0% found this document useful (0 votes)
3 views2 pages

Reliability Item Analysis Process

Uploaded by

Michael Suplaag
Copyright
© All Rights Reserved
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
0% found this document useful (0 votes)
3 views2 pages

Reliability Item Analysis Process

Uploaded by

Michael Suplaag
Copyright
© All Rights Reserved
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

Instrument Reliability Improvement through Item Analysis

This document presents the step-by-step process used to analyze and improve the
reliability of the pretest instrument used in the study entitled: “Instructional Design and
Effects of an Interactive, Contextualized Technical Vocabulary Module on Automotive
Technology Learning Among Senior High School Students.”

Step 1: Initial Reliability Test


Cronbach’s Alpha was computed using the formula:

α = (k/(k−1)) [1 − (Σσ²_i / σ²_total)]

Step 2: Item Difficulty Analysis


Item difficulty was computed as the mean score for each item. Acceptable items usually
have difficulty values between 0.30 and 0.80.

Item Difficulty Index Discrimination Index

EarnedPt1 0.4 0.0

EarnedPt2 0.667 0.25

EarnedPt3 0.267 0.0

EarnedPt4 0.067 0.0

EarnedPt5 0.333 -0.25

EarnedPt6 0.667 0.25

EarnedPt7 0.333 0.0

EarnedPt8 0.667 0.0

EarnedPt9 0.2 0.5

EarnedPt10 0.533 1.0

EarnedPt11 0.6 -0.25

EarnedPt12 0.2 0.0

EarnedPt13 0.667 0.5

EarnedPt14 0.6 0.25

EarnedPt15 0.467 1.0


Step 3: Item Selection
Items with acceptable difficulty values (0.30–0.80) were retained. Number of retained
items: 26 out of 50.

Step 4: Recalculation of Reliability


After retaining appropriate items, the Cronbach’s Alpha was recalculated using 26 items.

Revised Cronbach’s Alpha = 0.186

Conclusion
The reliability of the instrument improves when poorly performing items are removed. This
procedure ensures that the final test items measure the intended construct more
consistently.

You might also like