I
n
t
ern
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
l
e
ct
ri
ca
l
a
n
d
C
o
mp
u
t
er
E
n
g
i
n
eeri
n
g
(
I
J
E
C
E
)
V
o
l
.
11
,
N
o
.
1
,
F
e
b
ru
a
ry
2
021
,
p
p
.
284
~
292
I
S
S
N
:
208
8
-
87
08
,
D
O
I
:
10.
115
91
/
i
j
e
c
e
.
v11
i
1
.
pp
28
4
-
2
92
2
84
Jo
u
r
n
al
h
om
e
pa
ge
:
h
t
t
p
:
/
/
i
j
e
c
e
.
i
a
e
s
c
o
r
e
.
c
o
m
Mo
d
i
fi
e
d
h
o
te
l
l
i
n
g
’s
co
nt
ro
l
cha
rt
s
us
i
ng
mo
d
i
f
i
ed
m
ah
al
an
obi
s
di
s
t
an
c
e
F
i
r
a
s
H
a
dd
a
d
D
e
pa
rt
m
e
nt
o
f G
e
ne
ra
l
c
ours
e
s
,
Col
l
e
ge
of
A
ppl
i
e
d S
t
udi
e
s
a
nd
C
om
m
uni
t
y
S
e
rvi
c
e
,
Im
a
m
A
bdurra
h
m
a
n B
i
n F
a
i
s
a
l
U
ni
ve
rs
i
t
y,
A
l
-
D
am
m
am
,
S
au
d
i
A
r
ab
i
a
A
rt
i
cl
e
I
n
f
o
A
B
S
T
RA
C
T
Ar
t
i
c
l
e
h
i
s
t
o
r
y
:
R
ecei
v
ed
Ap
r
1
2,
2
020
Re
v
i
s
e
d
J
un
13
,
202
0
A
ccep
t
e
d
Ju
l
5
,
202
0
T
hi
s
pa
p
e
r prop
os
e
d ne
w
a
dj
us
t
e
d H
ot
e
l
l
i
ng’s
2
c
ont
rol
c
ha
rt
for
i
ndi
vi
dua
l
obs
e
rva
t
i
ons
.
F
or t
hi
s
obj
e
c
t
i
v
e
,
boot
s
t
r
a
p m
e
t
hod for
produc
i
ng
t
he
i
nd
i
vi
du
a
l
o
bs
e
rva
t
i
ons
w
e
re
e
m
pl
oye
d
.
T
o do
s
o,
bot
h
a
ri
t
h
m
e
t
i
c
m
e
a
n
v
e
c
to
r
a
n
d
th
e
c
o
v
a
r
ia
n
c
e
ma
tr
ix
in
th
e
tr
a
d
it
io
n
a
l H
o
te
llin
g
’
s
2
ch
ar
t
w
er
e
s
ubs
t
i
t
ut
e
d by
t
he
t
ri
m
m
e
d m
e
a
n ve
c
t
or
a
nd
t
he
c
ova
ri
a
nc
e
m
a
t
ri
x
of
t
he
robus
t
s
c
a
l
e
e
s
t
i
m
a
t
ors
Q
n
,
r
e
s
pe
c
t
i
v
e
l
y w
hi
c
h,
i
n
t
urn,
i
t
s
p
e
rfor
m
a
nc
e
i
s
c
a
rri
e
d out
by
s
i
m
ul
a
t
e
d
.
In
fa
c
t
,
t
he
c
a
l
c
ul
a
t
i
on
of fa
l
s
e
a
l
a
r
m
s
a
nd
t
he
prob
a
bi
l
i
t
y
o
f de
t
e
c
t
i
on ou
t
l
i
e
r
is
us
e
d for
de
t
e
rm
i
ni
ng
t
h
e
v
a
l
i
di
t
y
of t
h
i
s
m
odi
fi
e
d
c
h
a
rt
.
T
he
fi
ndi
ngs
r
e
ve
a
l
e
d
a
c
ons
i
de
ra
bl
e
s
i
gni
f
i
c
a
nc
e
i
n
i
t
s
pe
rform
a
n
c
e
.
Ke
y
wo
r
d
s
:
Bo
o
t
s
t
r
a
p
H
o
t
e
l
l
i
n
g
’
s
2
ch
ar
t
s
Ma
ha
l
a
n
obi
s
d
i
s
t
a
nc
e
Ro
b
u
s
t
e
s
t
i
m
a
t
o
r
T
r
i
m
m
e
a
n
T
hi
s
i
s
an ope
n
ac
c
e
s
s
ar
t
i
c
l
e
un
de
r
t
he
CC B
Y
-
SA
l
i
c
e
n
s
e.
C
or
r
e
s
po
n
di
n
g
A
u
t
h
or
:
F
i
ra
s
H
a
d
d
a
d
,
C
ol
l
e
ge
of
A
p
pl
i
e
d
S
t
udi
e
s
a
nd
C
o
m
m
uni
t
y
S
e
r
vi
c
e
,
I
m
a
m
A
b
d
u
l
r
a
h
m
a
n
Bi
n
F
a
i
s
a
l
U
n
i
v
e
r
s
i
t
y
,
D
a
m
m
a
m
,
Sa
u
d
i
A
r
a
b
i
a
.
E
m
a
i
l
:
f
s
ha
d
da
d@
i
a
u.
e
du
.
s
a
1.
I
N
T
R
O
D
U
C
T
I
O
N
S
t
a
t
i
s
t
i
c
a
l
p
r
o
c
e
s
s
c
o
n
t
r
o
l
c
h
a
r
t
s
e
m
p
l
o
y
s
t
a
t
i
s
t
i
c
a
l
i
m
p
l
e
m
e
n
t
s
t
o
n
o
t
i
c
e
t
h
e
a
c
c
o
m
p
l
i
s
h
m
e
n
t
o
f
t
he
p
r
o
d
uc
t
i
on
pr
oc
e
s
s
.
D
ur
i
ng t
he
p
r
o
c
e
s
s
of
pr
a
c
t
i
c
i
n
g,
m
o
r
e
t
ha
n
one
q
ua
l
i
t
y f
e
a
t
ur
e
i
s
de
f
i
n
e
d b
y
t
he
o
ve
r
a
l
l
q
ua
l
i
t
y of
a
pr
o
du
c
t
.
T
h
us
,
t
he
q
ua
l
i
t
y
of
a
c
e
r
t
a
i
n t
y
pe
of
a
n
y
p
r
o
d
uc
t
m
a
y
be
de
f
i
ne
d
b
y
de
g
r
e
e
of
ha
r
d
ne
s
s
,
t
hi
c
k
ne
s
s
,
we
i
g
ht
,
w
i
dt
h
a
n
d
l
e
ngt
h
et
c.
S
o
,
v
ar
i
o
u
s
f
eat
u
r
es
o
f
a m
an
u
f
act
u
r
e
d
c
o
m
p
o
n
e
n
t
r
e
q
ui
r
e
s
i
m
ul
t
a
ne
o
us
m
o
ni
t
or
i
ng
.
H
e
nc
e
,
i
t
c
a
n
be
u
s
e
d
b
ot
h;
t
he
m
ul
t
i
va
r
i
a
t
e
S
he
w
ha
r
t
-
t
y
p
e
2
o
r
t
h
e
H
o
t
e
l
l
i
n
g
’
s
2
c
o
nt
r
ol
c
ha
r
t
s
m
i
ght
be
us
e
d.
H
o
t
e
l
l
i
n
g
’
s
2
s
t
a
t
i
s
t
i
c
i
s
o
n
e
o
f
t
h
e
m
o
s
t
p
u
b
l
i
c
m
e
t
h
o
d
s
i
n
t
h
e
m
u
l
t
i
v
a
r
i
a
t
e
s
t
a
t
i
s
t
i
c
a
l
c
o
n
t
r
o
l
c
h
a
rt
s
[1
,
2
].
F
u
rt
h
e
r
m
o
re
,
t
h
e
H
o
t
e
l
l
i
n
g
’s
2
s
t
a
t
i
s
t
i
c
i
s
t
h
e
m
u
l
t
i
v
a
r
i
a
t
e
g
e
n
e
r
a
l
i
z
a
t
i
o
n
o
f
t
h
e
S
t
u
d
e
n
t
’
s
t
-
s
t
a
t
i
s
t
i
c
.
H
e
n
c
e
,
t
h
e
H
o
t
e
l
l
i
n
g
’
s
2
s
t
at
i
s
t
i
c
i
s
t
h
e
ex
p
an
d
e
d
cas
e
af
t
er
t
ak
i
n
g
t
h
e
s
q
u
a
r
e
f
or
t
he
t
w
o
s
i
de
s
of
t
he
e
q
ua
t
i
o
n
of
t
he
S
t
ude
nt
’
s
t
-
s
t
a
t
i
s
t
i
c
.
I
n
o
t
h
e
r
w
o
r
d
s
,
H
o
t
e
l
l
i
n
g
2
s
t
a
t
i
s
t
i
c
i
s
e
q
u
a
l
t
o
.
2
=
(
−
0
)
−
1
(
−
0
)
(
1)
Wh
e
re
a
nd
ar
e
t
h
e
s
am
p
l
e
m
ea
n
v
ect
o
r
a
n
d
t
h
e
p
×
p
co
v
a
r
i
an
ce
m
at
r
i
x
i
n
s
u
cce
s
s
io
n.
S
ev
e
r
al
v
al
u
e
s
am
o
n
g
t
h
e m
eas
u
r
e
m
en
t
s
o
f
t
h
e ch
a
r
act
er
i
s
t
i
cs
m
ak
e t
h
e
t
r
ad
i
t
i
o
n
al
H
o
t
el
l
i
n
g
’
s
2
i
ne
f
f
e
c
t
i
ve
,
a
l
t
ho
u
gh
t
he
H
ot
e
l
l
i
ng’
s
2
co
n
t
r
o
l
c
h
ar
t
s
a
r
e
ef
f
ect
i
v
e a
n
d
a
p
p
r
o
p
r
i
at
e
w
h
e
n
t
h
e
d
at
a a
r
e t
a
k
en
f
r
o
m
n
o
r
m
a
l
d
i
s
t
r
i
b
u
t
i
o
n
.
A
s
a
r
e
s
u
l
t
,
M
o
s
t
a
j
e
r
a
n,
I
r
a
npa
na
h a
n
d
N
oo
r
o
s
s
a
na
i
n
[
3]
p
oi
n
t
e
d
out
t
ha
t
e
m
pl
o
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
E
l
e
c
&
C
om
p
E
n
g
I
S
S
N
:
208
8
-
87
08
M
o
d
i
f
i
e
d
h
o
t
e
l
l
i
n
g
’
s
c
o
nt
r
ol
c
har
t
s
us
i
n
g
m
o
di
f
i
e
d…
(
F
i
r
as
H
ad
d
ad
)
2
85
n
on
-
pa
r
a
m
e
t
r
i
c
b
oot
s
t
r
a
p
c
o
n
t
r
ol
c
ha
r
t
s
f
or
un
k
no
w
n
di
s
t
r
i
but
i
o
n.
W
he
r
e
n
on
-
p
ar
a
m
et
r
i
c b
o
o
t
s
t
r
ap
co
n
t
r
o
l
c
ha
r
t
s
a
r
e
s
ui
t
a
bl
e
w
he
n t
he
e
m
pl
oy
o
f
l
a
r
ge
s
i
z
e
de
e
m
s
i
m
p
os
s
i
bl
e
i
n a
ddi
t
i
o
n t
o
e
va
l
ua
t
e
t
h
e p
r
o
ces
s
p
ar
a
m
et
er
s
f
r
o
m
t
h
e
Ph
a
s
e
I
.
G
e
ne
r
a
l
l
y s
pe
a
ki
ng
,
no
r
m
a
l
di
s
t
r
i
b
ut
i
on
i
s
r
e
q
ui
r
e
d
f
or
c
o
nt
r
ol
c
ha
r
t
s
f
or
pe
r
m
i
t
t
i
ng
o
bs
e
r
va
t
i
o
n.
I
n
r
e
s
pe
c
t
of
c
a
s
e
s
w
i
t
h
no
n
-
n
or
m
a
l
di
s
t
r
i
b
ut
i
on
s
,
t
he
us
a
ge
of
no
n
-
p
ar
a
m
et
r
i
c
c
o
n
t
r
o
l
ch
ar
t
s
co
n
t
ai
n
i
n
g
c
h
ar
t
s
o
f
s
i
g
n
c
o
n
t
r
o
l
w
i
l
l
b
e
a
p
p
l
i
c
a
b
l
e
.
I
t
i
s
w
o
r
t
h
m
e
n
t
i
o
n
i
n
g
t
h
a
t
t
h
e
a
l
g
o
r
i
t
h
m
o
f
n
on
-
p
a
r
a
m
e
t
r
i
c
b
o
o
t
s
t
r
a
p
i
n
t
h
i
s
s
t
u
d
y
i
s
e
m
p
l
o
y
e
d
f
o
r
c
a
l
c
u
l
a
t
i
n
g
t
h
e
c
o
n
t
r
o
l
c
h
a
r
t
p
a
r
a
m
e
t
e
r
s
.
B
y
a
n
d
l
a
r
g
e
,
or
i
gi
na
l
ob
s
e
r
v
a
t
i
ons
m
i
g
ht
b
e
e
m
pl
o
ye
d
i
n
c
a
s
e
s
t
ha
t
d
o
not
e
nt
a
i
l
a
n
y
d
i
s
t
r
i
b
u
t
i
o
n
a
s
s
u
m
p
t
i
o
n
.
