Professional Documents
Culture Documents
Regression Analysis
Regression Analysis
Scatter plots
Regression analysis requires
interval and ratio-level data.
To see if your data fits the models
of regression, it is wise to conduct
a scatter plot analysis.
The reason?
Regression analysis assumes a linear
relationship. If you have a curvilinear
relationship or no relationship,
regression analysis is of little use.
Types of Lines
e
rs
n
o
lIn
a
c
m
o
P
e
rC
it,c
p
a
u
re
td
n
o
la
rs
,
1P
9
Scatter plot
M
h
c
2O
0
tim
s
aB
te
sc
r15c
e
to
fP
p
o
la
u
tio
n
5y
e
rs
a
n
d
e
v
rw
h
h
lo
r'0.3s
D
g
e
ro
M
r35.e
o
,0
.0n
.2
0
2
5
2
.0
00P
2
5
2
3
0
50
3
0
4
erc
P
to
n
fP
plu
tio
a
n
w
th
ace
B
h
rlo
D
'seg
rey
b
P
rs
eo
a
n
lIc
o
m
P
e
rC
pit
a
This is a linear
relationship
It is a positive
relationship.
As population with
BAs increases so
does the personal
income per capita.
e
rs
n
o
lIn
a
c
m
o
P
e
rC
it,c
p
a
u
re
td
n
o
la
rs
,
1P
9
Regression Line
M
h
c
2O
0
tim
s
aB
te
sc
r15c
e
to
fP
p
o
la
u
tio
n
5y
e
rs
a
n
d
e
v
rw
h
h
lo
r'0.3s
D
g
e
r.54235.e
,0
.0n
.2
0
2
5
2
.0
00P
2
qr
S
R
io
L
rM
a
e
n
0o
=
2
5
0
3
50
3
0
4
erc
P
to
n
fP
plu
tio
a
n
w
th
ace
B
h
rlo
D
'seg
rey
b
P
rs
eo
a
n
lIc
o
m
P
e
rC
pit
a
Regression line is
the best straight
line description of
the plotted points
and use can use it
to describe the
association between
the variables.
If all the lines fall
exactly on the line
then the line is 0
and you have a
perfect relationship.
Things to remember
Regressions are still focuses on
association, not causation.
Association is a necessary
prerequisite for inferring
causation, but also:
1. The independent variable must
preceded the dependent variable in
time.
2. The two variables must be plausibly
lined by a theory,
3. Competing independent variables
must be eliminated.
e
n
o
rs
lIn
a
o
c
e
m
rC
P
p
a
it,c
re
u
td
n
la
o
,
rs
1P
9
Regression Table
0O
2
h
tim
s
aith
sB
e
rc
e
fP
pu
ti2o
la
n
eM
y
5
rscn
a
d
v25e
ch
a
lo
e
g
e
D
rM
15n
.0to
0.2
.0rw
30.r's
20P
qLineao
S
0.5e
r=
4235.0,
03250 R
The regression
coefficient is not a
good indicator for
the strength of the
relationship.
Two scatter plots
with very different
dispersions could
produce the same
regression line.
rs
e
P
n
o
lIc
a
m
o
P
e
rC
it,c
p
a
u
n
re
td
rs
la
o
,1
9
40350n
P
rc
e
tofP
ula
p
tion
w
ithB
ac
elo
h
r's
eg
D
re
by
P
on
rs
e
lIco
a
eP
m
ap
rC
ita
p
o
latio
nP
e60rS
q
ae
i80l.R10SqLi.near=0.461203.
M
40.u
.u
200.20. P
03250
40350n
P
rc
e
to
fP
pu
tio
la
nw
thB
he
c
a
r's
lo
D
gre
e
by
P
rso
e
na
lIco
m
P
e
rC
pit
a
Regression coefficient
The regression coefficient is the
slope of the regression line and
tells you what the nature of the
relationship between the variables
is.
How much change in the
independent variables is associated
with how much change in the
dependent variable.
