It depends on the objective of the study, although its doubt is not understandable. If you want to make a SEM model that integrates several latent variables you can use composite variables (sum of factor scores, etc)

Dear Sourabh Munjal

You can use factor scores too. Details:

https://www.researchgate.net/post/How_does_one_calculate_factor_score_in_factor_analysis https://www.researchgate.net/post/How_to_interpret_factor_scores_from_Exploratory_Factor_Analysis

Dear Cristian Ramos-Vera

we are having total 17 item scale, and with factor analysis all items are reduced to 4 variables. Having, 6, 4, 4 and 3 items in each variable.

in case can we use composite score by simply adding the item scores for each variable.

require some reference for support.

You may be interested in this

Article Understanding the population structure of the GHQ-12: Method...

Sourabh Munjal, I'll comment on two things in your most recent post.

First, having only three items per latent variable is a bit risky. Fabrigar et al. (reference below) recommend at least four items per latent variable.

Fabrigar, L. R., Wegener, D. T., MacCallum, R., C., & Strahan, E. J. (1999). Evaluating the use of exploratory factor analysis in psychological research. Psychological Methods, 4(3), 272—299. https://doi.org/10.1037/1082-989X.4.3.272

Second, I think you don't need a reference/citation for adding up item responses to form a latent variable. That is done so frequently among researchers that it is regarded as a standard practice that does not need to be "defended". You just need to say that you did it. Some researchers do other things, e.g., get the mean of responses on all responses relating to the latent variable, but, again, that's such standard practice that no justification for it is needed.

Whatever is done in terms of creating latent variables simply needs to be clearly and honestly indicated.

Hi Sourabh Munjal

There is some explanation.

Bests

Article Understanding and Using Factor Scores: Considerations for th...

Thanks to everyone for their suggestions.

Sir, Robert Trevethan

With your comment, I understand the adding score is common practice. However, I have been asked to show some previous literature/research papers where a similar method of adding scores is used.

If you can please suggest 1-2 papers for same, It will be helpful

Sourabh Munjal, sure, here are a couple:

On page 344 of the following article, one that a colleague and I had published recently, an "adding" procedure is used, though in our case we obtained the mean of the items after adding them up. That seems to be the most common practice:

Ma, K., & Trevethan, R. (2020). Efficacy perceptions of preservice and inservice teachers in China: Insights concerning measurement and culture. Frontiers of Education in China, 15(2), 332–368. https://doi.org/10.1007/s11516-020-0015-7

A similar practice occurred in the following article:

Tschannen-Moran, M., & Woolfolk Hoy, A. (2001). Teacher efficacy: Capturing an elusive construct. Teaching and Teacher Education, 17(7), 783–805. https://doi.org/10.1016/S0742-051X(01)00036-1

If you want articles in which simple addition occurred, I can probably find a couple for you, but simple addition is not the best if any items have missing data. Often, researchers will permit a certain (low) proportion of items to be missing, and then calculate the mean of the remaining items. Alternatively, they substitute values for missing data using one of several procedures for doing so.

I hope that's helpful.

Thanks a lot Robert Trevethan sir,

certainly refer above articles while using the mean.

currently required couple of articles for simple addition. If possible please provide.

I hope that you will find this useful: O'Rourke N, Hatcher L, editors. A Step-by-Step Approach to Using SAS for Factor Analysis and Structural Equation Modeling, Second Edition. 2013. Please check p.23, "Step 5".

Sourabh Munjal, I'm sorry that I didn't suggest exactly the kind of article you wanted (I'll explain why below). Here are two articles of the kind you want:

Klassen, R. M., Bong, M., Usher, E. L., Chong, W. H., Huan, V. S., Wong, I. Y. F., & Georgiou, T. (2009). Exploring the validity of a teachers’ self-efficacy scale in five countries. Contemporary Educational Psychology, 34, 67–76. https://doi.org/10.1016/j.cedpsych.2008.08.001

Skaalvik, E. M., & Skaalvik, S. (2007). Dimensions of teacher self-efficacy and relations with strain factors, perceived collective teacher efficacy, and teacher burnout. Journal of Educational Psychology, 99, 611–625. https://doi.org/10.1037/0022-0663.99.3.611

Again, my apologies for not tuning into your specific need(s). I would add, however, that if you have missing data, simply adding the responses, rather than what I suggested in my most recent post above, will yield invalid scores. That is why, when I went on a search for the two articles above, I found about 20 articles in which the mean of (presumably available) items, not the simple addition of them, was used. Then, after a lot of hunting, I found the two references above.

I hope these references satisfy your need.

Robert Trevethan Sir,

Thanks a lot indeed.

Providing information in no time is really appreciable. And thanks for enlighting with the explanation for usage of these methods.

Again thanks for guiding and helping.

Regards