S
i
m
i
l
a
r
l
y
,
r
o
b
u
s
t
s
t
a
t
i
s
t
i
c
s
w
e
r
e
e
m
p
l
o
y
e
d
r
a
t
h
e
r
t
h
a
n
s
e
n
s
i
t
i
v
e
s
t
a
t
i
s
t
i
c
s
i
n
t
h
e
H
o
t
e
l
l
i
n
g
2
c
ha
r
t
.
S
uc
h m
e
t
h
ods
w
er
e
r
eg
a
r
d
e
d
ef
f
i
ci
en
t
f
o
r
o
v
e
r
c
o
m
i
n
g
p
o
o
r
p
e
r
f
o
r
m
a
n
ce i
s
s
u
e i
n
t
h
e ex
i
s
t
en
ce o
f
ex
t
r
em
e
v
al
u
es
i
n
pr
o
duc
t
f
e
a
t
u
r
e
s
.
T
he
r
e
a
r
e
s
e
v
e
r
a
l
pr
e
vi
o
us
s
t
udi
e
s
t
ha
t
e
m
pl
o
ye
d
t
hi
s
t
e
c
hni
q
ue
a
nd
t
he
m
a
j
or
i
t
y
of
t
he
m
a
r
e
r
e
n
de
r
e
d i
n t
h
e
a
bo
ve
-
m
e
nt
i
one
d s
t
udi
e
s
r
e
l
a
t
i
ng wi
t
h i
m
p
r
o
vi
n
g t
hi
s
m
o
de
l
,
s
e
e
[
4
]
.
T
he
a
b
ove
m
e
nt
i
one
d
s
t
udi
e
s
t
ha
t
e
m
pl
o
ye
d t
he
bo
ot
s
t
r
a
p s
a
m
pl
e
s
,
t
h
e l
o
cat
i
o
n
,
a
n
d
s
cal
e
es
t
i
m
at
o
r
s
,
t
h
e t
r
i
m
m
e
d
m
e
an
a
n
d
t
he
t
r
i
m
m
e
d c
ova
r
i
a
nc
e
w
e
r
e
m
e
nt
i
o
ne
d.
O
ne
o
f
w
hi
c
h
[
5
]
wh
o
us
e
d
t
he
s
o
-
c
a
l
l
e
d
t
r
i
m
m
e
d
m
e
a
n
a
n
d
t
r
i
m
m
ed
c
o
v
a
r
i
an
ce m
at
r
i
x
as
an
al
t
er
n
at
i
v
e o
f
a
r
i
t
h
m
et
i
c m
ean
a
n
d
c
o
v
ar
i
a
n
ce
m
at
r
i
x
,
r
es
p
e
ct
i
v
el
y
.
Su
r
t
i
ha
di
i
n
[
6
]
e
m
pl
oye
d
m
e
di
a
n
a
s
a
r
o
b
us
t
l
oc
a
t
i
on
e
s
t
i
m
a
t
or
w
he
n
he
c
o
ns
t
r
uc
t
e
d
r
o
bus
t
bi
va
r
i
a
t
e
s
i
g
n
t
e
s
t
s
o
f
Bl
u
m
e
n
a
n
d
H
o
d
g
e
s
.
A
l
f
a
r
o
a
n
d
O
r
t
e
g
a
i
n
[
7
]
s
u
g
g
e
s
t
e
d
a
n
e
w
a
l
t
e
r
n
a
t
i
v
e
c
h
a
r
t
b
y
s
u
b
s
t
i
t
u
t
i
n
g
t
h
e
s
am
p
l
e
m
e
an
v
ect
o
r
w
i
t
h
t
r
i
m
m
ed
m
ea
n
v
ect
o
r
a
n
d
t
h
e
co
v
a
r
i
an
ce
m
at
r
i
x
b
y
t
r
i
m
m
ed
co
v
ar
i
a
n
ce
m
a
t
r
i
x
.
J
on
e
s
i
n
[
8]
u
s
e
d i
n c
ont
r
ol
c
ha
r
t
c
o
ns
t
r
u
c
t
i
ons
,
b
o
ot
s
t
r
a
p
r
a
t
he
r
t
ha
n
t
he
t
r
a
di
t
i
ona
l
pa
r
a
m
e
t
r
i
c
a
s
s
um
pt
i
o
n.
B
oot
s
t
r
a
p
m
e
t
h
o
ds
us
e
c
om
put
i
ng
po
we
r
.
P
ha
l
a
di
ga
no
n
e
t
a
l
.
i
n
[
9]
e
m
pl
o
y
e
d a
bo
ot
s
t
r
a
p
-
b
as
ed
m
u
l
t
i
v
a
r
i
a
t
e
T
2
c
ont
r
ol
i
n t
h
e
i
r
s
t
ud
y a
nd
i
ndi
c
a
t
e
d t
he
c
a
pa
c
i
t
y o
f
t
h
e
c
ha
r
t
i
n
o
bs
e
r
vi
ng a
pr
oc
e
s
s
i
n
n
on
-
n
or
m
a
l
or
un
k
no
w
n
di
s
t
r
i
but
i
o
n
o
f
da
t
a
.
T
he
a
ut
h
o
r
us
e
s
a
s
i
m
ul
a
t
i
o
n
s
t
ud
y t
o a
s
s
e
s
s
t
he
pe
r
f
or
m
a
n
c
e
o
f
t
h
e
c
o
n
t
r
o
l
c
h
a
r
t
.
T
he
m
e
t
h
o
d
pr
o
vi
de
d i
n
[
10
]
de
pe
nde
d
o
n
t
he
n
ot
i
o
n
o
f
b
oot
s
t
r
a
ppi
ng
.
F
o
r
t
h
i
s
o
bj
e
c
t
i
ve
,
t
he
a
ut
h
o
r
s
b
o
ot
s
t
r
a
p
pe
d t
he
da
t
a
,
a
n
d t
he
n
s
uc
h da
t
a
w
e
r
e
a
ppl
i
e
d
o
n i
n
-
c
ont
r
ol
s
t
a
t
e
e
s
t
i
m
a
t
i
on.
T
he
us
a
ge
of
a
n
on
-
pa
r
a
m
e
t
r
i
c
a
pp
r
oa
c
h
de
m
o
ns
t
r
a
t
e
d i
n
[
1
1
]
i
n c
o
nd
u
c
t
i
n
g
e
s
t
i
m
a
t
i
o
n
o
n
t
h
e
c
u
m
u
l
a
t
i
v
e
s
u
m
(
C
u
s
um
)
as
w
el
l
as
t
h
e
e
xp
o
ne
nt
i
a
l
l
y we
i
g
ht
e
d m
o
vi
ng
a
ve
r
a
ge
(
E
WMA
)
c
o
nt
r
ol
l
i
m
i
t
s
on a
gi
v
e
n
da
t
a
s
e
t
.
T
he
us
a
ge
o
f
a
n
i
n
n
o
v
a
t
i
v
e
b
o
o
t
s
t
r
a
p
a
l
g
o
r
i
t
h
m
w
a
s
r
e
v
e
a
l
e
d
i
n
[
1
2
]
i
n
t
h
e
H
o
t
e
l
l
i
n
g
’
s
T
2
c
o
n
t
r
o
l
c
h
a
r
t
c
r
e
a
t
i
o
n
.
A
p
pl
yi
ng
no
n
p
a
r
a
m
e
t
r
i
c
b
oot
s
t
r
a
p
m
ul
t
i
va
r
i
a
t
e
c
o
nt
r
ol
c
ha
r
t
s
|
S
|
,
W
,
a
nd
G
de
pe
n
ds
o
n
bo
ot
s
t
r
a
ppe
d
d
a
t
a
u
t
i
l
i
z
a
t
i
o
n
i
n
e
v
a
l
u
a
t
i
n
g
t
h
e
i
n
c
o
n
t
r
o
l
s
t
a
t
e
t
h
a
t
w
a
s
d
i
s
c
u
s
s
e
d
i
n
[
3
]
.
T
h
e
f
i
n
d
i
n
g
s
r
e
v
e
a
l
t
h
a
t
t
h
e
bo
ot
s
t
r
a
p
c
ont
r
ol
c
ha
r
t
s
a
c
hi
e
ve
d
r
e
a
s
o
na
bl
e
pe
r
f
or
m
a
nc
e
.
S
i
m
i
l
a
r
l
y
,
i
n
[
1
3
]
i
n
d
i
c
a
t
e
d
t
h
e
a
p
p
l
i
c
a
t
i
o
n
o
f
a
b
o
o
t
s
t
r
a
p
m
u
l
t
i
v
a
r
i
a
t
e
c
o
n
t
r
o
l
c
h
a
r
t
f
o
l
l
o
w
i
n
g
H
o
t
e
l
l
i
n
g
’
s
T
2
s
t
a
t
i
s
t
i
c
.
T
he
a
ut
h
or
i
n
[
1
4
]
m
o
d
i
f
i
e
d
t
h
r
e
e
r
o
b
u
s
t
H
o
t
e
l
l
i
n
g
’
s
T
2
c
h
ar
t
s
b
y
r
ep
l
aci
n
g
t
h
e
m
ean
ve
c
t
o
r
a
nd
t
he
c
o
va
r
i
a
nc
e
m
a
t
r
i
x
by
t
he
t
r
i
m
m
e
d e
s
t
i
m
a
t
or
s
.
T
he
t
r
i
m
m
i
ng
w
a
s
do
n
e
us
i
ng
t
he
m
odi
f
i
e
d
Ma
ha
l
a
n
obi
s
d
i
s
t
an
ce,
w
h
e
r
e
t
h
e l
o
cat
i
o
n
es
t
i
m
at
o
r
i
s
t
h
e
m
ed
i
an
a
n
d
t
h
e s
cal
e es
t
i
m
at
o
r
i
s
o
n
e
o
f
t
h
e
r
o
b
u
s
t
s
cal
e
es
t
i
m
at
o
r
s
MA
D
n
,
S
n
an
d
n
.
T
u
ke
y a
nd
M
c
L
a
u
ghl
i
n i
n [
1
5]
pr
o
po
s
e
d
ne
w
s
u
bs
t
i
t
ut
e
B
i
va
r
i
a
t
e
r
o
bus
t
H
ot
e
l
l
i
n
g
'
s
T
2
ch
ar
t
.
B
y E
xc
ha
n
ge
d t
he
a
r
i
t
h
m
e
t
i
c
m
e
a
n
w
i
t
h
w
i
n
s
o
r
i
z
e
d
m
o
d
i
f
i
e
d
o
n
e
s
t
e
p
M
-
e
s
t
i
m
a
t
o
r
(
w
MO
M
)
v
ect
o
r
a
n
d
s
u
b
s
t
i
t
u
t
e
d
t
h
e
s
e
n
s
i
t
i
v
e
c
o
v
a
r
i
a
n
c
e
m
a
t
r
i
x
w
i
t
h
t
h
e
c
o
v
a
r
i
a
n
c
e
m
a
t
r
i
x
o
f
r
o
b
u
s
t
s
c
a
l
e
e
s
t
i
m
a
t
o
r
n
r
es
p
ect
i
v
el
y
.
T
he
c
ur
r
e
nt
s
t
ud
y a
i
m
s
a
t
e
n
ha
nc
i
ng
H
ot
e
l
l
i
ng
’
s
2
T
c
h
a
r
t i
n
t
e
r
m
s
of
its
f
unc
tio
n
ing
.
T
hu
s
,
a
nov
e
l
m
e
t
h
o
d
w
a
s
s
u
g
g
e
s
t
e
d
,
w
h
i
c
h
c
o
n
t
a
i
n
s
m
o
d
i
f
i
c
a
t
i
o
n
t
o
t
h
e
s
e
n
s
i
t
i
v
i
t
i
e
s
t
o
w
a
r
d
s
o
u
t
l
i
e
r
s
.
T
h
e
r
e
a
r
e
a
w
i
d
e
s
pr
e
a
d
c
hoi
c
e
of
r
o
b
us
t
l
oc
a
t
i
on
a
n
d
s
c
a
l
e
e
s
t
i
m
a
t
or
s
t
ha
t
m
i
ght
be
r
e
ga
r
de
d
i
n
t
hi
s
i
s
s
ue
.
T
h
i
s
r
es
ea
r
c
h
s
eek
s
t
o
de
ve
l
op
t
he
f
unc
t
i
o
n
o
f
H
ot
e
l
l
i
ng
T
2
c
h
a
r
t
b
y
r
e
p
l
aci
n
g
t
h
e
m
ea
n
v
ect
o
r
an
d
t
h
e
co
v
ar
i
an
ce
m
at
r
i
x
w
i
t
h
tr
im
m
e
d m
e
a
n a
nd its
c
o
r
r
e
s
p
ond
ing
c
ov
a
r
ia
n
c
e
m
a
tr
ix f
o
llo
w
i
n
g
[
5]
.
T
h
e
tr
im
m
e
d
m
e
a
n ba
s
e
d
on
r
o
bu
s
t
s
cal
e es
t
i
m
at
o
r
Qn
.
T
o
a
ppr
a
i
s
e
t
he
f
u
nc
t
i
on
of
t
he
n
e
w m
o
di
f
i
e
d
r
o
b
us
t
H
ot
e
l
l
i
ng
T
2
c
o
n
t
r
o
l
c
h
a
r
t
,
t
he
o
ut
l
i
e
r
s
a
r
e
i
ns
e
r
t
e
d i
n t
he
da
t
a
,
w
hi
c
h a
r
e
c
om
i
ng
f
r
om
t
he
s
t
a
nda
r
d n
or
m
a
l
di
s
t
r
i
b
ut
i
on
b
y
us
i
n
g
b
o
o
t
s
t
r
a
p
m
et
h
o
d
i
n
g
e
n
er
at
i
n
g
t
h
e
s
am
p
l
es
,
t
h
en
cal
c
u
l
at
e
t
h
e
f
al
s
e
al
ar
m
s
an
d
t
h
e
p
r
o
b
a
b
i
l
i
t
y
o
f
d
e
t
e
c
t
i
o
n
o
f
out
l
i
e
r
s
a
s
a
t
e
c
hni
que
t
o
j
u
d
ge
t
he
f
u
nc
t
i
on
o
f
t
he
m
odi
f
i
e
d c
ha
r
t
.
