In which situation, the decision of CFA should be taken instead of exploratory factor analysis (EFA). For CFA which method is suitable - Traditional (through common statistical package) or SEM approach?
Dear Asit
In order to answer the question, I would like you to tell me what type of situation you wish to use the CFA
To answer the question, I would like to simply say---When the items (questionnaire) are tested in prior studies for several times, when theoretical background about your model exist then use CFA instead of EFA. However, it the questionnaire is newly developed, or the already developed but the not tested in your country, culture etc. and the Theory do not exist so, you can use EFA to check either items explain relationship with specific construct. this is rule of thumb.
Let me know if you have not yet understood.
Regards
One of the situations is when an instrument is already valid and reliable in other settings. If used in a new setting, it is preferred to run CFA, if the result shows high indices, then keep the instrument in the same structure; Otherwise you do EFA and then CFA
Dear Leon,
I have a set of groundwater analysis data of an area (say, 30 samples and 20 parameters (variables)). I intend to know the causative factors for the water quality. From other studies, I have already found some information on the factors controlling water quality. I like to find out the underlying structure (of interrelated variables) through FA to verify the said information. This is the background. Hope, it may help you to understand the situation.
Thanks for showing interest on the question.
Mr. Anwar Shah - I appreciate you for providing information on the selection criteria (EFA or CFA) - really educative.
Can you throw some light on the CFA methods (ref. question)?
Thanks to you
Dr. Muayyad Ahmad,
Sir - Thanks for information and recommending the question. May, I request you for information on the suitable method for CFA?
Regards
Hi
In order to initiate, it is necessary to make an analysis of the type of variable, the methods used are subject to the fulfillment of assumptions, scale of measurement of the variables and objectives of the investigation.
http://www.uv.es/aldas/resources/Docencia/URV/1.Apuntes_AFC.pdf
Dear Asit
For the information you tell me. It begins with Exploratory Analysis and takes that information as a prior hypothesis for the CFA. He also uses previous theory to model different factor structures.
This is the most coherent
Best Regards
José Ventura
Hi, in response to your comments "
Dr. Muayyad Ahmad,
Sir - Thanks for information and recommending the question. May, I request you for information on the suitable method for CFA?
Regards
Confirmatory factor analysis (CFA)?. Available from: https://www.researchgate.net/post/Confirmatory_factor_analysis_CFA [accessed Aug 14, 2017]."
I am attaching articles on CFA, hope you find it helpful
Confirmatory factor analysis (CFA) is a multivariate statistical procedure that is used to test how well the measured variables represent the number of constructs.
Confirmatory factor analysis (CFA) and exploratory factor analysis (EFA) are similar techniques, but in exploratory factor analysis (EFA), data is simply explored and provides information about the numbers of factors required to represent the data. In exploratory factor analysis, all measured variables are related to every latent variable. But in confirmatory factor analysis (CFA), researchers can specify the number of factors required in the data and which measured variable is related to which latent variable.
Confirmatory factor analysis (CFA) is a tool that is used to confirm or reject the measurement theory.
For Using CFA, we can use SPSS with AMOS. Usually, statistical software like AMOS, LISREL, EQS and SAS are used for confirmatory factor analysis. In AMOS, visual paths are manually drawn on the graphic window and analysis is performed. In LISREL, confirmatory factor analysis can be performed graphically as well as from the menu. In SAS, confirmatory factor analysis can be performed by using the programming languages.
http://www.statisticssolutions.com/confirmatory-factor-analysis/
Dr. Muayyad Ahmad,
Sir - The attached papers are good for understanding the factor analysis. Later, I will go through the papers in detail. Lot of thanks to you - Dr. Asit
Dr.S.C.Kundu,
Sir - You have clearly explained the CFA. ResearchGate readers will be highly benefited from your brief note on CFA. Thanks and regards - Dr. Asit
When reflective indicator are already known you can skip the EFA and move on to CFA. But in many cases, CFA does not give the proper result because of invalid data. So it is advisable to do EFA before going to CFA.
For performing CFA, AMOS is the better option.
- Badges
- Science topic
- Similar topics
- Geoscience
- Asia
- India