Scribd
Upload
52 views4 pages

Comparing Two Mean Vectors: Review of Univariate Two-Sample Paired T-Test

This document summarizes the paired t-test, a statistical test used to determine whether the means of two sets of observations are different, when these sets are paired or dependent in some way. It describes how to calculate the test statistic and determine whether to reject the null hypothesis that the means are equal, based on comparing the calculated test statistic to critical values from the t-distribution. It also briefly discusses extending the test to the multivariate case with multiple dependent variables.

Uploaded by

Selva Kumar
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
52 views4 pages

Comparing Two Mean Vectors: Review of Univariate Two-Sample Paired T-Test

This document summarizes the paired t-test, a statistical test used to determine whether the means of two sets of observations are different, when these sets are paired or dependent in some way. It describes how to calculate the test statistic and determine whether to reject the null hypothesis that the means are equal, based on comparing the calculated test statistic to critical values from the t-distribution. It also briefly discusses extending the test to the multivariate case with multiple dependent variables.

Uploaded by

Selva Kumar
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 4

COMPARING TWO MEAN VECTORS

PAIRED OBSERVATIONS TEST



Review of Univariate Two-Sample paired t-test


Pair
no.
Treatment 1 Treatment 2 Difference
d
i =
y
i
- x
i

1 y
1
x
1
d
1

2 y
2
x
2
d
2

. . . .
. . . .
n y
n
x
n
d
n


Assumption: y and x have a bivariate normal distribution with
|
|
.
|

\
|
= E
|
|
.
|

\
|
=
2
2
x xy
yx y
x
y
and
o o
o o

Review of Univariate Two-Sample paired t-test (contd.)



It follows that

d
i =
y
i
- x
i
is
( )
2
,
d x y
N o

Where
( )
2 2 2
2
x yx y d
o o o o + =

Calculations:

( )

=
n
i
i d
d d
n
s
1
2
2
1
1


To test H
0
:
y
=
x
that is, H
0
:
d
=0
We use
Or


and d
n
d
n
i
i

=
=
1
1
1
|
.
|

\
|
=
|
.
|

\
|
=
n
s
d
n
s
d
t
d
d
( )
1
2
2
2

=
d
s d n t
MULTIVARIATE CASE

Pair
no.
Treatment 1 Treatment 2 Difference
d
i =
y
i
- x
i

1 y
1
x
1
d
1

2 y
2
x
2
d
2

. . . .
. . . .
n y
n
x
n
d
n

To test
H
0
:
y
=
x
that is,
H
0
:
d
=0
Calculations:

( ) ( )

=

'

=
n
i
i i
d
d d d d
n
S
1 1
1




Then


Test Criterion
Reject H
0
if T
2
>T
2
o,p,n-1


and d
n
d
n
i
i
=
=
1
1
( ) d S d n d
n
S
d T
d
d
1
/
1
/
2

=
|
.
|

\
|
=

You might also like