
d
ices
N
u
mb
e
r
o
f
S
t
a
t
.
(
O
b
ser
v
e
va
r
i
a
b
l
e
s
-
m
)
=
1
2
I
n
d
e
x
C
u
t
o
f
f
v
a
l
u
e
s
b
a
s
e
d
o
n
m
o
d
e
l
c
h
a
r
a
c
t
e
r
i
s
t
i
c
s
2
I
n
si
g
n
i
f
i
c
a
n
t
p
-
v
a
l
u
e
s
p
r
e
d
i
c
t
e
d
C
F
I
/
TLI
0
.
9
7
o
r
p
r
e
f
e
r
a
b
l
e
R
N
I
M
a
y
n
o
t
d
i
a
g
n
o
se
mi
ss
p
e
c
i
f
i
c
a
t
i
o
n
w
e
l
l
S
R
M
R
B
i
a
s
e
d
u
p
w
a
r
d
,
u
s
e
m
o
r
e
i
n
d
i
c
e
s
Th
e
R
M
S
EA
W
o
r
t
h
<
0
.
0
8
by
C
F
I
=
0
.
9
7
o
r
h
i
g
h
e
r
3.
RE
SU
L
T
S AN
D
AN
AL
Y
SI
S
3
.
1
.
Da
t
a
s
um
ma
riza
t
io
n,
identif
y
ing
s
t
ruct
ures a
nd
da
t
a
re
du
ct
io
ns
T
h
e
p
u
r
p
o
s
e
o
f
s
u
m
m
ar
izin
g
d
ata
in
d
ef
in
in
g
s
ev
er
al
s
p
ec
if
ic
f
ac
to
r
s
is
to
ac
h
iev
e
th
e
r
ep
r
esen
tatio
n
o
f
m
an
y
c
o
n
s
tr
u
cts.
T
h
is
s
u
m
m
ar
izatio
n
p
r
o
ce
s
s
ex
p
lo
r
e
s
th
e
co
m
b
in
atio
n
o
f
s
tr
u
ctu
r
es
th
at
h
av
e
b
ee
n
d
ef
in
ed
i
n
th
e
m
ea
s
u
r
em
en
t
o
f
th
e
i
n
ter
r
elatio
n
s
h
ip
s
b
etw
ee
n
f
ac
to
r
s
th
at
allo
w
f
o
r
th
e
s
p
ec
if
icatio
n
o
f
a
s
m
all
n
u
m
b
er
o
f
d
im
en
s
io
n
s
(
f
ac
to
r
s
)
th
at
illu
s
tr
ate
p
ar
t
o
f
t
h
e
g
en
u
in
e
v
ar
iab
le.
Data
r
ed
u
ctio
n
also
d
ep
en
d
s
o
n
f
ac
t
o
r
l
o
ad
in
g
b
u
t
f
o
r
id
e
n
t
if
y
in
g
f
ac
to
r
s
f
o
r
f
u
r
t
h
er
a
n
aly
s
is
with
o
th
er
tec
h
n
iq
u
es
o
r
f
o
r
m
in
g
esti
m
atio
n
s
o
f
th
em
s
elv
es
(
f
ac
to
r
s
co
r
es
o
r
ad
d
itio
n
s
ca
les),
wh
ich
th
en
r
esto
r
e
th
e
g
en
u
in
e
v
a
r
iab
le
s
af
ter
th
e
an
aly
s
is
p
h
ase.
T
h
is
s
tu
d
y
u
s
es
f
iv
e
f
in
an
cial
r
atio
m
ea
s
u
r
em
en
t
f
ac
t
o
r
s
co
n
s
is
ts
o
f
C
R
,
T
AT
O,
D
E
R
,
R
OA,
an
d
PER
(
p
r
o
x
y
)
o
b
tain
e
d
f
r
o
m
p
r
o
s
p
ec
tu
s
r
ep
o
r
ts
a
n
d
f
in
an
cial
s
tatem
en
ts
o
f
f
if
ty
-
f
iv
e
I
PO
co
m
p
an
ies
in
2
0
1
9
an
d
r
ed
u
ce
d
b
y
two
co
m
p
an
y
s
o
t
h
at
th
e
o
b
s
er
v
a
tio
n
d
ata
th
at
m
ee
t
th
e
s
u
b
s
et
o
f
r
ep
r
esen
tativ
e
v
ar
iab
les
in
th
is
p
h
ase
is
5
3
x
2
y
ea
r
s
o
f
o
b
s
er
v
atio
n
.
3
.
2
.
Desig
nin
g
a
f
a
ct
o
r
a
na
l
y
s
is
m
o
del
Facto
r
an
aly
s
is
is
d
esig
n
ed
as
a
b
asis
f
o
r
ca
lcu
latin
g
d
ata
i
n
p
u
t
an
d
class
if
icatio
n
,
f
o
r
th
e
g
r
o
u
p
in
g
o
f
o
b
s
er
v
atio
n
al
d
ata,
m
ea
s
u
r
em
en
t
p
r
o
p
er
ties
,
an
d
v
a
r
iab
l
es,
as
well
a
s
u
s
in
g
th
e
s
am
p
le
s
ize
r
eq
u
ir
em
en
ts
n
ee
d
ed
to
a
n
aly
ze
d
ec
is
io
n
-
m
ak
in
g
.
T
h
e
s
am
p
le
ca
lcu
latio
n
in
t
h
e
p
r
ev
io
u
s
p
h
ase
was
1
0
6
d
ata
o
b
s
er
v
atio
n
s
th
at
h
av
e
f
u
lf
illed
th
e
r
e
q
u
ir
em
en
ts
in
th
e
esti
m
atio
n
tech
n
iq
u
e
b
ased
o
n
m
ax
im
u
m
lik
elih
o
o
d
esti
m
atio
n
(
ML
E
)
.