T
h
e
f
o
l
l
o
w
i
n
g
s
e
c
t
i
o
n
(
s
ect
i
o
n
2
)
p
r
es
en
t
s
t
h
e
d
e
t
a
i
l
s
o
f
t
h
e
r
e
s
e
a
r
c
h
m
e
t
h
o
d
s
.
A
f
t
e
r
t
h
a
t
,
s
e
c
t
i
o
n
3
p
r
e
s
e
n
t
s
t
h
e
r
e
s
u
l
t
s
a
n
d
d
i
s
c
u
s
s
i
o
n
.
f
o
l
l
o
w
e
d
b
y
t
h
e
c
o
n
c
l
u
s
i
o
n
i
n
s
e
c
t
i
o
n
4
.
2.
R
ES
EA
R
C
H
M
ETH
O
D
2.
1.
Tr
i
m
m
i
n
g
m
et
h
o
d
T
he
c
o
va
r
i
a
nc
e
m
a
t
r
i
x i
s
i
n
f
l
ue
nc
e
d
by
t
he
e
m
e
r
ge
nc
e
o
f
t
he
o
ut
l
i
e
r
s
.
As
a
r
e
s
ul
t
,
we
us
e
d
t
h
e
t
r
i
m
m
ed
v
ar
i
an
ce
-
co
v
ar
i
an
ce
m
at
r
i
x
as
an
e
x
ch
a
n
g
e
f
o
r
t
h
e
co
v
a
r
i
an
ce m
at
r
i
x
.
T
h
e
co
m
p
u
t
at
i
o
n
o
f
s
u
c
h
an
es
t
i
m
at
o
r
i
s
b
as
ed
o
n
t
h
e
w
i
n
s
o
r
i
ze
d
co
v
ar
i
an
ce m
at
r
i
x
.
S
o
,
t
h
e w
i
n
s
o
r
i
zed
v
ar
i
an
c
e
-
co
v
a
r
i
an
ce m
at
r
i
x
i
s
u
s
e
d
t
o
cal
c
u
l
at
e
t
h
e
co
v
ar
i
a
n
ce
m
at
r
i
x
f
o
r
t
he
wi
ns
or
i
z
e
d
s
a
m
pl
e
.
I
n
o
r
d
e
r
t
o
pr
o
duc
e
t
he
m
o
di
f
i
e
d
H
ot
e
l
l
i
ng
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
SN
:
2
088
-
87
08
I
nt
J
E
l
e
c
&
C
om
p
E
n
g,
V
o
l
.
11
,
No
.
1,
F
e
b
r
ua
r
y
2
02
1
:
284
-
2
92
2
86
2
c
ont
r
ol
c
ha
r
t
s
i
t
ha
s
be
e
n
us
e
d t
he
r
o
b
us
t
l
o
c
a
t
i
on e
s
t
i
m
a
t
o
r
t
he
t
r
i
m
m
e
d
m
e
a
n a
nd t
he
t
r
i
m
m
e
d va
r
i
a
n
c
e
-
c
ova
r
i
a
nc
e
m
a
t
r
i
x.
T
he
t
r
i
m
m
i
ng
of
t
he
o
ut
l
i
e
r
s
da
t
a
a
r
e
p
r
od
uc
e
d b
y i
m
p
l
e
m
e
nt
i
n
g
t
he
m
e
t
ho
d of
m
o
di
f
i
e
d
Ma
ha
l
a
n
obi
s
di
s
t
a
nc
e
,
s
uc
h
a
s
t
he
m
o
di
f
i
c
a
t
i
on a
p
p
r
o
v
e
d
out
b
y r
e
p
l
a
c
i
ng t
he
s
a
m
pl
e
m
e
a
n
ve
c
t
or
i
n
t
he
M
a
ha
l
a
no
bi
s
di
s
t
a
nc
e
f
or
m
ul
a
b
y t
h
e
m
e
di
a
n
ve
c
t
or
a
n
d r
e
pl
a
c
i
ng
va
r
i
a
nc
e
-
co
v
a
r
i
an
ce
m
at
r
i
x
,
by
t
he
r
o
bus
t
s
c
a
l
e
va
r
i
a
nc
e
-
c
ova
r
i
a
n
ce
m
a
t
r
i
ces
o
f
Q
n
[
16
]
.
T
he
t
r
i
m
m
i
ng
a
nd
r
e
pl
a
c
e
m
e
nt
of
t
he
da
t
a
t
o
obt
a
i
n
t
h
e
w
i
n
s
or
i
z
e
d s
a
m
pl
e
a
r
e
a
c
hi
e
ve
d by
e
m
pl
o
yi
n
g
t
he
va
l
ue
s
of
m
o
di
f
i
e
d
Ma
h
a
l
on
obi
s
di
s
t
a
n
c
e
t
ha
t
t
he
t
r
i
m
m
i
n
g
de
pe
n
de
nt
on
t
he
pe
r
c
e
nt
a
ge
20
%
f
r
om
e
a
c
h e
n
d.
T
he
na
t
ur
a
l
wa
y
o
f
M
a
h
a
l
a
n
o
b
i
s
d
i
s
t
an
ce.
I
n t
he
s
t
udi
e
s
of
[
5,
1
7
]
,
e
ach
en
d
f
r
o
m
o
u
t
l
i
er
o
b
s
e
r
v
at
i
o
n
w
as
t
r
i
m
m
ed
t
h
e
d
at
a t
h
at
ar
e p
r
o
v
i
d
ed
b
y
t
he
l
a
r
ge
s
t
t
w
o va
l
ue
s
of
M
a
ha
l
a
n
obi
s
di
s
t
a
nc
e
.
Me
a
nw
h
i
l
e
,
t
hi
s
t
e
c
hni
que
i
s
a
p
pr
o
pr
i
a
t
e
f
or
de
a
l
i
n
g wi
t
h
s
ub
g
r
o
u
p obs
e
r
va
t
i
o
ns
,
b
ut
ou
r
c
a
s
e
i
s
c
onc
e
r
ne
d
wi
t
h
t
he
bo
ot
s
t
r
a
p
i
ndi
vi
d
ua
l
o
b
s
e
r
va
t
i
o
ns
.
A
s
s
u
c
h
,
t
he
pe
r
c
e
nt
a
ge
f
o
r
t
r
i
m
m
i
ng
i
s
m
or
e
a
p
pr
o
pr
i
a
t
e
.
T
he
a
ut
ho
r
s
i
n
[
16
]
s
u
gge
s
t
e
d t
ha
t
t
h
e
be
s
t
pe
r
c
e
nt
a
ge
i
s
2
0%
-
2
5%
in a
s
ym
m
e
tr
ic
d
i
s
tr
ib
u
tion
.
T
h
e
a
u
thor
s
in [
18
,
19
]
pr
opo
s
e
d
to tr
im
20%
f
r
om
e
a
c
h
ta
il o
f
t
he
da
t
a
.
T
he
a
ut
h
or
i
n [
1
9]
pr
o
po
s
e
d
t
he
be
s
t
pe
r
c
e
nt
a
ge
t
o t
r
i
m
20
%
f
or
e
a
c
h s
i
de
.
C
o
ns
e
que
nt
l
y,
t
h
e
p
e
r
ce
n
t
ag
e
of
t
r
i
m
m
i
n
g
i
n
t
hi
s
pa
pe
r
f
or
e
a
c
h
e
nd
i
s
20%
.
2.
2.
C
o
n
s
tr
u
c
ti
n
g
c
on
t
r
ol
c
h
ar
t
s
S
u
b
s
t
i
t
u
t
i
n
g
a
r
i
t
h
m
e
t
i
c
m
e
a
n
v
e
c
t
o
r
b
y
t
h
e
al
t
er
n
at
i
v
e r
o
b
u
s
t
l
o
cat
i
o
n
es
t
i
m
at
o
r
,
t
h
e
t
r
i
m
m
ed
m
ea
n
an
d
s
u
b
s
t
i
t
u
t
e
t
h
e s
a
m
p
l
e
v
a
r
i
an
ce c
o
v
a
r
i
an
ce m
at
r
i
x
S
b
y
t
h
e
t
r
i
m
m
e
d
v
ar
i
a
n
ce c
o
v
ar
i
an
ce m
at
r
i
ces
each
o
n
e
o
f
t
h
em
r
el
i
es
o
n
t
h
e r
o
b
u
s
t
s
cal
e
es
t
i
m
at
o
r
.
T
h
e
c
o
m
p
u
t
a
t
i
o
n
o
f
t
h
e
t
r
i
m
m
e
d
c
o
v
a
r
i
a
n
c
e
m
a
t
r
i
x
r
e
q
ui
r
e
s
c
a
l
c
ul
a
t
i
ng t
he
w
i
ns
or
i
z
e
d c
o
va
r
i
a
nc
e
m
a
t
r
i
x be
f
or
e
.
T
he
w
i
ns
or
i
z
e
d va
r
i
a
nc
e
c
ova
r
i
a
nc
e
m
a
t
r
i
x
i
s
t
h
e
v
ar
i
a
n
ce
co
v
ar
i
a
n
ce
m
at
r
i
x
f
o
r
t
h
e
w
i
n
s
o
r
i
zed
s
am
p
l
e.
I
t
s
s
am
p
l
e
i
s
ac
h
i
ev
e
d
b
y
u
s
i
n
g
s
o
m
e
t
ec
h
n
i
q
u
es
t
o
t
r
i
m
t
he
o
ut
l
i
e
r
s
f
r
om
t
he
da
t
a
.
T
he
t
e
c
hni
que
o
f
Ma
ha
l
a
n
obi
s
di
s
t
a
nc
e
i
s
e
m
pl
oye
d i
n s
uc
h
s
t
ud
y.
T
h
e f
o
r
m
u
l
a o
f
M
a
h
al
an
o
b
i
s
d
i
s
t
an
ce r
el
i
es
o
n
t
h
e a
r
i
t
h
m
et
i
c m
ea
n
v
ect
o
r
an
d
t
h
e
v
ar
i
a
n
ce c
o
v
ar
i
an
ce
m
a
t
r
i
x.
T
hi
s
p
a
pe
r
m
o
di
f
i
e
d
t
he
Ma
ha
l
a
n
obi
s
di
s
t
a
nc
e
by
m
o
di
f
yi
n
g
t
he
a
r
i
t
hm
e
t
i
c
m
e
a
n
by t
he
r
o
bu
s
t
l
oc
a
t
i
on
e
s
t
i
m
a
t
or
t
he
m
e
di
a
n a
nd
m
o
di
f
yi
ng
t
he
va
r
i
a
nc
e
c
o
va
r
i
a
nc
e
m
a
t
r
i
x
b
y t
he
c
ova
r
i
a
nc
e
m
a
t
r
i
x
o
f
t
h
e r
o
b
u
s
t
s
cal
e es
t
i
m
at
o
r
s
[
2
0
]
.
I
n
r
es
p
ect
t
o
t
h
e t
y
p
e
o
f
r
o
b
u
s
t
s
cal
e es
t
i
m
at
o
r
t
h
e
w
i
n
s
o
r
i
zed
s
am
p
l
e i
s
a
c
hi
e
ve
d.
T
h
u
s
,
t
he
t
y
pe
o
f
w
i
ns
or
i
z
e
d
s
a
m
pl
e
i
s
f
or
m
e
d.
W
i
t
h r
e
ga
r
d t
o s
uc
h
w
i
n
s
o
r
i
z
e
d
s
a
m
pl
e
,
o
n
e
t
r
i
m
m
ed
m
ean
h
a
s
b
ee
n
cal
c
u
l
at
ed
X
tQ
n
an
d
o
n
e
t
r
i
m
m
ed
v
ar
i
a
n
ce
co
v
ar
i
a
n
ce m
at
r
i
x
,
ha
d be
e
n
c
a
l
c
u
l
a
t
e
d
.
Ba
s
e
d
o
n
t
h
i
s
t
y
p
e
o
f
w
i
n
s
o
r
i
z
e
d
s
a
m
p
l
e
,
t
h
e
M
o
d
i
f
i
e
d
H
o
t
e
l
l
i
n
g
’
s
2
c
o
n
t
r
o
l
c
h
a
r
t
i
s
s
t
r
u
c
t
u
r
e
d
a
s
f
o
l
l
o
w
s
:
−
D
e
f
i
ni
n
g
t
he
a
dj
us
t
e
d Ma
h
a
l
a
no
bi
s
di
s
t
a
nc
e
va
l
ue
s
∆
f
o
r
eac
h
v
ect
o
r
X
i1
,
…
.
.
,
X
ip
i
n
t
h
e
i
n
d
i
v
i
d
u
a
l
bo
ot
s
t
r
a
p
da
t
a
gr
o
ups
,
w
he
r
e
i
=
1
,
…
,
n
,
a
nd
p
n
u
m
b
er
o
f
v
ar
i
ab
l
es
.
−
O
r
ga
ni
z
i
ng
t
he
va
l
ue
s
of
m
od
i
f
i
e
d
Ma
ha
l
a
no
bi
s
di
s
t
a
nc
e
o
r
de
r
l
y
a
n
d
a
c
c
o
r
di
ng
t
o
[
1
6
]
w
ho
s
t
a
t
e
d
t
ha
t
t
he
be
s
t
pe
r
c
e
nt
a
g
e
of
t
r
i
m
m
i
n
g
i
s
20%
-
2
5
%
f
r
o
m
eac
h
e
n
d i
n s
y
m
m
e
t
r
i
c
d
i
s
t
r
i
but
i
o
n.
