Hello Nihat. Cronbach's alpha is very conservative, tending to under-estimate the true reliability. The alternative I am aware of is composite reliability. But keep aware that this one tends to over-estimate. Always cite both. Kind regards, Ana

Thanks very much for the response, Ana.

Nihat

Cronbach's alpha is a conservative measure (least lower bound for reliability) because it treats all of the items as making equal contributions. If you use Confirmatory Factor Analysis, this will each variable to have its own weight.

Thanks for the comment. I appreciate it. Its use is sometimes challenged despite being a 'conservative' measure. Maybe reporting the alpha range values for items can also help with such concerns?

Individual items to not have alpha values, only the combination of items has an alpha.

Can you say more about what your "concerns" are?

Thanks David and Yves.

I've always reported alpha values for the instrument, while also adding the range for items. I was just wondering if there is a better measure to report instead of this one. 

Here are two things to look at:

Starkweather, J. (2012). Step out of the past: Stop using coefficient alpha; there are better ways to calculate reliability. University of North Texas. Research and statistical support. 

Trizano-Hermosilla, I., & Alvarado, J. M. (2016). Best Alternatives to Cronbach’s Alpha Reliability in Realistic Conditions: Congeneric and Asymmetrical Measurements.

Is there an alternative to the Cronbach's alpha for scales that have different numbers of items?. Available from: https://www.researchgate.net/post/Is_there_an_alternative_to_the_Cronbachs_alpha_for_scales_that_have_different_numbers_of_items [accessed Apr 11, 2017].

Thanks very much Joe!!