Fu
r
th
er
m
o
r
e,
co
n
s
id
er
atio
n
o
f
th
ese
co
m
p
o
n
en
ts
'
s
elec
tio
n
was
co
n
ce
p
tu
alize
d
in
to
a
m
o
d
el
with
a
co
n
f
ir
m
ato
r
y
f
ac
t
o
r
an
aly
s
is
(
C
FA)
tech
n
iq
u
e.
Fig
u
r
e
2
is
s
h
o
win
g
p
at
h
d
iag
r
am
: in
itial
m
o
d
el
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2
2
5
2
-
8
8
1
4
C
o
n
fir
ma
to
r
y
fa
cto
r
a
n
a
lysi
s
:
mo
d
el
test
in
g
o
f fin
a
n
ci
a
l
r
a
tio
s
w
ith
d
ec
is
io
n
s
u
p
p
o
r
t …
(
T.
Hu
s
a
in
)
119
Fig
u
r
e
2
.
Path
d
iag
r
am
: in
itial
m
o
d
el
3
.
3
.
M
o
del sp
ec
if
ica
t
io
n a
nd
inte
rpre
t
ing
Mo
d
el
s
p
ec
if
icatio
n
s
d
esig
n
e
d
in
th
e
p
ath
d
ia
g
r
am
ar
e
co
n
v
er
ted
in
t
o
co
v
ar
ian
ce
m
at
r
ix
eq
u
atio
n
s
tr
u
ctu
r
es c
o
n
s
is
tin
g
o
f
:
λ
=
co
v
ar
ian
ce
m
atr
i
x
b
etwe
e
n
lo
ad
in
g
in
d
icato
r
s
o
f
a
f
ac
t
o
r
=
th
e
co
n
s
tr
u
ct
o
f
ea
ch
f
ac
to
r
=
m
ea
s
u
r
em
en
t e
r
r
o
r
o
f
ea
ch
f
ac
to
r
T
h
e
esti
m
ated
m
o
d
els
in
t
h
is
s
tu
d
y
wer
e
test
ed
u
s
in
g
t
h
e
L
I
SR
E
L
v
er
s
io
n
8
.
7
2
s
o
f
twar
e.
T
h
e
m
o
d
el
s
p
ec
if
icatio
n
s
tar
ts
with
th
e
it
em
v
alid
ity
test
(
in
d
icato
r
)
to
co
n
f
ir
m
a
f
ac
to
r
lo
ad
s
tan
d
ar
d
with
th
e
p
r
o
v
is
io
n
s
th
at
if
th
e
t
-
v
alu
e>
t
-
c
r
itical
o
r
s
tan
d
ar
d
ized
lo
a
d
in
g
f
ac
t
o
r
s
(
SLF)
v
alu
e
was
m
o
r
e
th
an
0
.
5
,
th
en
th
e
in
d
icato
r
is
d
ec
lar
ed
v
alid
o
r
v
ice
v
e
r
s
a.
Nex
t,
a
n
e
v
alu
atio
n
o
f
f
ac
t
o
r
cr
iter
ia
ca
r
r
ied
o
u
t
with
a
n
esti
m
ated
m
o
d
el
b
ased
o
n
th
r
ee
m
ea
s
u
r
em
e
n
t
cr
iter
ia,
c
o
n
s
is
ts
o
f
ab
s
o
lu
t
e,
in
cr
em
e
n
tal,
an
d
p
ar
s
im
o
n
io
u
s
f
it
m
ea
s
u
r
es
(
o
v
er
all
m
o
d
el
f
it)
o
r
k
n
o
wn
a
s
g
o
o
d
n
ess
-
of
-
f
it st
atis
tics
(
G
OF)
.
3
.
4
.
Va
lid
a
t
io
n/d
eplo
y
m
ent
m
o
d
el
T
h
e
ev
alu
atio
n
s
tag
e
is
ex
ec
u
t
ed
p
ass
two
s
u
b
-
test
s
i.e
.
,
−
Stan
d
ar
d
ized
lo
a
d
in
g
f
ac
to
r
s
CR
=
0
.
27F
R
+
78
,
49
TATO
=
−
0
.
055F
R
+
1
,
26
DE
R
=
0
.
29F
R
+
41
,
41
R
OA
=
0
.
22F
R
−
0
,
033
PBV
=
−
1
.
65F
R
+
540
,
92
Fin
an
cial
R
atio
'
s
g
iv
es
a
v
er
y
im
p
ac
t
o
n
th
e
ac
cu
r
ac
y
o
f
ea
ch
m
ea
s
u
r
em
en
t,
in
clu
d
i
n
g
C
R
o
f
7
8
.
4
9
,
T
AT
O
o
f
1
.
2
6
,
DE
R
o
f
4
1
.
4
1
,
R
OA
o
f
o
n
ly
m
i
n
u
s
0
.
0
3
,
an
d
PB
V
o
f
5
4
0
.
9
2
.
T
h
is
m
ea
n
s
th
at
PB
V
h
as
th
e
h
ig
h
est
s
tan
d
ar
d
ized
lo
ad
in
g
f
ac
to
r
s
to
d
eter
m
in
e
th
e
m
ea
s
u
r
em
en
t
o
f
Fin
an
cial
R
atio
's.
F
ig
u
r
e
3
is
s
h
o
win
g
p
ath
d
iag
r
a
m
: m
ea
s
u
r
em
e
n
t m
o
d
el
.
Fig
u
r
e
3
.
Path
d
iag
r
am
: m
ea
s
u
r
em
en
t m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
: 2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
10
,
No
.