T
h
e
a
ut
h
or
s
[
18
,
19
]
pr
o
pos
e
d
t
r
i
m
m
i
ng
2
0%
f
r
o
m
e
a
c
h
t
a
i
l
of
t
he
da
t
a
.
T
h
us
,
we
e
m
pl
o
ye
d
t
he
40
%
a
s
a
t
r
i
m
m
i
n
g
pe
r
c
e
nt
a
ge
.
−
T
r
i
m
m
i
n
g
t
h
e
l
a
r
g
e
s
t
4
0
%
o
f
t
h
e
v
a
l
u
e
s
o
f
m
o
d
i
f
i
e
d
M
a
h
a
l
a
n
o
b
i
s
d
i
s
t
a
n
c
e
∆
2
.
Ac
c
or
di
n
g
t
o t
he
s
e
v
al
u
es
of
Ma
ha
l
a
n
o
bi
s
di
s
t
a
nc
e
,
t
r
i
m
m
i
ng
t
he
o
bs
e
r
va
t
i
on
s
i
n t
he
da
t
a
t
ha
t
a
r
e
m
a
ni
f
e
s
t
e
d
b
y
4
0 %
of
t
he
l
a
r
g
e
s
t
va
l
ue
s
o
f
m
o
di
f
i
e
d
Ma
ha
l
a
n
o
bi
s
di
s
t
a
nc
e
∆
2
.
−
F
o
r
t
h
e
p
u
r
p
o
s
e
o
f
c
r
e
a
t
i
n
g
t
h
e
w
i
n
s
o
r
i
z
e
d
s
a
m
p
l
e
,
s
u
b
s
t
i
t
u
t
e
t
h
e
t
r
i
m
m
e
d
o
b
s
e
r
v
a
t
i
o
n
s
b
y
o
t
h
e
r
ob
s
e
r
va
t
i
on
s
a
r
e
m
a
ni
f
e
s
t
e
d
b
y
t
he
ne
xt
40
%
o
f
t
he
va
l
ue
s
o
f
m
o
di
f
i
e
d
Ma
ha
l
a
n
obi
s
di
s
t
a
nc
e
∆
2
.
−
D
e
f
i
ni
n
g
t
he
t
r
i
m
m
e
d
m
e
a
n
f
or
e
a
c
h
b
oot
s
t
r
a
p
da
t
a
s
e
t
of
t
he
i
ndi
vi
d
ua
l
o
bs
e
r
va
t
i
o
ns
b
y
s
pl
i
t
t
i
ng
t
he
t
ot
a
l
of
t
he
r
e
m
a
i
n
i
ng
i
n
di
vi
dua
l
o
bs
e
r
va
t
i
ons
b
y
(
n
-
k
)
,
wh
e
r
e
k
s
ym
bols
to
th
e
n
um
b
e
r
of
t
r
im
m
in
g
obs
e
r
va
t
i
on
s
b
e
c
a
us
e
o
nl
y
o
n
e
b
oot
s
t
r
a
p
da
t
a
s
e
t
,
f
ol
l
o
we
d
by
o
ne
va
l
ue
o
f
t
r
i
m
m
e
d
m
e
a
n
.
−
D
ef
i
n
i
n
g
t
h
e
w
i
n
s
o
r
i
zed
c
o
v
a
r
i
an
ce m
at
r
i
x
by
us
i
ng t
he
w
i
ns
o
r
i
z
e
d s
a
m
p
l
e
a
c
c
or
di
n
g t
o
t
he
us
e
o
f
t
h
e
r
o
b
u
s
t
s
c
a
l
e
e
s
t
i
m
a
t
o
r
s
,
.
−
P
i
n
p
o
i
n
t
i
n
g
t
h
e
t
r
i
m
m
e
d
v
a
r
i
a
n
c
e
c
o
v
a
r
i
a
n
c
e
m
a
t
r
i
x
f
or
t
h
e
i
ndi
vi
dua
l
bo
ot
s
t
r
a
p
da
t
a
s
e
t
by a
p
pl
yi
n
g
t
h
e
fo
rm
u
l
a
[1
7
]:
=
−
1
−
1
×
(
2)
w
h
e
re
i
s
t
h
e
w
i
n
s
o
r
i
zed
co
v
a
r
i
an
ce
m
at
r
i
x
,
n
t
i
s
t
h
e
n
u
m
b
e
r
o
f
t
h
e
r
e
s
t
d
a
t
a
a
f
t
e
r
t
r
i
m
m
i
n
g
.
T
he
di
a
go
na
l
c
o
m
p
o
ne
nt
s
i
n t
he
a
bo
ve
m
e
nt
i
one
d
t
r
i
m
m
e
d
va
r
i
a
n
c
e
c
o
va
r
i
a
nc
e
m
a
t
r
i
x a
r
e
t
h
e
s
a
m
p
l
e
-
t
r
i
m
m
e
d
v
a
r
i
an
ce
w
h
er
e
=
2
an
d
t
h
e
o
t
h
e
r
el
em
en
t
s
a
r
e
t
h
e
s
a
m
p
l
e
t
r
i
m
m
e
d
co
v
a
r
i
an
ce
m
at
r
i
x
o
f
t
h
e
t
w
o
v
ect
o
r
s
,
,
a
n
d
is
c
om
pu
te
d
a
s
f
o
llow
s
:
a)
C
om
put
e
t
X
j
,
t
X
g
;
j
=
1
,
…
,
p
,
g
=
1
,
…
,
p
a
n
d
,
≠
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
E
l
e
c
&
C
om
p
E
n
g
I
S
S
N
:
208
8
-
87
08
M
o
d
i
f
i
e
d
h
o
t
e
l
l
i
n
g
’
s
c
o
nt
r
ol
c
har
t
s
us
i
n
g
m
o
di
f
i
e
d…
(
F
i
r
as
H
ad
d
ad
)
2
87
b)
C
o
m
p
u
t
e
t
h
e
s
p
ear
m
an
r
an
k
co
r
r
el
at
i
o
n
b
et
w
een
a
nd
,
de
not
e
d b
y c
or
r
(
,
)
b
ecau
s
e t
h
i
s
t
ype
o
f
c
or
r
e
l
a
t
i
on
i
s
r
ob
us
t
a
g
a
i
ns
t
t
he
e
xt
r
e
m
e
da
t
a
[
21
]
.
c)
T
h
e s
a
m
p
l
e
c
o
v
a
r
i
an
ce
b
et
w
een
t
h
e
v
a
r
i
ab
l
es
a
n
d
i
s
c
om
put
e
d a
c
c
or
di
n
g t
o t
he
f
ol
l
o
w
i
n
g
fo
rm
u
l
a
:
=
,
=
(
)
(
)
(
,
)
(
3)
−
C
om
put
e
t
he
o
pp
os
i
t
e
of
t
he
s
a
m
pl
e
t
r
i
m
m
e
d s
t
a
nda
r
d
c
ov
a
r
i
a
nc
e
m
a
t
r
i
x
f
or
,
,
w
h
i
c
h
i
s
m
a
n
i
f
e
s
t
e
d
b
y
−
1
.
−
D
e
f
i
n
i
n
g
t
h
e
m
o
d
i
f
i
e
d
H
o
t
e
l
l
i
n
g
’
s
2
c
ont
r
ol
c
ha
r
t
by
s
ubs
t
i
t
ut
i
ng t
he
s
a
m
pl
e
m
e
a
n
i
n
t
he
t
r
a
di
t
i
o
na
l
H
o
t
e
l
l
i
n
g
’
s
2
c
ont
r
ol
c
ha
r
t
b
y
t
he
r
ob
u
s
t
l
o
c
a
t
i
o
n
e
s
t
i
m
a
t
o
r
s
,
,
a
n
d
s
u
b
s
t
i
t
u
t
e
t
h
e
o
p
p
o
s
i
t
e
o
f
t
h
e
s
a
m
p
l
e
s
t
a
n
d
a
r
d
c
o
v
a
r
i
a
n
c
e
m
a
t
r
i
x
i
n
t
h
e
t
r
a
d
i
t
i
o
n
a
l
H
o
t
e
l
l
i
n
g
’
s
2
c
ont
r
ol
c
ha
r
t
by
t
he
op
p
os
i
t
e
r
o
b
u
s
t
s
cal
e c
o
v
ar
i
a
n
ce m
at
r
i
ces
S
t
Qn
−
1
.
A
f
t
e
r
t
h
a
t
,
t
h
e
m
o
d
i
f
i
e
d
H
o
t
e
l
l
i
n
g
’
s
T
2
c
ont
r
ol
c
ha
r
t
a
n
c
ho
r
e
d
o
n
t
h
i
s
f
o
r
m
:
T
t
Qn
2
(
X
i
)
=
(
X
i
−
X
t
Qn
)
T
S
t
Qn
−
1
(
X
i
−
X
t
Qn
)
(
4)
2.
3.
I
nde
pe
n
de
n
t
a
nd
de
pe
nde
nt
var
i
ab
l
e
s
T
h
is
s
tudy
touc
h
e
d up
on t
he
i
nde
pe
nde
nt
a
nd
de
pe
nde
nt
c
a
s
e
s
w
hi
c
h a
r
e
a
c
q
ui
r
e
d
b
y
C
a
s
e
A
an
d
Ca
s
e
B r
e
s
p
e
c
t
i
v
e
l
y
.
T
he
f
ol
l
ow
i
ng
f
o
r
m
ul
a
s
c
l
a
r
i
f
y
t
h
e
c
o
nt
a
m
i
na
t
i
on
m
o
de
l
of
t
he
m
i
xt
u
r
e
n
or
m
a
l
d
i
s
t
r
i
b
u
t
i
o
n
:
(1
-
ε)
N
p
(
µ
0
,
Σ
0
)
+
ε
N
p
(
µ
1
,
Σ
1
)
(
5)
T
o
i
l
l
u
s
t
r
a
t
e
,
ε
i
s
t
h
e
p
er
ce
n
t
ag
e o
f
t
h
e
o
u
t
l
i
e
r
s
.
N
p
(
µ
0
,
Σ
0
)
i
s
t
h
e
i
n
c
o
n
t
r
o
l
d
i
s
t
r
i
b
u
t
i
o
n
a
n
d
t
h
e p
ar
am
et
er
s
µ
0
,
Σ
0
a
r
e
c
a
l
l
e
d
i
n
c
o
n
t
r
o
l
p
a
r
a
m
e
t
e
r
s
.
M
e
a
n
w
h
i
l
e
,
t
h
e
d
i
s
t
r
i
b
u
t
i
o
n
N
p
(
µ
1
,
Σ
1
)
i
s
t
h
e
o
u
t
o
f
c
ont
r
ol
di
s
t
r
i
b
ut
i
on
a
nd
t
he
pa
r
a
m
e
t
e
r
s
µ
1
,
Σ
1
ar
e
cal
l
ed
o
u
t
o
f
co
n
t
r
o
l
p
a
r
am
et
er
s
.
T
w
o
cas
es
o
f
t
he
va
r
i
a
bl
e
s
s
ha
l
l
be
t
a
ke
n
w
he
n s
uc
h
va
r
i
a
bl
e
s
a
r
e
ou
g
ht
t
o
be
i
nde
pe
nde
nt
a
n
d
c
a
l
l
e
d (
A
)
w
hi
l
e
t
he
de
pe
nde
nt
va
r
i
a
bl
e
s
a
r
e
c
a
l
l
e
d
a
s
(
B
)
.
T
h
e
f
o
l
l
o
w
i
n
g
f
o
r
m
u
l
a
c
l
a
r
i
f
y
t
h
a
t
.
2.
3.
1.
C
a
s
e
(
A
)
:
(1
-
ε)
N
p
0
,
I
p
+
ε
N
p
(
µ
1
,
I
P
)
(
6)
W
i
t
h
o
u
t
l
o
s
s
o
f
g
e
n
e
r
a
l
i
t
y
,
t
h
e
i
n
c
o
n
t
r
o
l
m
e
a
n
s
v
e
c
t
o
r
µ
0
i
s
0,
w
hi
l
e
t
he
va
r
i
a
nc
e
c
ova
r
i
a
nc
e
m
a
t
r
i
x
i
n
t
he
i
n
c
ont
r
ol
a
nd
o
ut
of
c
ont
r
ol
d
i
s
t
r
i
b
u
t
i
o
n
s
i
s
e
q
u
a
l
t
o
t
h
e
I
d
e
n
t
i
t
y
m
a
t
r
i
x
.
T
he
a
ut
h
or
s
i
n
[
2
2,
23
]
i
n
di
c
a
t
e
s
t
ha
t
t
h
e
v
ar
i
an
c
e c
o
v
a
r
i
an
ce
m
at
r
i
x
i
s
r
eg
a
r
d
ed
as
a h
o
m
o
g
en
o
u
s
v
a
r
i
an
ce
co
v
ar
i
a
n
ce
m
at
r
i
x
w
i
t
h
1
f
o
r
t
he
m
a
i
n
di
a
go
na
l
a
n
d
0
f
or
t
he
ot
h
e
r
e
l
e
m
e
nt
s
i
n t
he
m
a
t
r
i
x t
ha
t c
o
n
s
i
d
e
r
s
t
h
a
t
w
itho
u
t
c
or
r
e
la
tion a
m
on
g
t
he
va
r
i
a
bl
e
s
.
