Dear Nuchelle Chance

Generally speaking, you can use the factor analysis but I would like to draw your attention that there two types which are the following:

1. Explanatory Factor Analysis (EFA): In this approach, the research does not specify the model. In other words, you do not force (item1/question1) to measure (factor1/construct1). However, based on the data you have and the rotation TYPE you are applying, the result will show you the loading of each (item/question) on all of (factors/constructs). I would like to highlight that prior to this, you should also determine how many factors you would like to use, which can be done by multiple methods as eigenvalues. The EFA is mainly used for dimension reduction or if you are developing a new scale. To further ensure that the (items/questions) load appropriately on their hypothesized (factors/constructs).

2. Confirmatory Factor Analysis (CFA): Unlike, the EFA, this type of factor analysis, the researcher has to specify the measurement model and test it. The measurement model has to go through many steps to be checked for it's validity and reliability. Usually, it most commonly used to validate a questionnaire. Finally, I would like to mention a set of software that you can use to do that:

If you want to apply the EFA you can use either

1. SPSS through dimension reduction

2. R software using psych package

In the other hand if you are interested to apply CFA then you can use:

1. AMOS

2. R software using lavvan package and there is a function called cfa.

My suggestions are stated in the following part:

Usually, the factor analysis is applied within Structural Equation Modeling. Which is often performed in two steps approach. The first step is to validate the measurement model using (CFA) to ensure the measurement model reliability and validity. Then the structural model is analyzed to study the significance of the proposed relationships.

I would like to also to highlight that AMOS, R package (Laavn) applies so-called covariance-based structural equation modelling (CB-SEM). And there is another approach called Partial least square structural equation modelling (PLS-SEM).

Here is a link where you can find a question about using (CB-SEM) or (PLS-SEM) to give you a glance about the two approaches.

https://www.researchgate.net/post/Whether_analysis_with_CB-SEM_by_AMOS_will_have_better_results_comparing_with_PLS-SEM

So if you are following this (CB-SEM), I would recommend you to AMOS, or Laavn withing R.

If you are applying partial least square structural equation modelling you can still use R by relying on plspm package which is a great package that is equipped with many useful features.

Here is a book that was written by the designer of the (plspm) package to illustrate how to use it.

https://www.gastonsanchez.com/PLS_Path_Modeling_with_R.pdf

Or you can also use SmartPLS, which is very easy to use and very powerful software to run your questionnaire validation.

Dear Nuchelle Chance

Generally speaking, although the measure has been validated several times but you should also validate the measure since it is used within new context thus it applies that different findings may be found.

Thank you Belal Edries. I am an early career research (just finished my PhD in Spring 2020) so I feel like a fish out of water. Do you have a recommendation of the type of CFA I should do? I am using SPSS 26 for data analysis.

Dear Nuchelle Chance

Generally speaking, you can use the factor analysis but I would like to draw your attention that there two types which are the following:

1. Explanatory Factor Analysis (EFA): In this approach, the research does not specify the model. In other words, you do not force (item1/question1) to measure (factor1/construct1). However, based on the data you have and the rotation TYPE you are applying, the result will show you the loading of each (item/question) on all of (factors/constructs). I would like to highlight that prior to this, you should also determine how many factors you would like to use, which can be done by multiple methods as eigenvalues. The EFA is mainly used for dimension reduction or if you are developing a new scale. To further ensure that the (items/questions) load appropriately on their hypothesized (factors/constructs).

2. Confirmatory Factor Analysis (CFA): Unlike, the EFA, this type of factor analysis, the researcher has to specify the measurement model and test it. The measurement model has to go through many steps to be checked for it's validity and reliability. Usually, it most commonly used to validate a questionnaire. Finally, I would like to mention a set of software that you can use to do that:

If you want to apply the EFA you can use either

1. SPSS through dimension reduction

2. R software using psych package

In the other hand if you are interested to apply CFA then you can use:

1. AMOS

2. R software using lavvan package and there is a function called cfa.

My suggestions are stated in the following part:

Usually, the factor analysis is applied within Structural Equation Modeling. Which is often performed in two steps approach. The first step is to validate the measurement model using (CFA) to ensure the measurement model reliability and validity. Then the structural model is analyzed to study the significance of the proposed relationships.

I would like to also to highlight that AMOS, R package (Laavn) applies so-called covariance-based structural equation modelling (CB-SEM). And there is another approach called Partial least square structural equation modelling (PLS-SEM).

Here is a link where you can find a question about using (CB-SEM) or (PLS-SEM) to give you a glance about the two approaches.

https://www.researchgate.net/post/Whether_analysis_with_CB-SEM_by_AMOS_will_have_better_results_comparing_with_PLS-SEM

So if you are following this (CB-SEM), I would recommend you to AMOS, or Laavn withing R.

If you are applying partial least square structural equation modelling you can still use R by relying on plspm package which is a great package that is equipped with many useful features.

Here is a book that was written by the designer of the (plspm) package to illustrate how to use it.

https://www.gastonsanchez.com/PLS_Path_Modeling_with_R.pdf

Or you can also use SmartPLS, which is very easy to use and very powerful software to run your questionnaire validation.