Scribd
Upload
54 views3 pages

Continued Report

This document outlines the steps for analyzing test results to determine item discrimination: 1) Arrange test scores from lowest to highest; 2) Determine the upper and lower 27% of scores; 3) Tally responses of these groups; 4) Record frequency counts; 5) Compute discrimination indices by calculating (number right in top group - number right in bottom group) / half the sample size; 6) Examine indices using benchmarks to identify poorly discriminating items.

Uploaded by

Banaag Jay
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
54 views3 pages

Continued Report

This document outlines the steps for analyzing test results to determine item discrimination: 1) Arrange test scores from lowest to highest; 2) Determine the upper and lower 27% of scores; 3) Tally responses of these groups; 4) Record frequency counts; 5) Compute discrimination indices by calculating (number right in top group - number right in bottom group) / half the sample size; 6) Examine indices using benchmarks to identify poorly discriminating items.

Uploaded by

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

ITEM DISCRIMINATION

Steps in Analyzing Test Result


1.Arrange test scores from lowest to
highest.
2.Determine the upper and lower
27%.
3.Tally responses of the upper and
lower.

ITEM DISCRIMINATION

4.Indicate frequency counts in the


item analysis worksheet.
5. Compute the discrimination
indices.
6. Examine the discrimination
indices using the range.

DISCRIMINATION INDEX

Number of students in the lowest groupwho


got the item right (RL) from the number in
the highest who got it right (RH) and divide
by half of the samplke size (1/2n)

RH - RL
Discrimination index = ---------------------1/2n

You might also like