Scribd
Upload
3 views2 pages

Split

The document outlines two methods for measuring test reliability: the Split-Half Method and the Kuder-Richardson 20. It provides formulas and computations for each method, indicating that the Split-Half Method yields a moderate relationship (r = 0.33) while the Kuder-Richardson 20 shows moderate reliability as well. Key values and interpretations are included to support the findings.

Uploaded by

arcenarhea1
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
3 views2 pages

Split

The document outlines two methods for measuring test reliability: the Split-Half Method and the Kuder-Richardson 20. It provides formulas and computations for each method, indicating that the Split-Half Method yields a moderate relationship (r = 0.33) while the Kuder-Richardson 20 shows moderate reliability as well. Key values and interpretations are included to support the findings.

Uploaded by

arcenarhea1
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

SPLIT-HALF METHOD WHOLE TEST METHOD

formula: formula:
𝟔𝜮 ⅆ𝟐 2(𝑟ℎ𝑎𝐿𝑓 )
𝜞=𝟏− 𝟑 𝑟𝑓𝑢𝑙𝑙 =
𝒏 −𝒏 1 + 𝑟ℎ𝑎𝑙𝑓
where: 𝑟𝑓𝑢𝑙𝑙 = 2(0.33)
N= the number of students who took the exam 1+ 0.33
d2= is the difference between two ranks
𝑟𝑓𝑢𝑙𝑙 = 0.66
Rhalf= is the reliability of half test
0.33
values: 𝑟𝑓𝑢𝑙𝑙 = 0.4962 or 0.50
n= 40
𝜮 ⅆ𝟐 = 7193 interpretation:
r= 0.33 The reliability of the test in split half method has a strong
computation: relationship
1−6(7193)
rht=
(40)3 −40
1−43158
rht=
64000−40
1−43158
rht=
63960
rht= 1-0.67
rht= 0.33
interpretation: moderate relationship
KUDER-RICHARDSON 20

formula:
𝒌 𝟏 − 𝜮𝒑𝒒
𝑲𝑹𝟐𝟎 = [ ]
𝒌−𝟏 𝒔𝟐 computations:
𝒌 𝟏 − 𝜮𝒑𝒒
𝑲𝑹𝟐𝟎 = [ ]
where: 𝒌−𝟏 𝒔𝟐
K= is the number of test scores
p= is the proportion of the examinees who got the item 𝟑𝟎 𝟏 − 𝟓. 𝟕𝟒⬚
correct 𝑲𝑹𝟐𝟎 = [ ]
𝟑𝟎 − 𝟏 𝟏𝟔. 𝟏
q= is the proportion of the examinees who got the item
incorrect 𝑲𝑹𝟐𝟎 = 1.03448 x 0.64
𝒔𝟐= is the variance of the scores
𝑲𝑹𝟐𝟎 = 𝟎. 𝟔𝟔
∑pq= is the summation of the product of p and q

values:
Interpretation:
K=30 The reliability of the test in Kuder-Richardson20 is
∑pq= 5.74 Moderate.
𝒔𝟐 = 16.1

You might also like