Professional Documents
Culture Documents
Edpsy 580
Carolyn J. Anderson
Department of Educational Psychology
I L L I N O I S
UNIVERSITY OF ILLINOIS AT URBRANA - CHAMPAIGN
Correlation
Slide 1 of 38
Statistical Inference.
Coefficient
Fishers Z -Transformation
Correlation
Bi-variate regression
Multiple regression
Slide 2 of 38
Statistical Inference
Correlation
Fishers Z-Transformation.
Test of Ho : = K.
Slide 3 of 38
coefficient
How r Works
Examples of Different r s
Examples of Different r s
Non-Linear Relationships
Properties: Correlation
Coefficient
Properties: Correlation
Coefficient
Inference & the Correlation
Coefficient
Fishers Z -Transformation
Correlation
Slide 4 of 38
Correlation
Slide 5 of 38
r = sample correlation.
Formal definition
Statistics
Definition: Correlation
coefficient
How r Works
Examples of Different r s
Examples of Different r s
Non-Linear Relationships
Properties: Correlation
Coefficient
Properties: Correlation
Coefficient
Fishers Z -Transformation
Correlation
sxy
cov(X, Y )
=
sx sy
sx sy
Pn
1
i Y )
X)(Y
q
q
Pn
Pn
1
1
2
2
i=1 (Xi X)
i=1 (Yi Y )
n1
n1
Pn
2
(X
X)
i
i=1
i=1 (Yi Y )
n1
i=1 (Xi
How r Works
r=
Outline: Pearson Correlation
Coefficient
n
i=1 (Xi
n
i=1 (Xi
X)(Y
i Y)
2
X)
n
i=1 (Yi
Y )2
zxi zyi
i=1
Correlation
Slide 7 of 38
Examples of Different rs
Correlation
Slide 8 of 38
Examples of Different rs
Correlation
Slide 9 of 38
Non-Linear Relationships
r=0
Correlation
Slide 10 of 38
1 r +1
Statistics
Definition: Correlation
coefficient
How r Works
Examples of Different r s
Examples of Different r s
Non-Linear Relationships
Properties: Correlation
Coefficient
Properties: Correlation
Coefficient
Correlation
Slide 11 of 38
Statistics
Definition: Correlation
coefficient
How r Works
Examples of Different r s
Examples of Different r s
Non-Linear Relationships
Properties: Correlation
Coefficient
Properties: Correlation
Coefficient
Correlation
Slide 12 of 38
= 0&
x2 ,
y ,
y2 ,
and xy
Hypothesis Testing
Hypothesis Testing
Example Hypothesis Testing
for
Alternative Method
Alternative Method
Alternative Method
Alternative Method
Computing Correlations: SAS
Fishers Z -Transformation
Correlation
Slide 13 of 38
= 0&
Hypothesis Testing
Hypothesis Testing
Example Hypothesis Testing
for
Alternative Method
Alternative Method
Alternative Method
Alternative Method
Computing Correlations: SAS
Fishers Z -Transformation
Correlation
Slide 14 of 38
= 0&
Hypothesis Testing
Hypothesis Testing
Example Hypothesis Testing
r=0
Marginal distributions of X and Y are not normal:
for
Alternative Method
Alternative Method
Alternative Method
Alternative Method
Computing Correlations: SAS
Fishers Z -Transformation
Correlation
Slide 15 of 38
Hypothesis Testing
Assumptions:
X and Y are random variables whose joint distribution is
bivariate normal.*** qualification.
Observations are independent.