Ho
we
ve
r
,
a
s
t
he
va
l
ue
of
t
h
e
o
ut
o
f
c
ont
r
ol
pa
r
a
m
e
t
e
r
µ
de
pe
n
ds
o
n
t
he
no
n
-
cen
t
r
a
l
i
t
y
p
ar
a
m
et
er
as
f
o
l
l
o
w
s
:
(
µ
1
−
µ
)
′
Σ
−
1
(
µ
1
−
µ
)
(
7)
w
h
er
e
µ
a v
ect
o
r
i
s
m
a
n
i
f
e
s
t
i
n
g
t
he
a
m
o
u
nt
o
f
t
he
s
hi
f
t
f
o
r
t
he
m
e
a
n
ve
c
t
o
r
.
T
he
l
a
r
ge
r
va
l
ue
of
th
e
non
-
c
e
nt
r
a
l
i
t
y pa
r
a
m
e
t
e
r
s
t
a
nds
f
or
l
a
r
ge
r
e
xt
r
e
m
e
o
ut
l
i
e
r
s
.
A
s
s
uc
h,
a
c
c
or
di
n
g t
o m
a
ny
s
t
a
t
i
s
t
i
c
i
a
ns
s
uc
h
a
s
[
7,
2
4,
2
5]
t
he
y t
o
ok
t
he
f
ol
l
o
w
i
n
g
va
l
u
e
s
f
or
t
he
n
on
-
cen
t
r
al
i
t
y
p
a
r
am
et
er
µ
l
i
k
e
0
(
w
h
e
n
t
h
e
r
e
i
s
n
o
a
l
t
e
r
a
t
i
o
n
)
,
3
a
n
d
5
f
o
r
o
b
t
a
i
n
i
n
g
m
o
r
e
e
x
t
r
e
m
e
o
u
t
l
i
e
r
s
.
2.
3.
2.
C
a
s
e
(
B
):
(1
-
ε)
N
p
(
0
,
Σ
0
)
+
ε
N
p
(
µ
1
,
Σ
0
)
(
8)
I
n
c
o
n
t
r
o
l
p
a
r
a
m
e
t
e
r
,
w
i
t
h
o
u
t
l
o
s
s
i
n
g
e
n
e
r
a
l
i
t
y
,
s
t
a
n
d
s
f
o
r
v
e
c
t
o
r
µ
0
i
s
eq
u
al
t
o
0
w
h
i
l
e
t
h
e
v
ar
i
an
ce
c
ova
r
i
a
nc
e
m
a
t
r
i
x f
or
t
he
i
n
c
ont
r
ol
a
nd
o
u
t
of
c
ont
r
ol
di
s
t
r
i
but
i
o
ns
a
r
e
e
qui
va
l
e
nt
(
i
.
e
.
0
=
1
=
0
).
0
i
s
a
h
om
oge
n
ou
s
va
r
i
a
nc
e
c
ova
r
i
a
nc
e
m
a
t
r
i
x
of
s
i
z
e
×
w
i
t
h
hi
g
h l
e
ve
l
of
c
o
r
r
e
l
a
t
i
on be
t
we
e
n t
he
va
r
i
a
bl
e
s
.
F
or
e
xa
m
pl
e
,
t
he
c
om
po
ne
nt
s
o
f
t
he
m
a
i
n
di
a
go
na
l
i
n
0
a
r
e
1 a
n
d t
he
ot
he
r
e
l
e
m
e
nt
s
a
r
e
0
.
9
[
2
3,
26
]
.
H
o
we
v
e
r
,
t
he
out
o
f
c
ont
r
ol
pa
r
a
m
e
t
e
r
µ
1
r
e
c
e
i
ve
s
t
he
va
l
ue
s
0
(
w
i
t
ho
ut
a
l
t
e
r
a
t
i
on
)
a
n
d
5
(
w
he
n t
he
r
e
a
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
SN
:
2
088
-
87
08
I
nt
J
E
l
e
c
&
C
om
p
E
n
g,
V
o
l
.
11
,
No
.
1,
F
e
b
r
ua
r
y
2
02
1
:
284
-
2
92
2
88
a
go
o
d l
e
ve
r
a
g
e
poi
nt
s
)
.
S
uc
h c
a
s
e
wa
s
r
e
g
a
r
de
d f
or
j
ud
g
i
ng t
he
pe
r
f
or
m
a
nc
e
of
m
o
d
i
f
i
e
d H
ot
e
l
l
i
ng
’
s
2
s
t
a
t
i
s
t
i
c
s
c
onc
e
r
ni
ng
de
pe
nd
e
nt
v
a
r
i
a
bl
e
s
o
r
w
he
n t
h
e
r
e
i
s
c
o
r
r
e
l
a
t
i
o
n a
m
o
ng
t
he
va
r
i
a
bl
e
s
.
T
he
va
l
ue
s
o
f
t
he
pe
r
c
e
nt
a
g
e
s
of
o
ut
l
i
e
r
s
ε
a
r
e
0
.
1
,
a
nd
0.
2.
L
i
k
e
w
i
s
e
,
Hol
m
e
s
a
n
d
Me
r
ge
n
i
n
[
2
7]
w
h
e
ne
ve
r
t
h
e
H
o
t
e
l
l
i
n
g
’
s
2
s
t
a
t
i
s
t
i
c
s
i
s
o
u
t
o
f
c
o
n
t
r
o
l
,
t
h
i
s
c
l
a
r
i
f
i
e
s
t
h
a
t
t
h
e
c
o
r
r
e
l
a
t
i
o
n
a
m
o
n
g
t
h
e
v
a
r
i
a
b
l
e
s
h
a
s
c
ha
n
ge
d.
I
n
c
a
s
e
(
B
)
t
he
r
e
i
s
a
hi
g
h c
o
r
r
e
l
a
t
i
on
be
t
w
e
e
n
t
he
va
r
i
a
bl
e
s
,
d
u
r
i
ng
t
ha
t
,
i
t
c
a
n
be
m
e
a
s
ur
e
d
w
he
t
he
r
t
he
a
l
t
e
r
a
t
i
o
n i
n t
he
c
or
r
e
l
a
t
i
on
be
t
we
e
n t
h
e
va
r
i
a
bl
e
s
i
m
pa
c
t
on
t
he
va
l
ue
s
o
f
t
he
pr
ob
a
bi
l
i
t
y o
f
T
y
pe
I
e
r
r
o
r
a
n
d
t
h
e
p
r
o
b
a
b
i
l
i
t
y
o
f
d
e
t
e
c
t
i
o
n
o
f
o
u
t
l
i
e
r
s
f
o
r
t
h
e
m
o
d
i
f
i
e
d
H
o
t
e
l
l
i
n
g
2
s
t
a
t
i
s
t
i
c
s
.
2.
4.
U
p
p
er
c
o
n
t
r
o
l
l
i
m
i
t
s
(U
C
L
)
S
i
n
c
e
t
h
e
d
i
s
t
r
i
b
u
t
i
o
n
o
f
t
h
e
H
o
t
e
l
l
i
n
g
’
s
2
s
t
a
t
i
s
t
i
c
i
s
v
a
g
u
e
w
h
e
n
t
h
e
s
a
m
p
l
e
s
i
z
e
i
s
s
m
a
l
l
,
t
he
u
ppe
r
c
ont
r
ol
l
i
m
i
t
s
a
r
e
c
a
l
c
ul
a
t
e
d
b
y
e
m
pl
o
yi
n
g
t
he
s
i
m
ul
a
t
i
on
.
T
he
s
i
m
ul
a
t
i
on
oc
c
ur
s
d
ur
i
ng
t
wo
ph
as
e
s
I a
n
d
II
.
P
h
a
s
e
I
t
he
bo
ot
s
t
r
a
p da
t
a
s
e
t
s
ge
ne
r
a
t
e
d f
r
om
t
he
s
t
a
n
d
a
r
d no
r
m
a
l
di
s
t
r
i
but
i
o
n
0
,
.
T
he
t
r
a
di
t
i
ona
l
a
n
d
t
he
r
ob
us
t
e
s
t
i
m
a
t
or
s
a
r
e
cal
cu
l
at
ed
f
o
r
t
h
es
e
d
at
a
s
et
s
.
Ph
a
se
I
I
pr
o
du
c
e
s
a
ne
w
a
d
di
t
i
ona
l
o
b
s
e
r
v
a
t
i
o
n
f
r
o
m
t
h
e
s
t
a
n
d
a
r
d
n
o
r
m
a
l
d
i
s
t
r
i
b
u
t
i
o
n
0
,
.
R
ep
eat
t
h
e
g
en
er
at
i
n
g
f
o
r
5
0
0
0
t
i
m
es
.
T
he
n c
a
l
c
ul
a
t
e
t
he
c
o
r
r
e
s
p
on
di
n
g
m
odi
f
i
e
d
H
ot
e
l
l
i
ng’
s
2
s
t
a
t
i
s
t
i
c
f
o
r
t
h
e
s
e
5
0
0
0
n
e
w
a
d
d
i
t
i
o
n
a
l
obs
e
r
va
t
i
on
s
.
T
he
pe
r
c
e
nt
i
l
e
95
c
om
p
ut
e
d
f
or
t
he
s
e
va
l
ue
s
o
f
a
dj
us
t
e
d
H
ot
e
l
l
i
ng’
s
2
s
t
a
t
i
s
t
i
c
a
n
d
t
h
e
n
s
u
c
h
v
al
u
e
o
f
t
h
e
p
e
r
cen
t
i
l
e
co
n
s
i
d
er
ed
as
t
h
e
U
CL
.
T
h
e
s
i
m
u
l
a
t
i
o
n
f
o
r
c
o
m
p
u
t
i
n
g
f
a
l
s
e
a
l
a
r
m
s
a
n
d
t
h
e
p
o
s
s
i
b
i
l
i
t
y
o
f
d
e
t
e
c
t
i
o
n
o
u
t
l
i
e
r
s
u
n
d
e
r
g
o
t
h
r
o
u
g
h
t
w
o
ph
as
e
s
I
an
d
I
I
.
T
o
c
l
a
r
i
f
y,
P
ha
s
e
I
t
he
bo
ot
s
t
r
a
p m
e
t
h
od
f
or
t
he
ge
n
e
r
a
t
e
d i
ndi
vi
d
u
a
l
ob
s
e
r
va
t
i
o
ns
f
r
om
d
i
s
t
r
i
b
u
t
i
o
n
0
.
i
s
u
s
e
d
.
T
he
n t
he
o
ut
l
i
e
r
s
a
r
e
a
d
de
d
a
c
c
or
di
n
g t
o
t
he
t
wo c
a
s
e
s
i
nde
pe
n
de
nt
a
nd
d
ep
e
n
d
en
t
v
a
r
i
ab
l
es
(
ca
s
e (
A
)
an
d
ca
s
e (
B
)
)
.
T
h
e t
r
a
d
i
t
i
o
n
al
an
d
r
o
b
u
s
t
es
t
i
m
at
o
r
s
co
m
p
u
t
ed
i
n
t
h
i
s
p
h
as
e.
A
c
c
o
r
di
n
g t
o
ph
as
e
I
I
,
t
h
e
f
a
l
s
e
a
l
a
r
m
s
i
s
c
a
l
c
u
l
a
t
e
d
a
n
d
t
h
e
p
o
s
s
i
b
i
l
i
t
y
o
f
d
e
t
e
c
t
i
o
n
o
u
t
l
i
e
r
s
.
F
o
r
i
n
s
t
a
n
c
e
,
t
he
f
a
l
s
e
a
l
a
r
m
i
s
c
a
l
c
ul
a
t
e
d w
he
n we
p
r
o a
ne
w
o
bs
e
r
va
t
i
o
n f
r
om
i
n c
o
nt
r
ol
di
s
t
r
i
but
i
o
n.
Me
a
nw
hi
l
e
t
h
e
p
o
s
s
i
b
i
l
i
t
y
o
f
d
e
t
e
c
t
i
o
n
o
f
o
u
t
l
i
e
r
s
i
s
c
a
l
c
u
l
a
t
i
n
g
w
h
e
n
t
h
e
ne
w o
bs
e
r
va
t
i
on
i
s
pr
od
uc
e
d
f
r
o
m
t
he
out
o
f
c
o
n
t
r
o
l
d
i
s
t
r
i
b
u
t
i
o
n
.
3.
R
ES
U
LTS
A
N
D
D
I
S
C
U
SSI
O
N
T
h
e
f
o
l
l
o
w
i
n
g
t
a
b
l
e
r
e
p
r
e
s
e
n
t
s
b
o
t
h
t
h
e
r
e
s
u
l
t
s
o
f
f
a
l
s
e
a
l
a
r
m
s
a
n
d
t
h
e
p
r
o
b
a
b
i
l
i
t
y
o
f
d
e
t
e
c
t
i
o
n
out
l
i
e
r
s
f
or
t
h
e
ne
w
m
odi
f
i
e
d
r
ob
us
t
c
ha
r
t
.
A
s
s
how
n
in
T
a
b
le
1
p
a
r
t
i
cu
l
ar
l
y
i
n
cas
e (
A
)
,
t
h
e
b
i
v
ar
i
at
e
va
r
i
a
bl
e
s
wi
t
h
l
e
ve
l
o
f
s
i
g
ni
f
i
c
a
nc
e
α
=
0.
0
5.
I
n
t
he
pr
e
s
e
nc
e
o
f
t
he
da
t
a
o
ut
l
i
e
r
s
,
t
he
va
l
ue
s
o
f
t
he
r
a
t
e
s
,
i
n
t
h
e
r
o
b
u
s
t
c
h
a
r
t
f
o
r
f
a
l
s
e
a
l
a
r
m
s
a
r
e
b
e
t
t
e
r
t
h
a
n
t
h
e
v
a
l
u
e
s
t
h
e
r
a
t
e
s
i
n
t
h
e
t
r
a
d
i
t
i
o
n
a
l
H
o
t
e
l
l
i
n
g
’
s
2
ch
ar
t
.