2
,
J
u
n
e
2
0
2
1
:
1
1
5
–
1
2
1
120
−
Go
o
d
n
ess
-
of
-
f
it st
atis
tic
s
(G
o
F)
C
h
i
-
s
q
u
ar
e
test
p
r
o
d
u
ce
s
a
s
co
r
e
o
f
1
.
1
0
with
a
p
-
v
alu
e
o
f
0
.
9
5
4
0
5
.
T
h
e
C
FI/T
L
I
test
y
ie
ld
s
a
s
co
r
e
o
f
-
8
.
8
2
,
wh
ic
h
m
ea
n
s
it
s
h
o
ws
p
o
o
r
-
f
it.
A
s
tan
d
a
r
d
ized
R
MR
0
.
0
2
6
with
an
R
MSE
A
o
f
0
.
0
0
r
esu
lts
in
a
clo
s
e
-
f
it in
d
ex
.
GFI
a
n
d
AGFI
v
alu
es o
f
1
.
0
0
also
p
r
o
d
u
ce
a
clo
s
e
-
f
it in
d
ex
.
3
.
5
.
Ana
ly
s
is
T
h
e
C
FA
tech
n
iq
u
e
is
o
p
er
a
ted
to
p
r
o
v
e
t
h
e
ac
c
u
r
ac
y
o
f
th
e
m
o
d
el
d
ev
el
o
p
m
en
t
v
al
u
e
in
th
is
r
esear
ch
th
r
o
u
g
h
s
u
m
m
ar
izatio
n
,
d
esig
n
,
s
p
ec
if
icatio
n
,
an
d
v
alid
atio
n
s
tag
es
o
n
th
e
DSS
ap
p
r
o
ac
h
p
ass
ed
d
o
wn
in
s
id
e
s
tatis
tical
in
SE
M
with
f
in
an
cial
r
atio
'
s
o
b
jects.
T
h
ese
illu
s
tr
atio
n
s
ex
p
lain
t
h
at
d
esig
n
in
g
a
p
ath
d
iag
r
am
f
o
r
m
ea
s
u
r
em
en
t
p
r
o
p
er
ties
an
d
d
etec
tin
g
er
r
o
r
s
in
th
e
u
s
e
o
f
m
ea
s
u
r
em
en
ts
at
an
ea
r
ly
s
tag
e.
Her
ea
f
ter
,
it
s
p
ec
if
ies
th
e
d
esig
n
f
o
r
th
e
n
ex
t
s
tag
es
to
co
n
v
er
t
in
to
a
co
v
a
r
ian
ce
m
atr
ix
to
in
ter
p
r
et
a
f
o
r
war
d
in
g
d
ec
is
io
n
-
m
a
k
in
g
m
o
d
el.
I
n
th
is
r
esear
ch
,
t
h
e
C
F
A
tech
n
iq
u
e
u
s
in
g
o
r
k
n
o
wn
as
f
ir
s
t
-
o
r
d
er
co
n
f
ir
m
ato
r
y
in
SEM
u
s
ed
to
s
ee
wh
ich
m
ea
s
u
r
e
m
en
ts
m
ee
t
th
e
f
ac
to
r
lo
ad
r
eq
u
ir
em
en
ts
.
I
f
th
e
v
alu
e
is
m
o
r
e
th
an
0
.
5
,
th
e
n
th
e
m
ea
s
u
r
em
e
n
t
is
co
n
s
id
er
ed
v
alid
o
r
v
ice
v
er
s
a.
Fu
r
th
er
m
o
r
e
,
g
o
o
d
n
es
s
-
of
-
f
it
(
Go
F)
was
ex
ec
u
ted
b
ased
o
n
th
e
th
r
ee
cr
iter
ia
ab
o
v
e
to
ass
ess
wh
eth
er
th
e
m
o
d
el
p
r
o
p
o
s
ed
in
th
is
s
tu
d
y
co
u
l
d
b
e
co
n
tin
u
ed
at
t
h
e
d
ep
lo
y
m
en
t
s
tag
e
o
r
n
o
t.
I
f
it
d
o
es
n
o
t
m
ee
t
th
e
m
o
d
el
s
u
itab
ilit
y
ass
ess
m
en
t
cr
iter
ia
in
d
e
x
,
th
en
a
r
e
-
s
p
ec
if
icatio
n
o
r
m
o
d
if
icatio
n
in
d
i
ce
s
s
tep
ca
n
b
e
m
ad
e
th
r
o
u
g
h
a
r
ec
o
m
m
e
n
d
at
io
n
f
r
o
m
th
e
o
u
t
p
u
t
wh
en
u
s
in
g
th
e
L
I
SR
E
L
Ver
s
io
n
8
.
7
2
a
p
p
licatio
n
with
c
h
an
g
e
th
e
in
itial
s
y
n
tax
b
y
co
r
r
elatin
g
a
p
air
o
f
v
alu
es
b
etwe
en
er
r
o
r
v
a
r
ian
ce
s
.
T
h
is
f
in
d
in
g
p
r
esen
ts
th
e
v
a
lu
e
o
f
R
MSE
A
as
a
b
a
s
is
f
o
r
d
ec
is
io
n
m
ak
in
g
to
v
alid
ate
th
e
m
o
d
el,
wh
ich
r
eq
u
ir
es a
v
alu
e
o
f
less
th
an
0
.
0
8
.
Sev
er
al
s
tu
d
ies
s
h
o
w
f
in
d
in
g
s
with
ea
ch
ap
p
r
o
ac
h
to
a
n
s
wer
r
esear
ch
p
r
o
b
lem
s
,
s
u
ch
as
th
e
Pair
-
C
o
p
u
la
ap
p
r
o
ac
h
b
y
a
h
ier
ar
c
h
ical
m
o
d
el
co
n
s
tr
u
ct
with
ass
ess
m
en
t
th
r
o
u
g
h
o
b
s
er
v
ed
a
n
d
laten
t
v
ar
iab
les
[6
]
-
[
8
]
.
