I am preparing E-Readiness Index for farmers, extension personnel and agricultural scientist separately to measure the degree of an individual to utilize tools of ICT in agriculture. I have selected sub-groups as well as indicators for the same but i am stuck how to obtain e-readiness score ? As per my reading of literature i realized that PCA or Factor Analysis provides relevancy and accuracy to indicators but my confusion is when to apply PCA ? On which data - data obtained from pre-testing data or the final collected data? Or without any data collected ? Please guide.
Hello Ayushi,
The terse answer is: Both.
Any time you're working on a new measure, it makes sense to use data from pilot/field test of the measure to refine and modify the measure before it is used to collect data (for your intended research aims) in the "live study." So, do the pilot/field test and evaluate the measure accordingly (in your case, you'd likely want to explore structure--which implies factor analysis, subscore reliability, and individual item/question contributions to each). If at most minor modifications are required, then make those and go to the live study. If major modifications are required, you would be wise to engage in a second pilot/field trial.
After the live study (presumably, using a larger sample size), do recheck the technical indicators of your measure (here, you could use confirmatory factor analysis, as you are interesting in checking whether the originally identified structure continues to hold). If comparable, that will give you confidence that your characterization of the measure is not sample specific, and may well generalize to your target population. If not, then both you and others need to be aware of this limitation, and the possible need to rethink/revise the measure.
Good luck with your work.
Hi Ayushi Pal, Yes you can do that. Congrats on your innovative research.
Hello@Ayushi Pal
To perform PCA we don't need the replicated data, so you can go with it at any time based on requirment
Like erudite scholars said, you can use it for both. Good luck
Thank you so much for your guidance. Emmanuel Chinweike Nnabuihe David Morse Raveena Bishnoi Manish Yadav Biswajit Karmakar Babak Jamshidi
Hello Ayushi Pal. You mentioned both factor analysis and PCA in your question, but it was not clear to me which one you want to use. This article by Preacher & MacCallum (2003) does a great job of explaining how they differ, and how you should choose between them. (It also discusses many other things, such as orthogonal vs oblique rotations.) HTH.
http://quantpsy.org/pubs/preacher_maccallum_2003.pdf
Thank you sir Bruce Weaver I am looking for great guidance. I will take a look over it to perform better !
- Badges
- Science topic
- Similar topics
- Agriculture