Lecture 14a T Test Dep

T-TEST FOR CORRELATED OR DEPENDENT SAMPLES
It is a test of difference applied to one group of samples which can be used to evaluate a certain
program or treatment. It is applied when the mean before (pretest) and the mean after (posttest) are
being compared. The pretest is measured, the treatment of intervention is applied and then the
posttest is likewise measured. Then the 2 means are compared. This test is used to find out if there is a
difference that exist between the BEFORE and AFTER means. If there is a difference in favor of the
POSTTEST, then the treatment or intervention is EFFECTIVE. On the otherhand, if there is no significant
difference, then the treatment is NOT EFFECTIVE.
Formula:
D
√
2
t = Ʃ D 2−
( ƩD )
n
n ( n−1 )
where:
t = t-test
D = mean difference between the pretest and posttest
ƩD = summation of the difference between the pretest and posttest
ƩD2 = sum of squares of the difference between the pretest and posttest
n = sample size
Example:
Problem: A study was conducted on the effectiveness of learning modules in Mathematics on the
performance of 20 selected learners in Grade 8. The pretest was administered before the
program was implemented. At the end of the quarter, the same instrument was used to get
the posttest result. Below is the table showing the result of the experiment. Test the null
hypothesis that there is no significant difference between the result of the pretest and
posttest. Use the t-test at 5% level of significance.
Pretest (x1) 20 30 1 15 20 1 18 14 15 2 18 15 1 20 18 40 1 10 12 20
0 0 0 5 0
Posttest (x2) 25 35 2 25 20 2 22 20 20 1 30 10 1 25 10 45 1 10 18 25
5 0 5 6 5
1. State the Ho
There is no significant difference between the pretest and posttest. OR
The use of modules is not effective in increasing the performance of the learners in Mathematics.
(Ho = Ha)
2. Level of Significance:
α = 0.05
df = n – 1 degree of freedom
= 20 - 1
= 19
ttv = 1.729 (Tabular t-value at 0.05 one-tailed) /2.093 (Tabular t-value at 0.05 two-tailed)
3. Get the difference between the scores of each x 1 and x2, the (D). Get the summation of the
difference between the pretest and posttest (ƩD = -81).
PRETEST (x1) POSTTEST (x2) D

20 25 -5
30 35 -5
10 25 -15
15 25 -10
20 20 0
10 20 -10
18 22 -4
14 20 -6
15 20 -5
20 15 5
18 30 -12
15 10 5
15 16 -1
20 25 -5
18 10 8
40 45 -5
10 15 -5
10 10 0
12 18 -6
20 25 -5
ƩD = -81
4. Square each D and then get their summation (ƩD2 = 947).
PRETEST (x1) POSTTEST (x2) D D2
20 25 -5 25
30 35 -5 25
10 25 -15 225
15 25 -10 100
20 20 0 0
10 20 -10 100
18 22 -4 16
14 20 -6 36
15 20 -5 25
20 15 5 25
18 30 -12 144
15 10 5 25
15 16 -1 1
20 25 -5 25
18 10 8 64
40 45 -5 25
10 15 -5 25
10 10 0 0
12 18 -6 36
20 25 -5 25
2
ƩD = -81 ƩD = 947
5. Find D .
ƩD −81
D= = = -4.05
n 20
6. Compute for t by using the formula.
√
2
t = 2 ( ƩD )
ƩD −
n
n ( n−1 )
−4.05
√
2
t = (−81 )
947−
20
20 ( 20−1 )
−4.05
√
( 6,561 )❑
t = 947−
20
20 (19 )
−4.05 −4.05
−4.05 −4.05
t
t =
√ 947−328.05 =
380 √618.95 =
380
√ 1.63
= =
1.28
= -3.16 computed value of
Result : tcv = 3.16 > ttv = 1.729 (disregard the negative sign)
Decision : Reject Ho (Rule: If the computed t-value is greater than or beyond the critical value,
reject Ho)
Conclusion : There is a significant difference between the pretest and posttest in favor of the
posttest. This further implies that the use of learning modules is effective in increasing
the performance of the learners in Mathematics.
Problem Solving:
1. Ten samples were chosen for an experiment to perform a certain physical activity. The number of
heartbeats per minute, before and after the experiment were recorded as follows:
x Before After
1 60 92
2 67 79
3 72 72
4 71 80
5 68 70
6 72 71
7 71 68
8 69 79
9 75 80
10 68 76
2. Test at 5% level of significance if there is a significant difference between the results of the pretest
and posttest after 15 students were exposed to a learning strategy.
x Before After D D2
1 25 26
2 13 15
3 28 30
4 10 15
5 20 21
6 11 10
7 23 21
8 20 22
9 15 17
10 15 20
11 22 25
12 21 24
13 14 15
14 10 11
15 19 24

Lecture 14a T Test Dep

Uploaded by

Copyright:

Available Formats

Lecture 14a T Test Dep

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Lecture 14a T Test Dep

Uploaded by

Copyright:

Available Formats

T-TEST FOR CORRELATED OR DEPENDENT SAMPLES

PRETEST (x1) POSTTEST (x2) D

6. Compute for t by using the formula.

You might also like

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.