T
h
e
s
am
e
is
th
e
ca
s
e
with
th
e
u
s
ag
e
o
f
Go
F
to
ex
p
lain
a
m
o
d
el;
h
o
wev
e
r
,
it
u
s
es
an
ap
p
r
o
ac
h
to
p
ar
tial
least
s
q
u
ar
es
p
ath
m
o
d
elin
g
an
d
also
Ken
d
all'
s
-
T
co
p
u
la
m
o
d
el
(
R
-
v
i
n
e)
[
10
]
,
[
9
]
wh
ile
th
is
r
esear
ch
u
s
es
a
C
FA
tech
n
iq
u
e
a
n
d
a
ls
o
ad
o
p
ted
b
y
th
e
ML
E
a
p
p
r
o
ac
h
b
u
t
i
n
th
is
s
tu
d
y
d
i
d
n
o
t
ca
lcu
lated
with
va
r
ian
ce
alter
L
R
an
d
a
m
ea
n
test
s
tatis
tic
[
11
]
.
Mo
r
e
o
v
e
r
,
ac
co
r
d
in
g
to
d
eter
m
in
e
t
h
e
s
ig
n
if
ican
ce
o
f
th
e
f
u
n
ctio
n
d
is
cr
im
in
an
t
an
d
test
in
g
av
er
a
g
e
d
if
f
e
r
en
ce
b
etwe
en
s
ev
er
al
g
r
o
u
p
s
,
t
h
is
is
also
th
e
s
am
e
at
th
e
s
p
ec
if
icatio
n
s
tag
e
f
o
r
test
in
g
th
e
q
u
ality
o
f
th
e
p
r
o
p
o
s
ed
m
ea
s
u
r
em
en
t
in
s
tr
u
m
en
t
[
12
]
,
wh
ile
th
is
r
esear
ch
u
s
es a
n
SLF
co
n
f
ir
m
ato
r
y
tech
n
iq
u
e.
C
o
v
ar
ian
ce
m
o
d
els
with
v
in
e
to
an
y
th
in
g
(
ViT
A
)
wer
e
d
ev
elo
p
ed
b
ased
o
n
a
m
u
ltiv
ar
iate
d
is
tr
ib
u
tio
n
k
n
o
wn
as
th
e
R
-
Vin
es
co
n
ce
p
t
with
h
ig
h
-
lev
e
l
co
n
tr
o
l
s
p
ec
if
ically
f
o
r
th
e
n
ee
d
d
ata
with
n
o
n
-
n
o
r
m
ality
m
u
ltiv
ar
iate
th
r
o
u
g
h
th
e
s
k
ewn
ess
an
d
k
u
r
to
s
is
s
co
r
e
[
13
]
,
wh
ile
th
is
r
esear
c
h
u
s
es
a
Go
F
s
co
r
e
v
iewe
d
b
ased
o
n
clau
s
e
g
r
e
ater
th
an
0
.
5
(
p
-
v
alu
es;
C
h
i
-
Sq
u
ar
e
s
co
r
e
)
.
W
ith
c
o
m
p
u
tatio
n
al
co
g
n
itiv
e
m
o
d
elin
g
,
e
x
p
ec
tan
t
m
o
d
els'
s
im
u
latio
n
is
o
b
lig
ato
r
y
to
co
u
n
ter
f
eit
th
e
m
o
d
els
an
d
s
u
p
p
o
r
t
d
ef
in
ite
co
g
n
itiv
e
f
u
n
ctio
n
claim
s
.
Ho
wev
er
,
th
ey
o
v
er
lo
o
k
ed
th
eir
p
r
ed
ictiv
e
p
er
f
o
r
m
a
n
ce
[
14
]
,
wh
ile
th
is
r
esear
ch
u
s
es
a
C
FI/T
L
I
test
y
ield
s
co
r
e
th
a
t
is
-
8
,
8
2
v
iewe
d
b
ased
o
n
clau
s
e
g
r
ea
ter
th
an
0
.
9
7
s
o
it'
s
v
er
y
d
if
f
er
en
t
f
r
o
m
t
h
at
clau
s
e.
A
s
y
s
tem
atic
DSS
as
ev
alu
atio
n
in
g
r
e
d
ien
t
m
o
d
elin
g
as
a
b
ase
f
o
r
d
ec
is
io
n
-
m
ak
in
g
u
s
ed
to
a
weig
h
ted
-
s
u
m
m
eth
o
d
to
p
ick
a
f
in
al
m
o
d
el
wh
ich
u
s
es
th
e
m
o
n
etar
y
wo
r
t
h
o
f
th
e
Sectio
n
1
2
L
tax
in
ce
n
tiv
e
f
ac
to
r
with
a
s
co
r
e
b
etwe
en
0
.
1
to
0
.
3
3
[
15
]
,
wh
ile
i
n
th
is
r
esear
ch
u
s
es
an
R
MR
s
co
r
e
th
at
is
0
.
0
2
6
v
iewe
d
b
ased
o
n
a
clau
s
e
th
at
m
ee
ts
th
e
r
eq
u
i
r
em
en
ts
is
less
th
an
s
am
e
with
0
.
0
8
.
T
h
e
co
n
s
tr
u
ct
o
f
m
ar
k
etin
g
DSS
with
ex
p
lo
r
at
o
r
y
f
ac
to
r
an
aly
s
is
(
E
FA)
an
d
KM
O
an
d
B
ar
tlett's
test
with
y
ield
v
alid
an
d
r
eliab
le
in
s
tr
u
m
en
t
wh
ich
is
s
im
ilar
to
th
i
s
r
esear
c
h
lo
o
k
in
g
at
C
h
i
-
Sq
u
ar
e
s
co
r
e
an
d
p
-
v
al
u
es
[
16
]
,
wh
ile
p
air
-
s
am
p
le
T
-
test
with
a
y
ield
o
f
n
o
r
m
ality
a
n
d
L
ev
e
n
e'
s
test
i
s
ev
alu
atio
n
an
d
ass
ess
m
en
t
o
f
th
e
m
o
d
el
with
th
e
DSS
ap
p
r
o
ac
h
as
a
co
m
p
ar
ativ
e
s
tu
d
y
[
17
]
.
