0% found this document useful (0 votes)
127 views

Test Analysis

Uploaded by

Alona Paña
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
127 views

Test Analysis

Uploaded by

Alona Paña
Copyright
© © All Rights Reserved
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 15

TEST ITEM ANALYSIS

OBJECTIVES
At the end of the session, the students must
be able to;
define and know all about Test Item Analysis
Assess the quality of those items and of the
test as a whole
learn to compute on how to get the validity of
the test items and the test as a whole.
What is Test Item Analysis ?

It is a process which examines student


responses to individual test items
(questions) in order to assess the quality
of those items and of the test as a
whole.
 Item analysis will help us in selecting
the items that are of average difficulty.
PURPOSE OF ITEM ANALYSIS
1. It is the process of
examining the student’s
responses to each item.
2. The need to look into
the difficulty and
discriminating ability of the
item as well as the
effectiveness of each
alternative.
3. To select the best available
items for the final form of the
test
4. To identify structural or
content defects in the items.
5. To detect learning difficulties of
the class as a whole.

6. To identify the areas of


weaknesses of students in need of
remediation.
WHY DO WE NEED TO
ANALYZE TEST ITEM?
1. Item analysis are intended to
assess and improve the
reliability of the test. If the test
reliability is low, test validity
will necessary also be low.
2. This is the ultimate reason
you do item analysis-to improve
the validity of a test by
improving its reliability.
STEPS IN DOING THE ITEM
ANALYSIS
1.Rank the scores of the students from highest score to the
lowest score.
2.Select and identify the top 27% performing group/upper
group and bottom 27% performing from the lower group.
or get the 1/3 of the papers from the upper group and 1/3
from the lower group
3.Set aside the remaining 46% because they will not be used
for item analysis.
4. Tabulate the number of students in the upper group and
lower group based on their selected choice per item.
Index of Difficulty
Index of difficulty= ΣX
N

Where:
ΣX= sum of the right responses
of UG and LG
N = total no. of UG and LG
To determine if the item is
easy or difficult
if index of difficulty is
50%= the item is neither easy or
difficult

51% and above = easy question


49% and below= difficult question
Index of Discrimination

Index of Discrimination = RU – RL
NG

Where : RU = Right responses in the UG


RL = Right responses in LG
NG = no. of students in each group
 The index of discriminating
power is below one (1) the test
item must retained. This happen
when the learners from the upper
group got the correct response
and not from the lower group.
 If the index of discriminating is
1, the item is 50% level of
difficulty.
 Negative discriminating power is
obtained when more students from
the lower group got the right
responses than the upper group.
Classical Item and Test
Analysis Spreadsheet (CITAS)
…is a next-generation diagnostic
system that consolidates and
displays all patient data in a single
platform.

Item analysis includes item difficulty,


reliability, item discrimination, and
relation of the item to the scale to
which it has been assigned.
Classical Item and Test
Analysis Spreadsheet
What is CITAS? The Classical Item and Test Analysis
Spreadsheet (CITAS) is a simple tool to statistically
analyze small-scale assessments, CITAS is a Microsoft
Excel® spreadsheet with all necessary calculations
programmed in as formulas, which means that all the
user is required to do it type or paste in the student
responses and the correct answers, or keys. CITAS will
then score all students with number-correct (NC)
scoring, as well as populate important statistics.
Statistics include both test-level statistics such as
reliability, and item-level statistics such as difficulty
(P) and discrimination (rpbis).

You might also like