Help! - Common method bias (CMB)

[widefov]

Hi all,

Your kind advice will help me a lot. I am finalizing my thesis and some critical issues were asked. The problem is

I did some exploration on this forum and found out some links are broken (!!!!) and the answers are quite confusing for me (especially, post regarding marker variable). My questions are

1. what is the best way to identify CMB 'after' data collection? not 'before' data collection.

2. I see that to use marker variable should be prepared in the data collection method. Am I right? If it is not, could you define what marker variable is or how to make it up?

3. I found out Smartpls doesn't support it. Can I do that with other PLS S/W, such as WRAP-PLS or PLS-graph?

4. is still OK to use common latent variable (https://www.youtube.com/watch?v=Y7Le5Vb7_jg)?

Hope to hear from you guys soon.

All the best,

[cringle]

CMB is call reviewers often make. But no worries: CMB assessment methods always work not matter if it's an issue or not. Many methods have been suggested for PLS and dismissed again. See for example:

Rönkkö, M., & Ylitalo, J. (2011). PLS Marker Variable Approach to Diagnosing and Controlling for Method Variance. Paper presented at the ICIS 2011 Proceedings. http://aisel.aisnet.org/icis2011/procee ... hmethods/8

Chin, W. W., Thatcher, J. B., & Wright, R. T. (2012). Assessing Common Method Bias: Problems with the ULMC Technique. MIS Quarterly, 36(3), 1003-1019.

Why don't you use Harman's single factor test.

Here is a why how I adressed things in a paper but today, I would simply use Harman's single factor test:
Sattler, H., Völckner, F., Riediger, C., & Ringle, C. M. (2010). The Impact of Brand Extension Success Factors on Brand Extension Price Premium. International Journal of Research in Marketing, 27(4), 319-328.

Best
CR

[widefov]

Thanks for your support! It is a huge pleasure to have a reply from my methodology guru.
Thanks very much Dr. Ringle!

All the best,
Hugh