What is Wrong with Cronbach’s Alpha and What to Use Instead

Ever notice that almost all papers seem to report Cronbach's alpha when describing measures? Ever wonder if it is the right thing to be presenting? Or why people dont ever report other metrics of reliability? Well fear not, we have the talk (and the answers) for you!

We are delighted to be able to host Rick Zinbarg, Professor Psychology Department, Northwestern University, and Founder and PI of the Anxiety and Panic Treatment Program, The Family Institute at Northwestern University.

Among the many topics Prof. Zinbarg has published on is psychometric reliability. Below is the abstract for Prof. Zinbarg's talk:

Abstract: When interested in estimating the proportion of scale variance due to a latent variable common to all of a scale’s indicators, the vast majority of applied researchers believe that Cronbach’s alpha is the index of choice. Whereas many methodologists are aware of problems with using Cronbach’s alpha for this purpose, few seem to be aware that there is a better alternative to Cronbach’s alpha. In this talk, I will discuss the importance of the proportion of scale variance due to a latent variable common to all of a scale’s indicators and the central problem with Cronbach’s alpha for estimating this important parameter. In addition, an alternative to Cronbach’s alpha - coefficient omegahierarchical – will be introduced and shown to overcome the positive bias often inherent in Cronbach’s alpha. Finally, I will present the results of simulations testing the accuracy of several different methods for estimating omegahierarchical and conclude with recommendations regarding how to estimate omegahierarchical.

After the talk we will be going for some food and drinks - venue TBC. Please let me know if you would like to join us.