B
ased
o
n
th
e
ab
o
v
e
a
n
aly
s
is
,
th
e
C
FA
m
ea
s
u
r
em
en
t
o
n
an
SEM
b
asis
is
co
n
s
id
er
e
d
to
an
s
wer
o
r
r
ep
r
esen
t
t
h
e
a
cc
u
r
ac
y
o
f
s
ev
er
al
r
esu
lts
o
f
p
r
ev
i
o
u
s
s
tu
d
ies.
DSS
ab
ilit
ies
p
er
m
it
d
ec
is
io
n
-
m
ak
er
s
to
m
a
k
e
p
r
ef
er
a
b
le,
o
r
d
er
ly
d
ec
is
io
n
s
p
r
o
m
p
tly
if
co
n
jo
in
ted
with
C
FA
m
ea
s
u
r
em
en
t
f
o
r
s
p
ec
if
i
ca
tio
n
m
o
d
elin
g
.
4.
CO
NCLU
SI
O
N
T
h
e
f
in
an
cial
r
atio
test
in
g
m
o
d
el
with
a
C
FA
ap
p
r
o
ac
h
a
ttain
in
to
a
m
ath
em
atica
l
(
q
u
an
titativ
e)
m
o
d
el
ca
n
d
escr
ib
e
t
h
e
co
m
p
l
ex
ity
o
f
th
e
lin
k
b
etwix
t
th
e
g
o
o
d
n
ess
-
of
-
f
it
m
o
d
el
(
GOF)
.
T
h
e
d
eter
m
in
atio
n
o
f
th
e
n
u
m
b
e
r
o
f
s
am
p
les
r
an
g
in
g
f
r
o
m
5
0
-
2
0
0
is
s
u
itab
le
u
s
in
g
th
e
m
ax
im
u
m
lik
elih
o
o
d
esti
m
atio
n
(
ML
E
)
tech
n
iq
u
e.
C
h
i
-
s
q
u
ar
e
s
tatis
tic
s
(χ
2
)
o
f
1
.
1
0
with
a
p
-
v
alu
e
g
r
ea
ter
th
a
n
0
.
5
an
d
th
e
R
MSE
A
s
co
r
e
th
at
s
h
o
ws
a
m
o
d
el
th
at
m
ee
ts
th
e
cl
o
s
e
-
f
it
cr
iter
ia
is
th
e
b
asis
o
r
r
ef
er
e
n
ce
th
at
th
e
m
o
d
el
d
o
es n
o
t n
e
ed
to
b
e
ca
r
r
ied
o
u
t
re
-
s
p
ec
if
icatio
n
o
r
im
p
r
o
v
e
m
e
n
t.
T
h
e
g
o
o
d
n
ess
-
of
-
f
it
test
r
esu
lts
in
th
is
s
tu
d
y
p
r
o
d
u
ce
d
s
c
o
r
es
o
n
ea
ch
o
f
th
e
f
in
an
cial
r
atio
m
ea
s
u
r
em
en
t
m
o
d
els
at
an
ac
cu
r
ac
y
lev
el
o
f
C
R
o
f
7
8
.
4
9
,
T
AT
O
o
f
1
.
2
6
,
DE
R
o
f
4
1
.
4
1
,
R
OA
o
f
m
in
u
s
0
.
0
3
3
,
an
d
PB
V
o
f
5
4
0
.
9
2
.
T
h
is
m
ea
n
s
th
at
PB
V
h
as
th
e
h
ig
h
est
s
tan
d
ar
d
ized
lo
ad
in
g
f
ac
to
r
s
to
d
eter
m
in
e
th
e
m
ea
s
u
r
em
en
t
o
f
Fin
an
cial
R
atio
's.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2
2
5
2
-
8
8
1
4
C
o
n
fir
ma
to
r
y
fa
cto
r
a
n
a
lysi
s
:
mo
d
el
test
in
g
o
f fin
a
n
ci
a
l
r
a
tio
s
w
ith
d
ec
is
io
n
s
u
p
p
o
r
t …
(
T.
Hu
s
a
in
)
121
T
h
e
m
ea
s
u
r
e
m
en
t
o
f
C
FA
b
a
s
ed
o
n
SEM
ca
n
b
e
u
s
ed
as
a
co
n
s
id
er
atio
n
i
n
m
a
k
in
g
ap
p
r
o
p
r
iate
d
ec
is
io
n
s
.
T
h
is
r
esear
ch
p
r
o
p
o
s
es
p
r
ac
tical
r
eso
lv
es
f
o
r
h
e
r
ea
f
ter
in
v
esti
g
atio
n
th
at
in
te
g
r
ate
co
n
s
o
lid
ate
a
m
o
d
el
ap
p
ea
l
an
d
r
e
d
ev
elo
p
m
en
t
o
f
t
h
e
C
FA
s
o
th
at
m
o
d
el
t
esti
n
g
ca
n
b
e
u
s
ef
u
l f
o
r
th
e
d
e
n
o
m
in
atio
n
o
f
h
o
w
well
an
o
th
er
p
ath
m
o
d
el
ca
n
d
escr
ib
e
d
is
tin
ct
s
et
s
o
f
d
ata
an
d
u
s
e
o
th
er
s
o
f
twar
e
s
u
ch
as
S
PS
S,
PL
S,
AM
O
S,
an
d
o
th
e
r
s
.