The larger the regression coefficient
the more change.
Pearsons r
To determine strength you look at
how closely the dots are clustered
around the line. The more tightly
the cases are clustered, the
stronger the relationship, while the
more distant, the weaker.
Pearsons r is given a range of -1 to
+ 1 with 0 being no linear
relationship at all.
R
.736a
R Square
.542
Adjusted
R Square
.532
Std. Error of
the Estimate
2760.003
R-Square
Model Summary
Model
1
R
.736a
R Square
.542
Adjusted
R Square
.532
Std. Error of
the Estimate
2760.003
Adjusted R-square
Model Summary
Model
1
R
.736a
R Square
.542
Adjusted
R Square
.532
Std. Error of
the Estimate
2760.003
ANOVA
ANOVAb
Model
1
Regression
Residual
Total
Sum of
Squares
4.32E+08
3.66E+08
7.98E+08
df
1
48
49
Mean Square
432493775.8
7617618.586
F
56.775
Sig.
.000a
Coefficients
Coefficientsa
Model
1
(Constant)
Percent of Population
25 years and Over
with Bachelor's
Degree or More,
March 2000 estimates
Unstandardized
Coefficients
B
Std. Error
10078.565
2312.771
688.939
91.433
Standardized
Coefficients
Beta
.736
t
4.358
Sig.
.000
7.535
.000
Coefficients
Coefficientsa
Model
1
(Constant)
Percent of Population
25 years and Over
with Bachelor's
Degree or More,
March 2000 estimates
Population Per
Square Mile
Unstandardized
Coefficients
B
Std. Error
13032.847
1902.700
Standardized
Coefficients
Beta
t
6.850
Sig.
.000
517.628
78.613
.553
6.584
.000
7.953
1.450
.461
5.486
.000
Coefficients
Coefficientsa
Model
1
(Constant)
Percent of Population
25 years and Over
with Bachelor's
Degree or More,
March 2000 estimates
Unstandardized
Coefficients
B
Std. Error
10078.565
2312.771
688.939
91.433
Standardized
Coefficients
Beta
.736
t
4.358
Sig.
.000
7.535
.000
Independent variables
Percent population with BA
R2
Number of Cases
Single
Multiple
Regression
Model Summary
Model
1
R
.736a
Model Summary
Adjusted
R Square
.532
R Square
.542
Std. Error of
the Estimate
2760.003
Model
1
R
.849a
Regression
Residual
Total
Sum of
Squares
4.32E+08
3.66E+08
7.98E+08
df
1
48
49
ANOVAb
Mean Square
432493775.8
7617618.586
F
56.775
Sig.
.000a
Model
1
Regression
Residual
Total
(Constant)
Percent of Population
25 years and Over
with Bachelor's
Degree or More,
March 2000 estimates
688.939
91.433
df
2
47
49
Mean Square
287614518.2
4742775.141
F
60.643
Sig.
.000a
Coefficientsa
Coefficientsa
Unstandardized
Coefficients
B
Std. Error
10078.565
2312.771
Sum of
Squares
5.75E+08
2.23E+08
7.98E+08
Model
1
Std. Error of
the Estimate
2177.791
ANOVAb
Model
1
Adjusted
R Square
.709
R Square
.721
Standardized
Coefficients
Beta
.736
t
4.358
7.535
Sig.
.000
.000
Model
1
(Constant)
Percent of Population
25 years and Over
with Bachelor's
Degree or More,
March 2000 estimates
Population Per
Square Mile
Unstandardized
Coefficients
B
Std. Error
13032.847
1902.700
Standardized
Coefficients
Beta
t
6.850
Sig.
.000
517.628
78.613
.553
6.584
.000
7.953
1.450
.461
5.486
.000
Single Regression
Independent variables
Percent population with BA
R2
Number of Cases
Multiple Regression
Independent variables
Percent population with BA
Population Density
R2
Adjusted R2
Number of Cases
Perceptions of victory
Regression