312
LINEAR
REGRESSION
continued
bestfit
line
folloss
a
Gaussian
distribution,
and
that
the
standard
deviation
is
the
same
at
e
er)
\
alue
of
the
dependent
variable.
These
assumptions
are
rarely
true
after
transforming
data.
As
a
consequence
of
the
last
conclusion,
some
analysts
suggest
that
rather
than
using
linear
transformations.
nonlinear
regression
should
be
employed
to
fit
curvilinear
data.
in
this
approach.
a
bestfit
curve
is
developed
that
directly
minimizes
the
untransformed
residuals,
We
will
describe
how
this
is
done
in
Chap.
14.
PROBLEMS
8.8
0.5
9.8
9.4
10.0
9.4
10.1
9.2
11.3
9.4
10.0
10.4
7.9
10.4
9.8
9.8
9.5
8.0
8.8
10.6
10.1
9.5
9.6
10.2
8.9
Determine
(a)
the
mean,
(b)
median,
(c)
mode,
(d)
range.
(e)
standard
deviation.
(f)
sariance.
and
(g)
coefficient
of
ariation.
1
13.2
Construct
a
histogram
from
the
data
from
Prob.
13.1
L
se
a
range
front
7.5
to
11.5
with
inlers
als
of
0.5.
13.3
Given
the
data
28.65
2655
26,65
2765
27.35
28.35
26.85
28.65
29.65
27.85
27.05
28.25
28.85
26.5
27.65
28.45
28.65
28.45
31.65
26.35
27.75
29.25
2’.65
2.65
27.65
28.55
2’.65
2.25
Determine
(a)
the
mean,
bj
median,
(c)
mode.
d)
lange.
tel
standaid
des
iation.
(1)
s
ariance.
and
(gi
coefficient
of
S
ariation.
dii
Construct
a
histogram.
I
SC
a
I
ange
trun
2n
to
32
v.
ith
increments
f
I
iS.
(I)
Assunting
that
the
distribution
is
normal,
and
that
rour
et
in
late
of
the
standard
des
iation
is
al
id.
compute
the
range
that
is.
the
loss
ci
atid
thc
upper
salues
that
en
compasses
6S’
of
the
readings.
This preview has intentionally blurred sections. Sign up to view the full version.
View Full Document
This is the end of the preview.
Sign up
to
access the rest of the document.
 Spring '10
 Vorobyov
 Linear Regression, Normal Distribution, Regression Analysis, Standard Deviation, des iation

Click to edit the document details