Cronbach's Alpha scales

Moderators: statman, Analyst Techy, andris, Fierce, GerineL, Smash

Posts: 1
Joined: Fri Aug 03, 2012 4:17 pm

Cronbach's Alpha scales

Postby NiXeas » Fri Aug 03, 2012 4:36 pm

Dear SPSSpeople,

I have a dilemma with Cronbach's Alpha. I made 3 scales which need to merge to 1 final scale. I've found 2 possible ways but don't know which to choose from because Cronbach's Alpha is very low. These are the 2 scales, each divided in 3 scales with Cronbach's Alpha between brackets. They both passed the Factor analysis:

Scale possibility 1 (0,821)

Scale A (0.356)
Scale B (0.756)
Scale C (0.711)

As you can see Cronbach's Alpha on Scale 1A is very low but the others are oke. Ultimately the the scale is high with 0,821 but I don't know if that's representable.

That made me worry so I tried to make an alternative scale:

Scale possibility 2 (0,740)

Scale A (0.498)
Scale B (0.553)
Scale C (0.711)

I used gamma with both scales on several other variables and Scale possibility 2 has slightly higher relations with them

My question is: Which scale is the best to use?

With kind regards

Who is online

Users browsing this forum: No registered users and 1 guest