RE
F
E
R
E
NC
E
S
[1
]
Ra
m
e
sh
S
h
a
rd
a
,
Du
rsu
n
De
len
,
E
fra
im
Tu
rb
a
n
,
B
u
sin
e
ss
In
telli
g
e
n
c
e
a
n
d
A
n
a
lytics
:
S
y
ste
ms
fo
r
De
c
isio
n
S
u
p
p
o
rt
,
1
0
t
h
e
d
.
NJ
:
P
e
a
rso
n
,
2
0
1
5
.
[2
]
Efr
a
im
Tu
rb
a
n
,
Ja
y
E
.
Aro
n
so
n
,
Ti
n
g
-
P
e
n
g
Li
a
n
g
,
Rich
a
rd
V.
M
c
Ca
rth
y
,
De
c
isio
n
S
u
p
p
o
rt
S
y
ste
ms
a
n
d
I
n
telli
g
e
n
t
S
y
ste
ms
,
7
th
e
d
.
:
P
re
n
ti
c
e
-
Ha
l!
o
f
In
d
ia P
r
iv
a
ted
Li
m
it
e
d
,
2
0
0
7
.
[3
]
G
a
li
t
S
h
m
u
e
li
,
Niti
n
R.
P
a
tel,
P
e
ter
C.
Bru
c
e
,
Da
t
a
M
in
i
n
g
fo
r
B
u
sin
e
ss
In
telli
g
e
n
c
e
:
Co
n
c
e
p
ts,
T
e
c
h
n
iq
u
e
s,
a
n
d
Ap
p
li
c
a
ti
o
n
s i
n
M
icr
o
so
ft
Offi
c
e
Exc
e
l
wit
h
XL
M
in
e
r
,
2
n
d
e
d
.
Ca
n
a
d
a
:
Jo
h
n
Wi
le
y
&
S
o
n
s,
I
n
c
,
2
0
1
0
.
[4
]
Jo
se
p
h
F
.
Ha
ir,
Wi
ll
iam
C.
Blac
k
,
Ba
rry
J.
Ba
b
in
,
Ro
lp
h
E
.
A
n
d
e
rs
o
n
,
M
u
lt
iv
a
ria
te
D
a
ta
A
n
a
lys
is
,
7
th
e
d
.
L
o
n
d
o
n
:
P
e
a
rso
n
Ed
u
c
a
ti
o
n
Li
m
it
e
d
,
2
0
1
4
.
[5
]
Ag
u
s
Dj
o
k
o
S
a
n
to
sa
,
L
IS
RE
L
8
.
7
i
n
Res
e
a
rc
h
D
a
ta
Pro
c
e
ss
in
g
(
in
B
a
h
a
sa
),
Yo
g
y
a
k
a
rta:
P
u
b
li
sh
e
r
Ke
p
e
l
P
re
ss
,
2
0
2
0
.
[6
]
Kje
rsti
Aa
s,
Clau
d
ia
Cz
a
d
o
,
Arn
o
ld
o
F
r
ig
e
ss
i,
He
n
rik
Ba
k
k
e
n
,
“
P
a
i
r
-
c
o
p
u
la
c
o
n
stru
c
ti
o
n
s
o
f
m
u
lt
ip
le
d
e
p
e
n
d
e
n
c
e
,
”
In
su
ra
n
c
e
:
M
a
th
e
ma
ti
c
s
a
n
d
Eco
n
o
mic
s
,
v
o
l.
4
4
,
n
o
.
2
,
p
p
.
1
8
2
-
1
9
8
,
Ap
ril
2
0
0
9
.
[O
n
l
in
e
]
Av
a
il
a
b
le:
h
tt
p
s:/
/d
o
i.
o
rg
/
1
0
.
1
0
1
6
/j
.
i
n
sm
a
th
e
c
o
.
2
0
0
7
.
0
2
.
0
0
1
.
[7
]
S
a
y
y
e
d
H.
Ka
d
h
e
m
,
Aristid
is
K.
Nik
o
l
o
u
lo
p
o
u
lo
s,
“
F
a
c
to
r
c
o
p
u
la
m
o
d
e
ls
fo
r
m
ix
e
d
d
a
ta,”
W
o
rk
sh
o
p
a
t
th
e
T
e
c
h
n
ica
l
U
n
ive
rs
it
y
o
f
M
u
n
ich
,
p
p
.
1
-
2
8
,
Ju
ly
2
0
1
9
.
[O
n
li
n
e
]
A
v
a
il
a
b
le:
h
t
tp
s://
a
r
x
iv
.
o
r
g
/ab
s/1
9
0
7
.
0
7
3
9
5
v
1
.
[8
]
Kje
rsti
Aa
s,
“
P
a
ir
-
Co
p
u
la
Co
n
str
u
c
ti
o
n
s
fo
r
F
i
n
a
n
c
ial
Ap
p
li
c
a
ti
o
n
s:
A
Re
v
iew
,
”
Eco
n
o
me
trics
,
v
o
l.
4
,
n
o
.
4
,
p
p
.
1
-
1
5
,
2
0
1
6
.
[On
l
in
e
]
Av
a
il
a
b
le:
h
tt
p
s://
d
o
i
.
o
r
g
/1
0
.
3
3
9
0
/ec
o
n
o
m
e
tri
c
s4
0
4
0
0
4
3
.
[9
]
U
lf
S
c
h
e
p
sm
e
ier,
“
A
g
o
o
d
n
e
ss
-
of
-
fit
tes
t
fo
r
re
g
u
lar
v
i
n
e
c
o
p
u
la
m
o
d
e
ls,”
Eco
n
o
me
tric
Rev
iews
,
v
o
l
.
3
8
,
n
o
.