I
n
g
e
n
er
al
,
t
h
e
r
at
es
o
f
f
al
s
e
a
l
ar
m
s
ar
e
u
n
d
e
r
co
n
t
r
o
l
w
h
e
n
t
h
e
p
e
r
ce
n
t
ag
e
o
f
o
u
t
l
i
er
s
ε=
0
.
1
.
A
s
s
a
m
p
l
e
s
i
zes
i
n
cr
eas
e,
t
h
e
r
a
t
es
o
f
f
al
s
e
al
a
r
m
s
b
eco
m
e
c
o
n
s
er
v
at
i
v
e
w
h
e
n
ev
e
r
t
h
e
p
er
ce
n
t
ag
e
o
f
o
u
t
l
i
er
s
i
s
ε=0
.
2
I
n
r
e
s
pe
c
t
of
t
he
p
os
s
i
bi
l
i
t
y of
de
t
e
c
t
i
o
n
,
o
u
t
l
i
e
r
s
a
r
e
c
o
n
s
i
d
e
r
e
d
b
e
t
t
e
r
i
n
t
h
e
r
o
b
u
s
t
H
o
t
e
l
l
i
n
g
’
s
2
c
ont
r
ol
c
ha
r
t
s
c
om
pa
r
i
ng
wi
t
h t
r
a
di
t
i
o
na
l
H
ot
e
l
l
i
ng’
s
2
c
ont
r
ol
c
ha
r
t
s
.
P
a
r
t
i
c
ul
a
r
l
y
w
he
n t
he
pe
r
c
e
nt
a
ge
o
f
o
u
t
l
i
er
s
ε=0
.
2
,
t
h
e
h
u
g
e
d
i
f
f
e
r
en
ce
c
o
u
l
d
b
e
d
et
ect
e
d
b
et
w
een
t
h
e
r
at
es
o
f
t
h
e
p
os
s
i
bi
l
i
t
y
of
de
t
e
c
t
i
on of
out
l
i
e
r
s
be
t
w
e
e
n
t
he
r
o
bus
t
c
ha
r
t
a
n
d
t
he
t
r
a
di
t
i
ona
l
c
ha
r
t
w
hi
c
h
i
m
pl
i
e
s
t
ha
t
t
he
f
i
n
di
n
gs
c
o
nc
e
r
ni
ng
r
o
b
us
t
c
ha
r
t
s
a
r
e
be
t
t
e
r
t
ha
n
t
he
f
i
n
di
ngs
i
n t
he
t
r
a
di
t
i
ona
l
c
ha
r
t
s
.
F
ur
t
he
r
m
o
r
e
,
t
h
e
r
o
bus
t
H
ot
e
l
l
i
ng
2
c
ont
r
ol
c
ha
r
t
,
t
h
e
m
o
r
e
v
al
u
es
o
f
t
h
e
p
o
s
s
i
b
i
l
i
t
y
o
f
d
et
ect
i
o
n
o
u
t
l
i
er
s
i
n
cr
eas
e,
t
h
e
m
o
r
e s
am
p
l
e s
i
ze i
n
c
r
eas
e
t
h
at
ach
i
ev
es
1
0
0
%
d
et
ect
ed
w
h
en
t
h
e
s
am
p
l
e s
i
ze ach
i
e
v
e t
o
1
0
0
.
O
n
t
h
e c
o
n
t
r
ar
y
,
t
h
e m
o
r
e
v
a
l
u
es
o
f
t
he
pr
o
ba
bi
l
i
t
y
of
de
t
e
c
t
i
on
f
o
r
t
he
t
r
a
di
t
i
ona
l
c
ont
r
ol
c
ha
r
t
s
d
ecr
eas
e
,
t
h
e m
o
r
e s
a
m
p
l
e s
i
ze i
n
c
r
eas
e.
T
he
r
e
f
or
e
,
i
t
c
a
n be
de
duc
e
d t
ha
t
t
he
m
o
di
f
i
e
d
r
o
b
u
s
t
H
ot
e
l
l
i
ng
’
s
2
co
n
t
r
o
l
ch
a
r
t
s
ar
e b
et
t
er
t
h
an
t
h
e
t
r
a
d
i
t
i
o
n
a
l
H
o
t
e
l
l
i
n
g
’
s
2
c
o
n
t
r
o
l
c
h
a
r
t
s
p
a
r
t
i
c
u
l
a
r
l
y
i
n
t
h
e
p
o
s
s
i
b
i
l
i
t
y
o
f
d
e
t
e
c
t
i
o
n
o
u
t
l
i
e
r
s
.
W
i
t
h r
e
ga
r
d t
o
c
a
s
e
(
B
)
c
o
nc
e
r
ni
ng t
he
d
e
p
e
nde
nt
va
r
i
a
bl
e
s
,
t
he
r
o
b
us
t
c
ha
r
t
ha
s
be
t
t
e
r
pe
r
f
o
r
m
a
nc
e
co
m
p
ar
i
n
g
w
i
t
h
t
h
e
p
er
f
o
r
m
an
ce o
f
t
h
e t
r
ad
i
t
i
o
n
al
ch
a
r
t
r
el
at
i
n
g
w
i
t
h
f
al
s
e al
ar
m
s
a
n
d t
he
p
os
s
i
bi
l
i
t
y o
f
d
e
t
e
c
t
i
o
n
.
I
t
ha
s
be
e
n
o
bs
e
r
ve
d t
ha
t
t
h
e
v
a
l
u
e
s
o
f
t
h
e
p
o
s
s
i
b
i
l
i
t
y
o
f
d
e
t
e
c
t
i
o
n
o
f
o
u
t
l
i
e
r
s
a
r
e
b
e
t
t
e
r
p
a
r
t
i
c
u
l
a
r
l
y
w
h
e
n
t
h
e
p
e
r
c
en
t
ag
e
o
f
o
u
t
l
i
er
s
ε=0
.
1
d
es
p
i
t
e
t
h
at
t
h
e
v
al
u
es
o
f
f
al
s
e
al
ar
m
s
i
n
t
h
i
s
c
as
e
ar
e
n
o
t
w
e
l
l
an
d
r
eas
o
n
a
b
l
e.
T
h
e
i
n
c
r
e
a
s
i
n
g
o
f
t
h
e
s
a
m
p
l
e
s
i
z
e
i
m
p
a
c
t
s
o
n
t
h
e
p
o
s
s
i
b
i
l
i
t
y
o
f
d
e
t
e
c
t
i
o
n
,
b
u
t
d
o
e
s
n
o
t
i
m
p
a
c
t
o
n
t
h
e
v
a
l
u
e
s
o
f
f
a
l
s
e
a
l
a
r
m
s
.
T
h
i
s
s
u
g
g
e
s
t
s
t
h
a
t
t
h
e
m
o
d
i
f
i
e
d
r
o
b
u
s
t
H
o
t
e
l
l
i
n
g
’
s
2
c
o
n
t
r
o
l
c
h
a
r
t
i
s
b
e
t
t
e
r
t
h
a
n
t
h
e
t
r
a
d
i
t
i
o
n
a
l
H
o
t
e
l
l
i
n
g
’
s
2
c
o
n
t
r
o
l
c
h
a
r
t
p
a
r
t
i
c
u
l
a
r
l
y
i
n
t
h
e
p
o
s
s
i
b
i
l
i
t
y
o
f
d
e
t
e
c
t
i
n
g
o
u
t
l
i
e
r
s
.
C
a
s
e
A i
ndi
c
a
t
e
s
t
ha
t
i
n
de
pe
nde
nt
va
r
i
a
bl
e
s
a
r
e
de
m
o
ns
t
r
a
t
e
d i
n
F
i
g
ur
e
s
1
-
4 w
ith th
e
nu
m
b
e
r
o
f
c
ha
r
a
c
t
e
r
i
s
t
i
c
s
a
t
p=
2.
T
he
f
i
ndi
ng
s
r
e
ve
a
l
t
ha
t
i
n t
he
de
t
e
c
t
i
on o
f
out
l
i
e
r
s
,
t
he
ne
w a
d
o
pt
e
d c
ha
r
t
ha
s
b
e
t
t
e
r
pe
r
f
o
r
m
a
nc
e
c
om
pa
r
i
ng
wi
t
h
t
he
c
on
ve
nt
i
o
na
l
c
ha
r
t
.
I
t
i
s
ob
vi
o
us
t
he
s
t
r
on
g
pe
r
f
or
m
a
n
c
e
o
f
t
he
ne
w
c
ha
r
t
i
n
d
e
t
e
c
t
i
n
g
o
u
t
l
i
e
r
s
d
a
t
a
w
h
e
n
t
h
e
s
a
m
p
l
e
s
i
z
e
s
a
r
e
3
0
a
n
d
4
0
t
h
a
n
o
t
h
e
r
s
i
z
e
s
.
I
n
r
e
s
p
e
c
t
o
f
t
he
de
p
e
nde
nt
va
r
i
a
bl
e
s
(
c
a
s
e
B
)
,
F
i
gu
r
e
s
5
a
n
d 6
c
on
f
i
r
m
s
th
e
s
up
e
r
io
r
ity of
th
e
ne
w
c
h
a
r
t
to the
c
onv
e
n
tion
a
l
on
e
,
i
ndi
c
a
t
i
n
g t
he
a
pp
r
op
r
i
a
t
e
ne
s
s
o
f
t
he
ne
w
c
h
a
r
t
f
or
t
he
a
b
ov
e
-
m
e
nt
i
one
d
c
a
s
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
E
l
e
c
&
C
om
p
E
n
g
I
S
S
N
:
208
8
-
87
08
M
o
d
i
f
i
e
d
h
o
t
e
l
l
i
n
g
’
s
c
o
nt
r
ol
c
har
t
s
us
i
n
g
m
o
di
f
i
e
d…
(
F
i
r
as
H
ad
d
ad
)
2
89
T
a
b
l
e
1
.
T
h
e
r
a
t
e
s
o
f
f
a
l
s
e
a
l
a
r
m
s
a
n
d
d
e
t
e
c
t
i
o
n
o
u
t
l
i
e
r
s
f
o
r
t
h
e
r
o
b
u
s
t
c
h
a
r
t
,
i
n
c
a
s
e
P
=
2,
a
l
pha
=
0.
05
,
ε
i
s
pe
r
c
e
nt
a
ge
of
o
ut
l
i
e
r
s
a
nd
va
r
i
ous
va
l
ue
s
of
n
o
n
-
c
e
n
t
r
a
l
i
t
y
p
a
r
a
m
e
t
e
r
t
r
i
m
m
i
n
g
i
s
4
0
%
.
Ca
se
n
µ
̅
−
2
̅
−
2
A
20
0
(0
,0
)
(3
.4
)
(
6.
28)
0
.1
(3
,3
)
(
2.
54)
49.
7
(4
.3
)
73.
2
(5
,5
)
(
3.
48)
94
(
4.
44)
98.
1
0
.2
(3
,3
)
(
2.
74)
4.
22
(
2.
22)
50.
16
(5
,5
)
(
1.
42)
29.
66
(
1.
66)
87.
36
30
0
(0
,0
)
(
2.
16)
(9
)
0
.1
(3
,3
)
(
1.
66)
42.
56
(
4.
94)
85.
2
(5
,5
)
(
2.
04)
92.
02
(
4.
42)
99.
88
0
.2
(3
,3
)
(0
.5
)
2.
08
(
4.
76)
69
(5
,5
)
(
0.
26)
15.
24
(
1.
94)
97.
46
40
0
(0
,0
)
(
2.
84)
(
9.
16)
0
.1
(3
,3
)
(
1.
66)
40.
62
(
6.
38)
84.
6
(5
,5
)
(
1.
02)
97.
3
(
5.
84)
99.
9
0
.2
(3
,3
)
(
0.
52)
8
.2
(
5.
34)
71.
5
(5
,5
)
(
0.
12)
16.
1
(2
.4
)
97.
74
50
0
(0
,0
)
(
5.
26)
(4
.4
)
0
.1
(3
,3
)
(
1.
94)
60.
06
(1
.7
)
70
(5
,5
)
(
1.
02)
99.
6
(
1.
56)
99.
8
0
.2
(3
,3
)
(
0.
54)
4
.8
(
0.
16)
45.
3
(5
,5
)
(
0.
12)
54.
7
(
0.
18)
95.
24
100
0
(0
,0
)
(
12.
06)
(8
.9
)
0
.1
(3
,3
)
(
1.
04)
76.
4
(
4.
29)
93.
24
(5
,5
)
(
0.
14)
100
(
4.
24)
100
0
.2
(3
,3
)
(
2.
88)
4
.3
(
1.
98)
81.
34
(5
,5
)
(
0.
08)
87.
72
(
1.
12)
99.
98
B
20
0
(0
,0
)
(
0.
08)
(0
.5
)
0
.1
(5
,5
)
(0
.5
)
88
(0
.3
6
)
84.
18
0
.2
(5
,5
)
(
0.
42)
22.
7
(0
.0
6
)
57.
98
30
0
(0
,0
)
(
0.
06)
(1
.3
)
0
.1
(5
,5
)
(
0.
24)
76.
7
(
1.
46)
98.
28
0
.2
(5
,5
)
(
0.
14)
8.
54
(1
.4
)
92.
74
40
0
(0
,0
)
(0
)
(
0.
52)
0
.1
(5
,5
)
(
0.
02)
90.
5
(
0.
36)
95.
94
0
.2
(5
,5
)
(0
)
8.
94
(
0.
12)
86.
06
50
0
(0
,0
)
(0
)
(
0.
