You can perform a confirmatory factor analysis to determine if it fits a three-factor model and its respective reactive.

Hello Karishma,

I don't understand one little thing. The graphic is not informative as I cannot see anything. What do you mean with "side by side questions"? What is the difference between question and items? Adding a graphic in higher resolution could help.

When you simply want to reduce the number of questions, don't do a factor analysis (not exploratory but surely not confirmatory) but a principal component analysis. But be aware that this also induces some amount of uncertainty / ambiguity as in any other kind of aggregation.

Best,

--Holger

to reduce the items (questions) you can use Principal Component Analysis

before doing so, check reliability and based on that you can maybe omit those that are really insignificant. as Mr Holger said, the quality of the photo is really bad and we cannot see anything. you also use different terms to explain the matter which is a bit confusing.

Do elaborate and maybe provide a HQ photo so we can see what you are dealing with.

Factor analysis (CFA not EFA) would be a good way to reduce your items and it does not differ significantly if you have 1 or more columns!

if all indicators are reflective and degree of freedom allows you, then you can have them analyzed in one group of 33 and omit those that show low or insignificance.

hope this helps.

check this one too:

Hair, J. F., Black, W. C., Babin, B. J., Anderson, R. E., & Tatham, R. L. (1998). Multivariate data analysis (Vol. 5, No. 3, pp. 207-219). Upper Saddle River, NJ: Prentice hall.