= 0&
Hypothesis Testing
Hypothesis Testing
Example Hypothesis Testing
for
Alternative Method
Alternative Method
Alternative Method
Alternative Method
Computing Correlations: SAS
Fishers Z -Transformation
Correlation
Slide 16 of 38
Hypothesis Testing
(1r 2 )
n2
= 0&
Hypothesis Testing
Hypothesis Testing
Example Hypothesis Testing
for
Alternative Method
Alternative Method
Alternative Method
Alternative Method
Computing Correlations: SAS
Fishers Z -Transformation
Correlation
Slide 17 of 38
= 0&
6002
Hypothesis Testing
Hypothesis Testing
Example Hypothesis Testing
for
Alternative Method
Alternative Method
Alternative Method
Alternative Method
Computing Correlations: SAS
Fishers Z -Transformation
Correlation
Slide 18 of 38
Alternative Method
or
observed
= 0&
Take
t=
Hypothesis Testing
Hypothesis Testing
Example Hypothesis Testing
for
Alternative Method
r
(1r2 )
n2
=r
(n 2)
(1 r2 )
and r as a function of t.
Alternative Method
Alternative Method
Alternative Method
Computing Correlations: SAS
Fishers Z -Transformation
Correlation
Slide 19 of 38
Alternative Method
= 0&
Hypothesis Testing
Hypothesis Testing
Example Hypothesis Testing
for
Alternative Method
t= q
r
(1r 2 )
(n2)
Alternative Method
Computing Correlations: SAS
(n 2)
= rp
(1 r)2
(n 2)
1 r2
t2
r2
r2 )
t
(n 2)
r2
t2
(n 2)
r2 (1 + t2 /(n 2))
t2
(n 2)(1 + t2 /(n 2))
2 (1
Alternative Method
Alternative Method
Fishers Z -Transformation
Correlation
Slide 20 of 38
Alternative Method
So
= 0&
Hypothesis Testing
Hypothesis Testing
Example Hypothesis Testing
for
Alternative Method
tcrit
rcrit = p
(n 2)(1 + t2crit /(n 2))
Any correlation > .08 (or < .08) would be significant for
n = 600.
Note: Statistical significance does not imply importance.
Alternative Method
Alternative Method
Alternative Method
Computing Correlations: SAS
Fishers Z -Transformation
Correlation
Slide 21 of 38
Alternative Method
= 0&
Hypothesis Testing
Science
(p-value)
Hypothesis Testing
Example Hypothesis Testing
for
Alternative Method
Alternative Method
Alternative Method
Alternative Method
.32
(< .01)
.07
(.09)
.12
(< .01)
Correlation
Slide 22 of 38
or
PROC CORR;
VAR rdg sci locus concpt mot;
ASSIST
ANALYST
= 0&
Hypothesis Testing
Hypothesis Testing
Example Hypothesis Testing
for
Alternative Method
Alternative Method
Alternative Method
Alternative Method
Computing Correlations: SAS
Fishers Z -Transformation
Correlation
Slide 23 of 38
Fishers Z-Transformation
Correlation
Slide 24 of 38
Fishers Z-Transformation
Fishers Z-Transformation:
1
Z = ln
2
1+r
1r
where
Fishers Z -Transformation
How Fishers
Z -Transformation Works
. . . and for Smaller
Samples. . .
Sampling Distribution of
Fishers Z
Fishers Z -Transformation
Fishers Z -Transformation
Using Fishers Z
Example Using Fishers Z
Confidence Interval for
Confidence Interval for
Fishers Z in SAS
Two Independent Group Test
Two Independent Group Test
Example Two Independent
Group Test
Example Two Independent
if
expa = x then
ln(x) = a
Group Test
Correlation
Slide 25 of 38
Fishers Z-Transformation
Correlation
Slide 26 of 38
Correlation
Slide 27 of 38
Correlation
Slide 28 of 38
IF Observations
Are from a bivariate normal distribution.
Are independent across individuals.
n 10
2
THEN the sampling distribution of Z is N (Z , Z
) where
Fishers Z -Transformation
Fishers Z -Transformation
E(Z) = Z = Z
Fishers Z -Transformation
Fishers Z -Transformation
How Fishers
Z -Transformation Works
. . . and for Smaller
2
Z
Samples. . .