84)
0
.1
(5
,5
)
(
0.
04)
95.
78
(0
.1
4
)
97.
72
0
.2
(5
,5
)
(0
)
28.
02
(0
)
84.
1
100
0
(0
,0
)
(0
)
(
2.
72)
0
.1
(5
,5
)
(
0.
02)
99.
88
(
0.
48)
99.
92
0
.2
(5
,5
)
(0
)
71.
58
(
0.
02)
98.
26
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
SN
:
2
088
-
87
08
I
nt
J
E
l
e
c
&
C
om
p
E
n
g,
V
o
l
.
11
,
No
.
1,
F
e
b
r
ua
r
y
2
02
1
:
284
-
2
92
2
90
1
0
%
o
u
t
l
i
e
r
s
w
i
t
h
s
h
i
f
t
e
d
m
e
a
n
3
2
0
%
o
u
t
l
i
e
r
s
w
i
t
h
s
h
i
f
t
e
d
m
e
a
n
3
F
i
gu
r
e
1.
T
h
e
r
a
t
e
s
o
f
d
e
t
e
c
t
i
o
n
o
u
t
l
i
e
r
s
w
i
t
h
s
am
p
l
e
s
i
ze
m
(
C
as
e
A
)
F
i
gu
r
e
2.
T
h
e
r
a
t
e
s
o
f
d
e
t
e
c
t
i
o
n
o
u
t
l
i
e
r
s
w
i
t
h
s
am
p
l
e
s
i
ze
m
(
C
as
e
A
)
1
0
%
o
ut
l
i
e
r
s
w
i
t
h
s
hi
f
t
e
d
m
e
a
n
5
2
0
%
o
ut
l
i
e
r
s
w
i
t
h
s
hi
f
t
e
d
m
e
a
n
5
F
i
gu
r
e
3.
T
he
r
a
t
e
s
of
de
t
e
c
t
e
d
out
l
i
e
r
s
w
i
t
h
s
a
m
p
l
e
s
i
z
e
m
(
C
as
e
A
)
F
i
gu
r
e
4.
T
he
r
a
t
e
s
of
de
t
e
c
t
e
d
out
l
i
e
r
s
w
i
t
h
s
a
m
p
l
e
s
i
z
e
m
(
C
as
e
A
)
1
0
%
o
ut
l
i
e
r
s
w
i
t
h
s
hi
f
t
e
d
m
e
a
n
5
2
0
%
o
ut
l
i
e
r
s
w
i
t
h
s
hi
f
t
e
d
m
e
a
n
5
F
i
gu
r
e
5.
T
he
r
a
t
e
s
of
de
t
e
c
t
e
d
out
l
i
e
r
s
w
i
t
h
s
a
m
p
l
e
s
i
z
e
m
(
Ca
s
e
B)
F
i
gu
r
e
6.
T
he
r
a
t
e
s
of
de
t
e
c
t
e
d
out
l
i
e
r
s
w
i
t
h
s
a
m
p
l
e
s
i
z
e
m
(
Ca
s
e
B)
3.
1.
E
mp
i
ri
ca
l
ca
s
e
s
t
u
d
y
V
a
r
ga
s
J
i
n
[
2
8]
f
i
n
di
n
gs
w
e
r
e
e
m
pl
oy
e
d i
n o
r
de
r
t
o c
om
pa
r
e
be
t
w
e
e
n t
he
m
.
T
h
us
,
t
h
e
f
i
ndi
ng
s
o
f
t
he
s
ug
ge
s
t
e
d
t
e
c
hni
q
ue
a
n
d
t
ho
s
e
of
t
he
c
on
ve
nt
i
ona
l
a
nd
a
dj
us
t
e
d
c
ont
r
ol
c
ha
r
t
s
w
e
r
e
c
o
nt
r
a
s
t
e
d.
I
t
i
s
ob
vi
o
us
t
wo f
e
a
t
ur
e
s
of
r
a
n
d
o
m
va
r
i
a
bl
e
s
i
n t
he
da
t
a
na
m
e
l
y
1
X
an
d
2
X
.
M
o
s
t
i
m
p
o
r
t
a
n
t
l
y
t
h
e
d
a
t
a
w
e
r
e
e
l
i
c
i
t
e
d
f
r
om
30
va
r
i
ous
pr
o
duc
t
s
f
r
om
t
he
p
r
od
uc
t
i
o
n pr
oc
e
s
s
.
Va
r
ga
s
J
i
n
[
2
8]
us
e
d
t
w
o va
r
i
a
bl
e
s
f
r
o
m
Q
u
es
en
b
er
r
y
d
at
as
et
.
A
s
s
u
c
h
,
T
a
b
l
e
2
r
e
v
eal
s
t
h
e o
b
s
e
r
va
t
i
on
s
o
f
t
he
a
bo
ve
-
m
e
nt
i
on
e
d r
a
n
do
m
va
r
i
a
bl
e
s
na
m
e
l
y
t
he
va
l
ue
s
of
t
he
ne
w
Hot
e
l
l
i
ng
’
s
T
2
an
d
t
he
c
o
nve
n
t
i
ona
l
T
2
c
h
a
r
t
s
t
a
t
i
s
t
i
c
s
.
T
he
s
i
m
ul
a
t
i
o
n f
or
t
he
r
o
b
u
s
t
c
ha
r
t
s
w
a
s
us
e
d i
n t
he
U
C
L
c
a
l
c
u
l
a
t
i
o
n
.
T
hi
s
s
t
u
dy
r
e
ve
a
l
s
t
ha
t
t
he
va
l
ue
of
a
l
l
U
CL
w
a
s
e
s
t
a
bl
i
s
he
d a
t
9.
4
78
7
f
or
α=
0.
05
.
T
he
e
l
i
c
i
t
e
d
f
i
ndi
n
gs
,
f
or
t
h
e
c
on
ve
nt
i
ona
l
c
h
a
r
t
,
onl
y one
o
ut
l
i
e
r
w
a
s
de
t
e
c
t
e
d na
m
e
l
y
t
he
2
nd
,
w
h
i
l
e
t
h
e
r
o
b
u
s
t
c
h
a
r
t
s
w
e
r
e
a
b
l
e
t
o
d
e
t
e
c
t
f
i
v
e
o
u
t
l
i
e
r
s
n
a
m
e
l
y
t
h
e
2
nd
,
5
th
,
1
4
nd
,
17
th
a
n
d
20
th
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
E
l
e
c
&
C
om
p
E
n
g
I
S
S
N
:
208
8
-
87
08
M
o
d
i
f
i
e
d
h
o
t
e
l
l
i
n
g
’
s
c
o
nt
r
ol
c
har
t
s
us
i
n
g
m
o
di
f
i
e
d…
(
F
i
r
as
H
ad
d
ad
)
2
91
T
ab
l
e
2
.
B
i
v
ar
i
at
e
v
ar
i
a
b
l
es
X
1
a
nd
X
2
o
f
V
ar
g
as
d
a
t
a
s
et
w
i
t
h
t
h
e
v
al
u
es
o
f
T
2
s
t
a
t
i
s
t
i
c
s
e
m
p
l
o
y
i
n
g
t
he
c
o
n
ve
nt
i
on
a
l
a
nd
t
he
w
i
ns
or
i
z
e
d
MO
M
e
s
t
i
m
a
t
o
r
Pr
o
d
u
ct No
1
X
2
X
2
0
T
T
t
Qn
2
1
0.
567
60.
558
0.
807
4.
8584
2
0.
538
56.
303
12.
975
31.
451
3
0.
53
59.
524
0.
1373
1.
026
4
0.
562
61.
102
1.
8375
4.
9479
5
0.
483
59.
834
1.
5697
28.
065
5
6
0.
525
60.
228
0.
33
1.
4439
7
0.
556
60.
756
0.
977
1.
8793
8
0.
586
59.
823
0.
904
2.
6814
9
9
0.
547
60.
153
0
0.
1269
0.
2652
10
0.
531
60.
64
0.
801
3.
1888
11
0.
581
59.
785
0.
7192
0.
9387
12
0.
585
59.
675
0.
910
1.
8479
9
13
0.
54
60.
489
0.
483
2.
8319
14
0.
458
61.
067
5.
2413
13.
241
3
15
0.
554
59.
788
0.
073
0.
9757
8
16
0.
469
58.
64
3.
5357
8.
3317
17
0.
471
59.
574
2.
2696
10.
050
2
18
0.
457
59.
718
3.
2442
8.
8545
19
0.
565
60.
901
1.
398
2.
0478
4
20
0.
664
60.
18
6.
8326
14.
425
21
0
.6
60.
493
1.
8978
3.
8182
22
0.
586
58.
37
3.
3564
6.
66
23
0.
567
60.
216
0.
4275
46
1.
7246
24
0.
496
60.
214
1.
1838
5.
3057
4
25
0.
485
59.
5
1.
4968
7.
3952
26
0.
573
60.
052
0.
4843
2
0.
3187
27
0.
52
59.
501
0.
2898
9
2.
2453
9
28
0.
556
58.
476
2.
0635
7.
5750
22
29
0.
539
58.
666
1.
3859
6
1.
2791
14
30
0.
554
60.
239
0.
2404
3
0.
1520
33
4.
C
O
N
CL
U
S
I
O
N
T
h
e
H
o
t
e
l
l
i
n
g
’
s
T
2
ch
ar
t
t
r
i
m
m
ed
c
o
v
ar
i
a
n
ce m
at
r
i
x
an
d
t
r
i
m
m
e
d
m
e
an
w
e
re
u
s
e
d
i
n
t
h
i
s
s
t
u
d
y
r
es
p
ect
i
v
el
y
as
t
h
e
s
cal
e
co
v
a
r
i
an
ce
m
at
r
i
x
a
n
d
t
h
e
l
o
cat
i
o
n
v
ect
o
r
.
T
h
e
c
o
m
p
a
r
a
t
i
v
e
c
onc
e
r
n
i
n
g
the
m
od
if
ie
d
c
h
a
r
t
a
n
d
t
h
e
c
o
n
v
e
n
t
i
o
n
a
l
c
h
a
r
t
a
i
m
e
d
a
t
r
e
v
e
a
l
i
n
g
t
h
e
i
r
p
e
r
f
o
r
m
a
n
c
e
i
n
d
e
t
e
c
t
i
n
g
o
u
t
l
i
e
r
s
a
n
d
f
a
l
s
e
a
l
a
r
m
s
.
T
o t
hi
s
e
n
d,
t
w
o c
as
es
w
e
r
e
u
t
i
l
i
zed
cas
e (
A
)
a
n
d
cas
e
(
B
)
.
T
o
i
l
l
u
s
t
r
at
e,
t
h
e
f
o
r
m
e
r
c
o
n
t
ai
n
s
t
h
e
i
n
d
ep
e
n
d
e
n
t
v
a
r
i
a
b
l
e
s
,
w
h
i
l
e
t
h
e
l
a
t
e
r
c
o
n
t
a
i
n
s
t
h
e
d
e
p
e
n
d
e
n
t
v
a
r
i
a
b
l
e
s
.
T
h
e
f
i
n
d
i
n
g
s
o
f
t
h
e
s
i
m
u
l
a
t
i
o
n
r
e
s
u
l
t
s
s
h
o
w
t
h
a
t
m
o
d
i
f
i
ed
c
h
ar
t
w
as
ab
l
e t
o
co
n
t
r
o
l
f
al
s
e a
l
ar
m
r
at
es
un
d
e
r
m
os
t
of
c
o
ndi
t
i
o
ns
.
S
u
r
p
r
i
s
i
n
g
l
y
,
s
u
c
h
a
b
i
l
i
t
y
st
a
r
te
d to r
e
duc
e
f
o
llow
e
d
by th
e
e
nha
nc
e
i
n
t
he
s
hi
f
t
e
d
m
e
a
n
ve
c
t
or
µ
a
nd
pr
o
po
r
t
i
on
of
o
ut
l
i
e
r
s
.
T
he
r
o
bus
t
c
ha
r
t
h
a
s
i
n
di
c
a
t
e
d i
t
s
s
upe
r
i
or
a
bi
l
i
t
y i
n
pr
o
duc
i
ng t
he
pos
s
i
bi
l
i
t
y of
de
t
e
c
t
i
on
out
l
i
e
r
s
c
om
pa
r
i
n
g w
i
t
h
t
he
a
bi
l
i
t
y
of
c
on
ve
nt
i
ona
l
T
2
ch
ar
t
.
R
EF
ER
E
N
C
ES
[1]
A
l
t
,
F. B
. (
E
d
.
)
.,
“
Mu
l
t
iv
a
r
ia
te
q
u
a
lity
c
o
n
tr
o
l
,
”
En
c
y
c
lo
p
e
d
ia
o
f
s
t
a
tis
tic
a
l s
c
ie
n
c
e
,
vol
.
6,
pp.
110
-
122,
1985
.
[2]
M
ont
gom
e
ry,
D
.
C.
(E
d
.)
.,
“
In
t
ro
duc
t
i
on
to
S
t
a
tis
t
ic
a
l Q
u
a
l
ity
C
o
n
tr
o
l,
”
J
ohn Wi
l
e
y
and Sons
In
c
,
2
005.
[3]
M
os
t
a
j
e
ra
n
A
.
,
Ira
np
a
na
h
,
a
nd
N
.
,
N
ooros
s
a
na
R.
,
“
A
n e
v
a
l
u
a
t
i
on
of
t
he
mu
ltiv
a
r
ia
te
d
is
p
e
r
s
io
n
c
h
a
r
ts
w
it
h
e
s
tima
te
d
p
a
ra
m
e
t
e
rs
und
e
r
n
on‐norm
a
l
i
t
y,
A
ppl
i
e
d
St
o
c
has
t
i
c
Mod
e
l
s
i
n
B
us
i
n
and
Indus
t
r
y
,
vol
.