1
,
p
p
.
25
-
4
6
,
2
0
1
9
.
[On
li
n
e
]
Av
a
i
lab
le:
h
tt
p
s:/
/d
o
i.
o
rg
/
1
0
.
1
0
8
0
/0
7
4
7
4
9
3
8
.
2
0
1
6
.
1
2
2
2
2
3
1
.
[1
0
]
Jö
r
g
He
n
se
ler
a
n
d
M
a
r
k
o
S
a
rste
d
t,
“
G
o
o
d
n
e
ss
-
of
-
fi
t
i
n
d
ice
s
fo
r
p
a
rti
a
l
lea
st
sq
u
a
re
s
p
a
th
m
o
d
e
li
n
g
,
”
Co
mp
u
ta
ti
o
a
l
S
ta
t
ist
ics
,
v
o
l.
2
8
,
p
p
.
5
6
5
-
5
8
0
,
2
0
1
3
.
[On
li
n
e
]
Av
a
i
lab
le:
h
tt
p
s:/
/d
o
i.
o
r
g
/
1
0
.
1
0
0
7
/s
0
0
1
8
0
-
0
1
2
-
0
3
1
7
-
1
.
[1
1
]
Alb
e
rto
M
a
y
d
e
u
-
Oli
v
a
re
s,
“
M
a
x
i
m
u
m
Li
k
e
li
h
o
o
d
Esti
m
a
ti
o
n
o
f
S
tru
c
tu
ra
l
E
q
u
a
ti
o
n
M
o
d
e
ls
fo
r
C
o
n
ti
n
u
o
u
s
Da
ta:
S
tan
d
a
rd
Err
o
rs
a
n
d
G
o
o
d
n
e
ss
o
f
F
it
,
”
S
tr
u
c
tu
ra
l
Eq
u
a
ti
o
n
M
o
d
e
li
n
g
:
A
M
u
l
ti
d
isc
i
p
li
n
a
ry
J
o
u
rn
a
l
,
v
o
l.
2
4
,
n
o
.
3
,
p
p
.
3
8
3
-
3
9
4
,
F
e
b
ru
a
ry
2
0
1
7
.
[On
l
in
e
]
Av
a
il
a
b
le:
h
tt
p
s://
d
o
i.
o
r
g
/1
0
.
1
0
8
0
/
1
0
7
0
5
5
1
1
.
2
0
1
6
.
1
2
6
9
6
0
6
.
[1
2
]
A.
Rizk
ian
a
,
P
.
He
n
d
i
k
a
wa
ti
,
“
Clas
sifica
ti
o
n
o
f
Cu
st
o
m
e
r
S
a
ti
s
fa
c
ti
o
n
Le
v
e
ls
with
Disc
rimin
a
n
t
An
a
ly
sis
(in
b
a
h
a
sa
),
”
M
IPA
o
f
J
o
u
rn
a
ls
,
v
o
l.
3
8
,
n
o
.
1
,
p
p
.
8
9
-
1
0
0
,
No
v
e
m
b
e
r
2
0
1
5
.
[O
n
li
n
e
]
Av
a
il
a
b
le:
h
tt
p
s:/
/j
o
u
rn
a
l.
u
n
n
e
s.a
c
.
id
/
n
ju
/
in
d
e
x
.
p
h
p
/JM
/article
/
v
iew
/5
4
9
0
.
[1
3
]
S
teffe
n
G
rø
n
n
e
b
e
rg
,
Njå
l
F
o
ld
n
e
s,
“
Co
v
a
rian
c
e
M
o
d
e
l
S
imu
latio
n
Us
in
g
Re
g
u
la
r
Vi
n
e
s,”
Psy
c
h
o
me
trika
,
v
o
l
.
8
2
,
n
o
.
4
,
p
p
.
1
0
3
5
-
10
5
1
,
Ja
n
u
a
ry
2
0
1
7
.
[On
li
n
e
]
Av
a
il
a
b
le:
h
tt
p
s://
d
o
i
.
o
rg
/
1
0
.
1
0
0
7
/s1
1
3
3
6
-
0
1
7
-
9
5
6
9
-
6
.
[1
4
]
S
tefa
n
o
P
a
lmi
n
teri,
Va
len
ti
n
Wy
a
rt,
Et
ien
n
e
Ko
e
c
h
li
n
,
“
Th
e
Im
p
o
rtan
c
e
o
f
F
a
lsifi
c
a
t
io
n
in
Co
m
p
u
tat
io
n
a
l
Co
g
n
it
iv
e
M
o
d
e
li
n
g
,
”
T
re
n
d
s
i
n
Co
g
n
it
ive
S
c
ien
c
e
s
,
v
o
l.
2
1
,
n
o
.
6
,
p
p
.
4
2
5
-
4
3
3
,
Ju
n
e
2
0
1
7
.
[O
n
li
n
e
]
Av
a
il
a
b
le:
h
tt
p
s:/
/d
o
i.
o
rg
/
1
0
.
1
0
1
6
/j
.
ti
c
s.
2
0
1
7
.
0
3
.
0
1
1
.
[1
5
]
L.
A.
Bo
tes
,
W.
B
o
o
y
se
n
,
M
.
J.
M
a
th
e
ws
,
M
.
Kle
in
g
e
ld
,
“
A
sy
ste
m
a
ti
c
d
e
c
isio
n
su
p
p
o
rt
sy
ste
m
to
o
b
jec
ti
v
e
ly
e
v
a
lu
a
te
re
tro
sp
e
c
ti
v
e
e
n
e
rg
y
e
ffi
c
ie
n
c
y
m
o
d
e
li
n
g
o
p
ti
o
n
s,”
J
o
u
rn
a
l
o
f
E
n
e
rg
y
in
S
o
u
t
h
e
rn
A
frica
,
v
o
l.
