JASP 0.14 Tutorial: Reliability Analysis (Cronbach's alpha) (Episode 23)

In this JASP tutorial, I go through how to do a Reliability Analysis, using Cronbach's alpha, using data from the Data Library. Options include choosing the stats for your analysis, getting descriptives for items and for the scale, and perhaps the best feature: Reverse-coding items for the analysis (with a note that indicates when an item should be reverse coded!).
JASP: jasp-stats.org
NOTE: This tutorial uses the new preview/beta build of 0.14. This build contains slightly more functions/features than the previous builds used for tutorials on this channel, but it is functionally the same for the purposes of this tutorial.
Find me on Twitter: / profaswan
Go to my website: swanpsych.com
Twitch streams on psych & related topics: / cogpsychprof

[@abm.9750]

Thank you for making this video.

[@justinedefensor6994]

Thank you for this! Very helpful! 💖

[@bebsevertots]

Love it ever

[@NatividadMotaPapaseit]

Moltes gràcies! Ho expliques molt bé.

[@esthervandijk1661]

We are using the 0.17 version of JASP, is it correct that the 'Single Test Reliability Analysis' is changed to the 'Unidimensional Reliability' Analysis?

[@AlexanderSwan]

I believe that's right. I didn't pay attention to the name change. This video is for determining Cronbach's alpha for an internal consistency esitmation.

[@lahoktc2019]

Hi Prof. Alex. Very helpful. Thank you for this!! Do you have KR-20 tutorial?

[@AlexanderSwan]

I do not have that tutorial. That isn't a measure of reliability I've used, so I wouldn't know where to start! Maybe someday in the future

[@bigroll2235]

Thank you!!!! You saved my life! I'm not even joking xD

[@kimdsdelacruz]

where do i find cronbach alpha in Jasp's version 0.18?

[@AlexanderSwan]

In this same module as I present in this video

[@JuanDuque-be5uh]

Out of date: These setting are no longer available

[@AlexanderSwan]

I should update it then...

[@balanced_barrister]

Hello! How do I change the alpha value (p) in regression, correlation in JASP? I need to do one data set with p < 0.05 and another data set with p < 0.01

[@AlexanderSwan]

Alphas and p-values are not the same thing. Alpha is a criterion value you make a decision against. So if you want to use alpha = .05, then compare any p-value you get against that. If you use alpha = .01, then any p-value you get for that test should just be compared against .01.
To answer your question specifically about JASP, there is no option to change alpha levels.

[@upraz1930]

Thank you for the video! What is the difference between using standardised cronbach's alpha and unstandardised cronbach's alpha?

[@AlexanderSwan]

I'm not entirely sure, but I imagine the standardized alpha allows for comparison across scales. Unstandardized is just for that scale's reliability. I could be wrong about that tho

[@themusicifeel]

So for a non-random sample should we unclick the Confidence Interval?

[@AlexanderSwan]

I don't think so? I'm not sure I'm following your question. Confidence intervals merely give uncertainty around your point estimate, which can be useful for random and nonrandom sampling

[@TheMissantos]

How do I deal with missing values? I cannot calculate the alpha with missing values from a form that has as an answer NA. Can I put an 0 in those entries? Could anyone help me?

[@AlexanderSwan]

I usually leave missing values empty. So delete the NA and rerun your alpha calc. Don’t make it 0, cuz that value will be entered into the calc and you’ll get an incorrect alpha

[@TheMissantos]

@@AlexanderSwan I had empty values and I got an error

[@AlexanderSwan]

@@TheMissantos sorry, I'm not sure what the issue is