33,
no
.
6,
pp.
694
-
716
,
20
17.
[4]
Ha
d
da
d
F
.
a
nd
A
ls
ma
d
i M
.
K
.
,
“
I
m
prove
m
e
nt
of T
h
e
H
ot
e
l
l
i
n
g’s
T
2
Cha
rt
s
U
s
i
ng Robus
t
L
oc
a
t
i
on
W
i
ns
ori
z
e
d
O
ne
S
t
e
p M
-
E
st
i
m
a
t
o
r
(
W
MOM)
,
”
P
unj
ab
U
ni
v
e
r
s
i
t
y
,
J
our
nal
o
f
Mat
he
m
at
i
c
s
,
v
ol
.
5
0,
n
o.
1,
p
p.
97
-
112,
2018
.
[5]
Al
l
o
wa
y
,
J
.
A
.
J
.,
R
ag
h
av
ach
ar
i
,
M
.,
“
M
u
ltiv
a
r
ia
t
e
C
o
n
tr
o
l
C
h
ar
t
s
B
as
ed
o
n
T
r
i
m
m
ed
M
ean
,
”
A
SQ
C
Q
u
a
l
i
t
y
Congr
e
s
s
T
r
ans
ac
t
i
ons
-
San
F
r
a
n
ci
s
co
,
pp.
449
-
453,
1990
.
[6]
S
urt
i
ha
di
J
.
,
“
M
ul
t
i
va
r
i
a
t
e
a
nd
r
obus
t
c
ont
ro
l
c
h
a
r
t
s
for
l
oc
a
t
i
on
a
nd
di
s
pe
rs
i
on,
”
D
i
s
s
. R
en
s
s
el
a
er
P
o
l
yt
ech
n
i
c
I
n
s
titu
te
,
1994
.
[7]
A
l
fa
ro,
J
. L
.
, a
n
d
O
r
t
eg
a
, J
.
F
.,
“
A
Robus
t
A
l
t
e
rn
a
t
i
v
e
t
o H
o
t
e
l
l
i
n
g’s
T
2 Cont
rol
Cha
rt
U
s
i
ng T
r
i
mme
d
Es
tim
a
to
r
s
,
”
Q
ual
i
t
y
and R
e
l
i
abi
l
i
t
y
E
ngi
ne
e
r
i
ng Int
e
r
nat
i
onal
,
vol
.
24,
no.
5,
p
p.
601
-
611
,
200
8.
[8]
Jo
n
es
L
.
A
.
a
nd
W
ooda
l
W
.
H
.
, “
T
he
pe
rfor
m
a
nc
e
of boo
t
s
t
ra
p
c
ont
rol
c
ha
r
t
s
,
”
J
our
nal
of
Q
ua
l
i
t
y
T
e
c
hnol
o
gy
,
vol
.
30
,
no
.
4
,
pp
.
362
-
375
,
1998
.
[9]
P
.
P
ha
l
a
di
ga
non
,
et
a
l
.
, “
Boot
s
t
r
a
p
-
b
a
s
e
d
T
2
m
u
ltiv
a
r
ia
te
c
o
n
tr
o
l
c
h
a
r
ts
,
"
Com
m
uni
c
a
t
i
ons
i
n
S
t
a
tis
ti
c
s
,
v
o
l.
4
0
,
no.
5
,
pp
.
645
-
6
62,
2011
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
SN
:
2
088
-
87
08
I
nt
J
E
l
e
c
&
C
om
p
E
n
g,
V
o
l
.
11
,
No
.
1,
F
e
b
r
ua
r
y
2
02
1
:
284
-
2
92
2
92
[10]
G
a
ndy
A
.
a
n
d K
va
l
oy
J
.
T
.
, “
G
ua
ra
nt
e
e
d Con
di
t
i
ona
l
P
e
rform
a
nc
e
of
Cont
rol
Cha
rt
s
vi
a
Boo
t
s
t
ra
p M
e
t
hods
,
”
Sc
andi
nav
i
an
J
o
ur
nal
of
S
t
a
tis
t
ic
s
,
vol
.
40,
no.
4,
pp.
647
-
668,
20
13.
[11]
O
gbe
i
de
E
fos
a
M
i
ch
ea
l
an
d
E
d
opka
I.
W
.,
“
B
oot
s
t
ra
p A
pproa
c
h Cont
rol
l
i
m
i
t
f
o
r
s
ta
tis
t
ic
a
l q
u
a
lity
c
o
n
tr
o
l,
”
Int
e
r
nat
i
onal
J
o
ur
nal
of
E
ngi
ne
e
r
i
ng Sc
i
e
nc
e
Inv
e
nt
i
on
,
v
o
l
. 2
, n
o
. 4
,
p
p.
2319
-
67
34
,
2013
.
[12]
M
os
t
a
j
e
ra
n
A
.
,
Ira
np
a
na
h
N
.
,
a
nd
N
ooros
s
a
na
R
.
,
“
A
N
e
w
Boot
s
t
ra
p
B
a
s
e
d A
l
gor
i
t
hm
for
H
ot
e
l
l
i
ng’s
T
2
M
ul
t
i
va
ri
a
t
e
Co
nt
rol
Ch
a
rt
,”
J
ou
r
nal
of
S
c
i
e
n
c
e
s
,
Is
l
am
i
c
R
e
pub
l
i
c
of
Ir
an
,
vo
l
.
27
,
no
.
3
,
pp
.
269
-
278,
2016
.
[13]
M
o
s
t
aj
er
an
A
.,
I
ra
npa
na
h
N
.
,
a
n
d N
ooros
s
a
na
R
.
,
“
A
n
e
xpl
a
n
a
t
o
ry s
t
udy on
t
he
non
-
pa
ra
m
e
t
ri
c
mu
ltiv
a
r
i
a
te
T2
c
ont
rol
c
ha
rt
,
”
J
our
nal
of
Mod
e
r
n A
pp
l
i
e
d S
t
at
i
s
t
i
c
al
Me
t
hods
,
vo
l
.
17
,
no
.
1
,
2018
.
[14]
S
ye
d Y
a
ha
ya
S
.
S.,
e
t a
l.
, “
Ro
bus
t
H
ot
e
l
l
i
ng’s
Cha
rt
s
w
i
t
h M
e
di
a
n
Ba
s
e
d
T
ri
m
m
e
d
Es
ti
ma
to
r
s
,
”
J
our
nal
of
E
ngi
ne
e
r
i
ng and
A
ppl
i
e
d s
c
i
e
n
c
e
,
vol
.
14,
no.
24,
pp.
9632
-
9638
,
2019.
[15]
H
a
d
d
a
d
F. S., “
I
m
provi
ng
Bi
va
r
i
a
t
e
H
ot
e
l
l
i
ng’s
T
2 Ch
a
rt
U
s
i
ng
N
e
w
Robus
t
E
s
t
i
m
a
t
ors
(W
M
O
M
w
i
t
h
Q
n
)
a
nd
Boot
s
t
ra
p D
a
t
a
,
”
Int
e
r
nat
i
onal
J
o
ur
nal
of
A
ppl
i
e
d E
ngi
ne
e
r
i
ng
R
e
s
e
ar
c
h,
vo
l
.
14,
n
o.
21
,
pp
.
4001
-
4009,
2019
.
[16]
Roc
k,
D
.
M
.
,
D
ow
ns
,
G
.
W
.
,
a
n
d Roc
k
,
A
.
J
.
,
“
A
re
robus
t
e
s
t
i
m
a
t
ors
re
a
l
l
y
ne
c
e
s
s
a
ry?
,”
T
ech
n
i
m
et
r
i
cs
,
vol
.
2
4,
no.
2
,
pp
.
95
-
10
1,
1982
.
[17]
T
uke
y,
J
.
W
.
,
a
nd M
c
L
a
ughl
i
n
,
D
.
H
.
,
“
L
es
s
V
u
l
n
er
ab
l
e
Con
fi
de
nc
e
a
nd
S
i
g
ni
fi
c
a
nc
e
P
roc
e
dure
s
for
L
o
c
a
t
i
o
n
B
as
ed
o
n
a S
i
n
g
l
e S
am
p
l
e
,”
San
k
hy
ā:
T
he
Indi
an
J
our
nal
of
St
at
i
s
t
i
c
s
,
Se
r
i
e
s
A
,
vol
.
25
,
pp
.
331
-
33
2,
1963
.
[18]
Ros
e
nbe
rge
r,
J
.
L
.
,
a
nd
G
a
s
ko,
M
.
,
“
Com
p
a
ri
ng
l
o
c
a
t
i
on e
s
t
i
m
a
t
ors
:
T
ri
m
m
ed
m
ean
s
,
m
ed
i
an
s
an
d
tr
imm
e
a
n
,
”
U
nde
r
s
t
andi
ng r
obus
t
and e
x
pl
or
at
or
y
dat
a
anal
y
s
i
s
,
297
-
336,
19
83.
[19]
Wi
l
co
x
, R
. R
.,
“
A
N
O
V
A
:
A
pa
ra
di
g
m
for
l
o
w
pow
e
r a
nd
m
i
s
l
e
a
d
i
ng
m
e
a
s
ure
s
of e
ff
e
c
t
s
i
z
e
?
,”
R
e
vi
ew
o
f
E
duc
at
i
o
n
a
l
R
es
ea
r
ch
,
vo
l
.
65,
n
o.
1
,
pp
.
51
-
77
,
1995.
[20]
Croux,
C.
,
a
nd
R
o
u
s
s
eeu
w
, P
. J
.,
“
T
i
m
e
-
e
ffi
c
i
e
n
t
a
l
gori
t
h
m
s
for t
w
o hi
g
h
l
y robus
t
e
s
t
i
m
a
t
ors
of s
c
a
l
e
,
”
Com
put
at
i
o
n
a
l S
ta
tis
ti
c
s
,
vo
l
.
2,
pp.
411
-
428
,
19
92.
[21]
Ab
dul
l
a
h,
M
.
B
.
,
“
On
r
obus
t
c
orr
e
l
a
t
i
on c
oe
ff
i
c
i
e
nt
,
”
S
ta
t
is
tic
ia
n
,
vol
.
3
9,
p
p.
455
-
460
,
1990
.
[22]
J
ohns
on,
M
.
E
.
(
E
d.
),
“
M
u
l
tiv
a
r
i
a
te
s
ta
t
is
tic
a
l
s
i
mu
la
t
io
n
:
Ne
w Yo
r
k
,
”
J
ohn Wi
l
e
y
and
s
ons
,
198
7.
[23]
J
ohns
on,
N
.
,
“
A
c
om
pa
r
i
t
i
v
e
s
i
m
ul
a
t
i
on
s
t
udy of
robus
t
e
s
t
i
m
a
t
or
s
of s
t
a
nda
rd e
rr
or,
”
Br
i
gha
m
Y
o
ung U
ni
v
.
,
2007
.
[24]
A
l
fa
ro,
J
.
L
.
,
a
nd
O
r
t
e
g
a
, J
. F
.
, “
A
c
o
m
pa
r
i
s
on of
robus
t
a
l
t
e
rna
t
i
v
e
t
o
H
ot
e
l
l
i
ng
T
2
c
on
t
rol
c
h
a
rt
,
”
Ap
p
lie
d
S
ta
tis
ti
c
s
,
vo
l
.
3
6,
no
.
12
,
pp
.
13
85
-
1396,
2009
.
[25]
C
h
en
o
u
r
i
,
S
.,
V
ar
i
y
at
h
, A
.
,
M
, an
d
S
t
e
i
n
er
, S
. H
.
,
“
A
M
ul
t
i
va
r
i
a
t
e
Rob
us
t
Cont
rol
Ch
a
rt
for Indi
vi
d
ua
l
O
bs
e
rva
t
i
ons
,
”
Q
ual
i
t
y
T
e
c
hn
ol
ogy
.
,
vol
.
41
,
no
.
3,
pp.
259
-
271,
2009.
[26]
J
e
ns
e
n,
W
.
A
,
Bi
rc
h,
J
.
B
a
nd
W
ooda
l
l
,
W
.
H
.
,
“
H
i
gh Br
e
a
kd
ow
n E
s
t
i
m
a
t
i
on
M
e
t
hods
for P
h
a
s
e
I
M
ul
t
i
v
a
ri
a
t
e
Cont
rol
Ch
a
rt
s
Q
ua
l
i
t
y
,”
R
e
lia
b
ilit
y
En
g
in
e
e
r
i
ng
Int
e
r
nat
i
onal
,
v
ol
.
23
,
no
.
5
,
pp
.
615
-
629,
2007
.
[27]
H
o
lme
s
, D
. S
.
,
a
n
d
Me
r
g
en
, A
.
E
.,
“
Id
e
nt
i
fyi
ng
t
he
s
ourc
e
s
for
o
ut
of
c
ont
ro
l
s
i
g
na
l
s
w
h
e
n
t
he
T
2 c
ont
ro
l
c
ha
rt
i
s
us
e
d,
”
Q
u
a
l
i
t
y
E
ngi
ne
e
r
i
ng
,
vol
.
8,
no
.
1
,
pp
.
137
-
143,
1995
.
[28]
V
ar
g
as
, J
. A
.,
“
Robus
t
E
s
t
i
m
a
t
i
on i
n
M
ul
t
i
v
a
ri
a
t
e
Cont
rol
Cha
r
t
s
for Ind
i
vi
dua
l
O
bs
e
rva
t
i
on,
”
Q
ual
i
t
y
T
e
c
hnol
og
y
,
vol
.
35
,
pp
.
367
-
376,
2003
.
Evaluation Warning : The document was created with Spire.PDF for Python.