3
0
,
n
o
.
2
,
p
p
.
5
2
-
6
3
,
M
a
y
2
0
1
9
.
[
O
n
li
n
e
]
A
v
a
il
a
b
le:
h
tt
p
s:/
/d
x
.
d
o
i.
o
rg
/
1
0
.
1
7
1
5
9
/
2
4
1
3
-
3
0
5
1
/
2
0
1
9
/
v
3
0
i
2
a
5
7
4
0
.
[1
6
]
Am
g
e
d
S
a
leh
S
h
k
e
e
r,
Zain
u
d
i
n
Aw
a
n
g
,
“
E
x
p
l
o
ri
n
g
th
e
Item
s
fo
r
M
e
a
su
rin
g
th
e
M
a
rk
e
ti
n
g
I
n
fo
r
m
a
ti
o
n
S
y
ste
m
Co
n
stru
c
t:
An
Ex
p
lo
ra
t
o
ry
F
a
c
to
r
An
a
ly
sis,
”
I
n
ter
n
a
t
io
n
a
l
Rev
iew
o
f
M
a
n
a
g
e
me
n
t
a
n
d
M
a
rk
e
ti
n
g
,
v
o
l.
9
,
n
o
.
6
,
p
p
.
87
-
9
7
,
2
0
1
9
.
[On
li
n
e
]
Av
a
i
lab
le:
h
tt
p
s:/
/d
o
i.
o
rg
/
1
0
.
3
2
4
7
9
/i
rm
m
.
8
6
2
2
.
[1
7
]
T.
Hu
sa
in
,
M
a
u
lan
a
Ard
h
ian
sy
a
h
,
“
P
a
ir
-
S
a
m
p
les
T
Tes
t:
S
imu
lati
o
n
M
o
d
e
l
o
f
F
i
n
a
n
c
ial
Ra
ti
o
'
s
M
e
a
su
re
m
e
n
t
wit
h
De
c
isio
n
S
u
p
p
o
r
t
S
y
ste
m
s
(DS
S
)
Ap
p
ro
a
c
h
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
T
re
n
d
s
in
E
n
g
i
n
e
e
rin
g
,
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
IJ
AT
ES
T
,
v
o
l.
5
,
n
o
.
4
,
p
p
.
1
3
-
1
7
,
J
u
ly
2
0
2
0
.
[On
li
n
e
]
Av
a
il
a
b
le:
h
tt
p
:/
/www
.
ij
a
tes
t.
o
rg
/wp
-
c
o
n
ten
t/
u
p
lo
a
d
s/
v
5
.
i4
.
3
.
P
a
ir
-
S
a
m
p
les
-
T
-
Tes
t
-
S
imu
lati
o
n
-
M
o
d
e
l
-
of
-
F
in
a
n
c
ial
-
Ra
ti
o
s
-
M
e
a
su
re
m
e
n
t
-
with
-
De
c
isio
n
-
S
u
p
p
o
rt
-
S
y
tem
s
-
DSS
-
Ap
p
ro
a
c
h
.
p
d
f
.
[1
8
]
In
d
o
n
e
sia
S
t
o
c
k
Ex
c
h
a
n
g
e
,
D
e
c
e
m
b
e
r
IDX
,
2
0
1
9
.
[O
n
li
n
e
]
Av
a
il
a
b
le:
h
tt
p
s://
ww
w.i
d
x
.
c
o
.
id
/
p
e
ru
sa
h
a
a
n
-
terc
a
tat/ak
ti
v
it
a
s
-
p
e
n
c
a
tata
n
/
.
[1
9
]
S
u
p
ra
n
to
,
Na
n
d
a
n
Li
m
a
k
risn
a
,
Pra
c
ti
c
a
l
Gu
id
e
li
n
e
s
fo
r
S
c
ien
ti
fi
c
Res
e
a
rc
h
fo
r
Pre
p
a
rin
g
T
h
e
sis,
T
h
e
sis
a
n
d
Diss
e
rta
ti
o
n
(
in
b
a
h
a
s
a
)
,
5
th
e
d
.
Bo
g
o
r
:
P
u
b
li
s
h
e
r
M
it
ra
Wac
a
n
a
M
e
d
ia,
2
0
1
3
.
[2
0
]
S
h
e
rid
a
n
Ti
tma
n
,
Art
h
u
r
J.
Ke
o
w
n
,
J
o
h
n
D.
M
a
rti
n
,
Fi
n
a
n
c
ia
l
M
a
n
a
g
e
me
n
t:
Pri
n
c
ip
les
a
n
d
Ap
p
li
c
a
ti
o
n
s
,
1
2
th
e
d
.
Bo
sto
n
,
USA:
P
re
n
ti
c
e
Ha
ll
,
2
0
1
3
.
[2
1
]
T.
Hu
sa
in
,
“
An
A
n
a
ly
sis
o
f
M
o
d
e
li
n
g
Au
d
it
Qu
a
li
t
y
M
e
a
su
re
m
e
n
t
Ba
se
d
o
n
De
c
isio
n
S
u
p
p
o
r
t
S
y
ste
m
s
(DSS
),
”
Eu
ro
p
e
a
n
J
o
u
r
n
a
l
o
f
S
c
ien
ti
fi
c
Exp
l
o
ra
ti
o
n
,
v
o
l.
2
,
n
o
.
6
,
p
p
.
1
-
9
,
De
c
e
m
b
e
r
2
0
1
9
.
[O
n
li
n
e
]
Av
a
il
a
b
le:
h
tt
p
s:/
/www
.
sy
n
i
u
tajo
u
rn
a
ls.c
o
m
/i
n
d
e
x
.
p
h
p
/E
J
S
E/
a
rti
c
le/v
iew
/
1
2
8
/
1
1
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.