Scribd
Upload
16 views

Topic 16. Reliability and Validity

Uploaded by

janice harjani
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
16 views

Topic 16. Reliability and Validity

Uploaded by

janice harjani
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
You are on page 1/ 21

RELIABILIY & VALIDITY

Understanding the concept and practice


Tuesday, May 28TH 2024
Have you heard +

these term?
Valid? +
+
Reliable?
+

+
What do you think
+ about validity and
reliability?
+
The concept of
Reliability and Validity
+

+
Validity Concept
The extent to which the scales are precise and accurate
when carrying out its measuring function.
+ +
Ghozali (2009) à validity test is used to measure the
extent to which the scale are valid or appropriate.

In a glimpse:
a condition that describes whether the instrument or scale
we use is capable of measuring what we want to measure.
The results obtained from the validity test are a valid or
legal instrument.
+
+
+ Why is it matter?

+
Let’s see this reality
+ Can all of those scale measure
1 kg of onion?
+ What if the scale show you the
1 kgs, but it is actually less
than 1 kg?
Lets move to unobservable one
Can you measure psychological or covert concept,
like satisfaction, motivation, pride, prestige, etc…?

+
+

+
For these covert concept,
We can measure those
+
concept by the its behavior
+
indicator.
The instrument should contain the behavior indicator
represent by the items or statements in the questionnaire.

+
Validity Concept
We can describe the validity like this too….
+ +
What evidence/proof we can provide to prove the measuring
instruments are valid.

What evidence/proof we can provide to prove the


instruments can measure the object they should be
measured.

+
+
The Problem
How accurate/valid the items/statements in
+
the questionnaire can measure the
concept?

It can handled by validity test.


+
Kind of Validity Test +
• Content Validity
• Face validity
• Logical validity +
• Construct Validity
• Criterion-related Validity +
• Predictive validity
• Concurrent validity
Reliability Concept
The extent to which the scales are consistent/steady and
+ trusted.

• Can you believe person who always lie to you?


+ • Does he/she say something consistent when
he/she lies?
• The only consistent thing is they always lie…
• So can you believe to this person?

+
Let’s back to this reality
+ Which scale is potential to
error/tricky to buyer?
+ Which scale will show you more
consistent measure?
Which scale do you believe that
the scale really measure 1 kgs
of onion?
+

SPSS
Simulation +
Use ‘Data RV.sav’ +
Reliability Test
•Click Analyze
•Click Scale
•Click Reliability Analysis...
•Wait until the new window
popping-up.
•Block all items (S1-S18).
•Put them all to the
‘Items:’ box.
•Click ‘Statistics...’
•Check item
•Check Scale if item
deleted
•Click Continues
•Clik OK.
+ Output of Reliability Test

+ Look at:
Cronbach’s Alpha
The cut off criteria is the score of Cronbach’s Alpha minimal 0,7 to get good reliability of the
instrument. If you get score of Cronbach’s Alpha > 0,7, which means the scale is good.
The score of Cronbach’s Alpha score range from 0,0 – 1.0. Approachin 1,0 the score, the scale
would be better.
In this case, the score of Cronbach’s Alpha score is 0,863 à which means the scale has
good reliability. The scale can reveal about 86,3 % (of 100%) concept of satisfaction.
Output of Reliability Test

+ Look at:
Corrected Item-Total Correlation. Cronbach’s Alpha if item Deleted
This output helps us to increase the cronbach alpha score by deleting the useless/bad items.
To know the bad item, you should see on the Corrected Item-Total Correlation. If item score in
Corrected Item-Total Correlation < 0,3 à delete it (e.g red circle/item 8). In this case, the
data show that, item satisfaction 8 have Corrected Item-Total Correlation < 0,3 (0,219). So we
need to delete it and re-analyze again with the same process.
When item satisfaction 8 have been deleted, you can see in Cronbach’s Alpha if item Deleted
(blue circle), that means, when you delete item satisfaction 8, the Cronbach Alpha score would
become 0,874 (increase from 0,863)
“ It’s easy to lie with statistic.
It’s hard to tell the truth
without statistic.

Thank you!

You might also like

pFad - Phonifier reborn

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

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy