Hi Doaa,

Your question is not clear. It is confusing whether you are talking about SPSS or SSPS? Please make it clearer for what SPSS and SSPS stand.

Good luck

Hello, Dr. Firdos Khan.

I asked about SPSS (Statistical Package for the Social Sciences).

It is statistical software developed for data display and analysis.

My thanks and appreciation.

Hi Doaa,

Please see the link below:

https://www.youtube.com/watch?v=qu4la8K212M

I hope, this will explain what you wanted to know.

Good luck!

Doaa Adel Elemam, I am a bit confused by your question. Perhaps it would help if I pointed out that it is not really appropriate to compare PCA and SPSS.

PCA is one of the extraction methods within the data reduction section of SPSS. In fact, it's the default extraction method

The usual comparison is between PCA and exploratory factor analysis (EFA), and there are a number of extraction methods within EFA. They appear in the drop-down menu where PCA is the default.

I hope that helps.

This questuon is rather confusing, would you mind if you can rephase your question so that the reserach community can better assist you?

Principal Component Analysis (PCA) is a factor extraction technique for data reduction. In other words, PCA is often applied to reduce the dimensionality of a large data set by transforming its measured items into a few composite variables that still hold most information of the large data set. A statistical package that can perform PCA is SPSS. You might check out the textbook by Humble (2020) for insightful inputs into PCA techniques on SPSS.

Humble, S. (2020). Quantitative analysis of questionnaires: Techniques to explore structures and relationships. https://www.routledge.com/Quantitative-Analysis-of-Questionnaires-Techniques-to-Explore-Structures/Humble/p/book/9780367022839

Good luck,

Hello Doaa,

I think the prior answers should help clarify that PCA (principal component analysis) is one approach to data reduction or a structure-seeking process (similar to factor analysis, albeit with different assumptions about reality).

If your interest is in data display and general analysis options, then SPSS, SAS, R (and R-based packages such as Jamovi or JASP), Minitab, and a host of others are all far more capable of these general goals than is PCA.

It's sort of like asking which is better: A recipe for cake ("PCA" in your query) or having the repertoire of a well-trained chef (the full statistical/display package, such as SPSS). The steps for a cake are one minor aspect of the breadth of data display and analytic methods (the "well-trained chef").

Good luck with your work.

Thank you, Dr. Firdos Khan

I really appreciate your help.

Thank you, Dr. Muhammad Mubashar Dogar

I really appreciate your help

Thank you, Dr. Robert Trevethan.

I was really confused about PCA and I have rephrased my question.

I really appreciate your help.

Thank you, Dr. Vusi Mshayisa

I was really confused about PCA and I have rephrased my question.

I really appreciate your help.

Thank you, Dr. Mohialdeen Alotumi .

I was really confused about PCA and your answer clarified it for me.

I really appreciate your help.

Thank you, Dr. David Morse.

Your answer was very helpful and ended my confusion

I really appreciate your help.

Thank God, the confusion has changed to being better informed, the benefits of Q/A feature on Researchgate. Definitely, there exist other tools relating to factor analysis and reduction, also detecting collinearity, instrumental variables, etc. It all depends on the context of your research interest, the model specifications, the type of research and possible covariates including suppressor suspects.

@Doaa, as already observed by seniors and experts in the field, PCA (principal component analysis) is just one approach to data reduction or a structure-seeking process particularly exploratory factor analysis, (EFA), for large data (this is where it's related to factor analysis, but with almost clear difference in questions answered from the analysis. Interestingly, SPSS allows you to obtain the factor scores [SPSS FACTOR], tricky to interprete but can be used as predictors in regression analysis/modeling).

There are many different methods that can be used to conduct a factor analysis in SPSS, (such as principal axis factor(PCA), maximum likelihood, generalized least squares, unweighted least squares...), as well as many types of rotations that can be done after the initial extraction of the sufficient factors.

While trying to confirm a model by fitting it to data is known as “confirmatory factor analysis” (CFA), SPSS , however, does not include confirmatory factor analysis, AMOS provides that aspect of analysis. See https://stats.oarc.ucla.edu/spss/seminars/introduction-to-factor-analysis/&ved=2ahUKEwiNp8rx2O_1AhUA8rsIHUfYDskQFnoECCgQBQ&usg=AOvVaw1Ym0AdCtj2vFb-wl2ph13_

Best wishes

Ibiloye A. C.

Thank you, Dr. Abiodun Christian Ibiloye

Your answer was very helpful and superbly detailed.

I really appreciate your help.

You can also look at the medelisation of structural equations which is another complementary approach to principal component analysis and more powerful

Thank you very much, Dr. Mohamed El Bakkali for your suggestion.

I really appreciate your help.

Hello Doaa,

Components and factors are two different statistical representations for constructs. They have different usages/assumptions so we cannot say one is better than the other. Reading the Introduction of the following two papers would be helpful.

• Cho, G., Sarstedt, M., & Hwang, H. (2021). A comparative evaluation of factor- and component-based structural equation modeling methods under (in)consistent model specifications. British Journal of Mathematical and Statistical Psychology, Advance online publication. https://doi.org/10.1111/bmsp.12255
• Hwang, H., Cho, G., Jung, K., Falk, C. F., Flake, J., & Jin, M. J. (2021). An approach to structural equation modeling with both factors and components: Integrated generalized structured component analysis. Psychological Methods, 26(3), 273–294. https://doi.org/10.1037/met0000336.

Best,

Gyeongcheol