I conducted a survey and subjected the responses to EFA-CFA cross validation. I also want to check the results for common method bias. I can use the single factor method using SPSS or common latent factor method in AMOS. So should these tests be applied to the whole set of responses or only those split for the EFA/CFA parts respectively.
Hi Syed,
here are the most important papers with regard to the topic:
Antonakis, J., Bendahan, S., Jacquart, P., & Lalive, R. (2010). On making causal claims: A review and recommendations. The Leadership Quarterly, 21, 1086–1120.
Conway, J. M., & Lance, C. E. (2010). What reviewers should expect from authors regarding common method bias in organizational research. Journal of Business and Psychology, 25(3), 325–334. doi:10.1007/s10869-010-9181-6
Richardson, H. A. H. A., Simmering, M. J., & Sturman, M. C. (2009). A tale of three perspectives: Examining post hoc statistical techniques for detection and correction of common method variance. Organizational Research Methods, 12(4), 762–800. doi:10.1177/1094428109332834
Simmering, M. J., Fuller, C. M., Richardson, H. a., Ocal, Y., & Atinc, G. M. (2014). Marker variable choice, reporting, and interpretation in the detection of common method variance: A review and demonstration. Organizational Research Methods, 18(3), 473–511. doi:10.1177/1094428114560023
The best solution would be
- to use different sources for IVs and DVs
- to think of potential instruments that are not object to the method-covariance generating process
- Don't regard CMB as a separte and singular problem - it is one form of overall confounder bias (i.e., an entity has causes on several model variables - thus generating a "non-causal link", see
Elwert, F. (2013). Graphical causal models. In S. L. Morgan (Ed.), Handbook of Causal Analysis for Social Research (pp. 245–273). Dordrecht Heidelberg New York London: Springer. doi:10.1007/978-94-007-6094-3
http://www.ssc.wisc.edu/soc/faculty/pages/docs/elwert/Elwert 2013.pdf
HTH
Holger
Syed, in addition to Holger's suggestions and if you already performed your investigation: It is often suggested to specify a common construct on which all items load - this would be done using CFA, not SPSS. The trouble with this approach is that method effects and trait variance are mixed which means that you cannot separate both sources of common variance. You would need two different methods in your data such as two types of questionnaires, or two types of raters. Then, it would be possible to let all variables measured by the same type of questionnaire (or rater) load onto the same latent variable. Holger's references are very good!
Hope this helps, Karin
There are three techniques for common method bias such as Harman Single Factor, Marker variable and common latent factor. For Harman single factor, you can handle this technique with SPSS but the rest you can try using CFA with AMOS. I prefer you to conduct CMB using CFA like Dr Karin suggested.
Dear All,
Thank you so much for your valuable feedback. I have gone through some of the papers and they seem really interesting. Having said that, perhaps I couldn't make myself clear initially.
I conducted a survey to determine the motives responsible for sound hospital waste management practices among nursing staff. Initially I used a 20 item questionnaire with a 10 point scale for the pilot study which was conducted at a teaching hospital with 100 nurses. I used the responses for EFA and discovered 3 latent factors with 10 items retained. Consequently I conducted the main survey using a 10 item questionnaire with a 5 point scale. The main survey was conducted across 12 hospitals with 250 nurses. The respondents for the pilot study were avoided in the main study. I used the responses for EFA-CFA cross validation by splitting the 250 responses into equal halves of 125 each. Now I also want to conduct a CMB test using CFA. Should I use all 250 responses or just the 125 responses initially split for CFA?
Since I'm a new researcher please forgive me if my question seems silly.
Mustafa
Conway, J. M., Lance, C. E. (2010). What Reviewers Should Expect from Authors Regarding Common Method Bias in Organizational Research. Journal of Business Psychology, 25, 325-334.
- Badges
- Science topic
- Similar topics
- Phytochemistry
- Extracts