Sampling Distribution of
Fishers Z
Using Fishers Z
Example Using Fishers Z
Group Test
Correlation
1
ln
2
1
n3
1+
1
+
2(n 1)
Slide 29 of 38
Using Fishers Z
Correlation
Slide 30 of 38
Test statistic is
Zobs Znull
.0416
.2138 .2554
z=
=
= 1.016
=
Z
.04093
.04093
Samples. . .
Sampling Distribution of
Fishers Z
Using Fishers Z
Example Using Fishers Z
Confidence Interval for
Confidence Interval for
Retain Ho . . . .
Note: a lower case z is used for the test statistic and upper
case Z is denotes Fishers Z-transformed value of r.
Fishers Z in SAS
Two Independent Group Test
Two Independent Group Test
Example Two Independent
Group Test
Example Two Independent
Group Test
Correlation
Slide 31 of 38
Steps:
z/2 Z
Group Test
Correlation
Slide 32 of 38
e2Z 1
r = 2Z
e +1
Our example
Fishers Z -Transformation
Fishers Z -Transformation
Fishers Z -Transformation
Fishers Z -Transformation
How Fishers
Z -Transformation Works
. . . and for Smaller
Samples. . .
Sampling Distribution of
Fishers Z
Using Fishers Z
Example Using Fishers Z
Confidence Interval for
Confidence Interval for
Fishers Z in SAS
Two Independent Group Test
Two Independent Group Test
Example Two Independent
Group Test
Example Two Independent
rlower
rupper
e2(.1336) 1
.3063
2.71828.2672 1
=
= .1328
=
.2672
2(.1336)
2.71828
+1
2.3063
e
+1
.8004
e2(.2940) 1
2.71828.5880 1
=
= .2858
=
2.71828.5880 + 1
2.8004
e2(.2940) + 1
Group Test
Correlation
Slide 33 of 38
Fishers Z in SAS
Group Test
Correlation
Slide 34 of 38
- slide -
34-1
Statistical hypotheses:
Ho : 1 = 2
vs
Ha : 1 6= 2
Assumptions:
Correlation
Slide 35 of 38
Test Statistic:
z=
Z1 Z2
Z1 Z2
where
Z1 and Z2 are Fisher Z-transformations of the sample
correlations, r1 and r2 , from the two groups.
Samples. . .
Sampling Distribution of
Fishers Z
Using Fishers Z
Example Using Fishers Z
Confidence Interval for
Confidence Interval for
Standard deviation,
r
q
2 + 2 =
Z1 Z2 = Z
Z2
1
1
1
+
n1 3 n2 3
Why?
Fishers Z in SAS
Two Independent Group Test
Two Independent Group Test
Example Two Independent
Group Test
Example Two Independent
Group Test
Correlation
Slide 36 of 38
Statistical hypotheses:
Ho : male = f emale vs Ha : male 6= f emale
Assumptions:
. . . so whats dependent?
Group Test
Correlation
Slide 37 of 38
Zf emale
Coefficient
Fishers Z -Transformation
Fishers Z -Transformation
Zmale
Fishers Z -Transformation
Fishers Z -Transformation
How Fishers
Z -Transformation Works
. . . and for Smaller
Samples. . .
Sampling Distribution of
Fishers Z
Using Fishers Z
Example Using Fishers Z
Confidence Interval for
Confidence Interval for
Fishers Z in SAS
Two Independent Group Test
Two Independent Group Test
Example Two Independent
Group Test
Example Two Independent
(Zm Zf )
z
1 + .28250
1
1
ln
= (.5808) = .29040
2
1 .28250
2
1 + .40196
1
1
ln
= (.85197) = .425980
=
2
1 .40196
2
s
r
1
1
1
1
+
=
+
= .08240
=
nmale 3 nf emale 3
324 270
.42598 .29040
= 1.645
.08240
Group Test
Correlation
Slide 38 of 38