I agree with all answers so far, but would also add that Mplus is better than AMOS or LISREL. Mplus has 'black boxed' many of the more complicated aspects of SEM (e.g. multi-group is very easy), can embed EFA in a SEM model (ESEM), can constrain parameters and create new parameters that are functions of other parameters, and it handles ordinal variables very nicely. It also offers a broader statistical framework where mixture and multi-level aspects of SEMs can be accommodated.
Amos is covariance base SEM, which dosnt need programing. and it is nice garphical program. but for SEM analysis I do recommend PLS analysis with smart PLS. Cause in addition to being friendly user, no assumptions are needed to run your analysis.
I agree with all answers so far, but would also add that Mplus is better than AMOS or LISREL. Mplus has 'black boxed' many of the more complicated aspects of SEM (e.g. multi-group is very easy), can embed EFA in a SEM model (ESEM), can constrain parameters and create new parameters that are functions of other parameters, and it handles ordinal variables very nicely. It also offers a broader statistical framework where mixture and multi-level aspects of SEMs can be accommodated.
I think R is useful for SEM analysis as long as you know how to use this software. As far as I know, it requires programming. For those who don't know how to use R, SPSS AMOS or LISREL are better alternatives.
this is not quite correct. The lavaan package which is used within R is easy to use and its syntax is very similar to those of MPLUS. For instance, a CFA model would be like
cfamodel summary(sem(cfamodel, data = mydata) )
in which you can incorporate further argeuments such as the chosen estimator (e.g., Satorra-Bentler or Yuan-Bentler correction for non-normality) or missing data treatment (full information maximum likelihood).
You need one day to learn that. This is a nice introduction into lavaan:
https://amzn.to/2Ms6YhJ
For all German I readers, I wrote a short book that treats especially theoretical and practical issues (what latent variables mean, the difference between latent variables and "constructs", model implications such as path tracing rules and d-separation and diagnostics of misfitting models.
https://amzn.to/2vRpXbS
Amos has surely its advantages especially for beginners (as you can draw diagrams but the above code can be learned in 1 day and lavaan offers many nice benefits - for instance the above arguments and standardized residuals that are essential to diagnose misfitting models :)
@Maryam kh: I have to disagree with you. Although PLS-PM seems ro be very user friendly and produces almost always results, it of course requires certain assumptions to hold to obtain trustworthy results.
Amos and Lisrel are just the software to conduct SEM based on CB-SEM approach. The most widely used is the Amos as it was copyrighted by IBM SPSS, and it is very friendly to use. I suggest for you to use Amos for you SEM.
Lisrel and Amos are just the softwares for conducting SEM analysis. Both for CB-SEM analysis. However, Amos is more recent and more user friendly as compared to Lisrel.
My data have a likert scale which contain five categories (strongly disagree, disagree, undecided, agree, and disagree). Which one handles categorical data more efficiently?
You may check what is your research is all about, sample and etc.
Rules of thumb for choosing between PLS-SEM and CB-SEM by Hair, J. F., Hult, G. T. M., Ringle, C. M., and Sarstedt, M. 2014. A Primer on Partial Least Squares Structural Equation Modeling (PLS-SEM). 2nd Ed. Thousand Oaks, CA: Sage.
Use PLS-SEM when
The goal is predicting key target constructs or identifying key “driver” constructs.
Formatively measured constructs are part of the structural model. Note that formative measures can also be used with CB-SEM, but doing so requires construct specification modifications (e.g., the construct must include both formative and reflective indicators to meet identification requirements).
The structural model is complex (many constructs and many indicators).
The sample size is small and/or the data are nonnormally distributed.
The plan is to use latent variable scores in subsequent analyses.
Use CB-SEM when
The goal is theory testing, theory confirmation, or the comparison of alternative theories.
Error terms require additional specification, such as the covariation.
The structural model has circular relationships.
The research requires a global goodness-of-fit criterion.
When to choose PLS-SEM according to Richter, N.F., Cepeda Carrión, G., Roldán, J. L. and Ringle, C. M. 2016. "European Management Research Using Partial Least Squares Structural Equation Modeling (PLS-SEM): Editorial." European Management Journal 34(6): 589-597:
"The question that arises is the following: Why and when should PLS-SEM be used? Wold (2006) provides, among others, the following key reasons for using PLS-SEM: (a) the PLS-SEM approach has a broad scope and flexibility of theory and practice; and (b) a PLS path model develops through a dialogue between the investigator and the computer, in that tentative model improvementsdsuch as the introduction of a new latent variable, an indicator, and an inner model relation, or the omission of such an elementdare easily and quickly tested for predictive relevance. Moreover, prediction-oriented analyses, complex models, and secondary/ archival or big data motivate the use of PLS-SEM (Gefen, Rigdon, & Straub, 2011; Rigdon, 2012, 2014). Additional reasons, suggested by Sarstedt, Ringle, and Hair (2016) and Rigdon (2016), are the use of composites that represent formatively measured latent variables, the use of small sample sizes due to a small population, applying PLS-SEM latent variable scores in subsequent analyses, and endeavoring to overcome factor-based SEM's limitation by mimicking the results of common factor models (i.e., by using consistent PLS approaches; Bentler & Huang, 2014; Dijkstra & Henseler, 2015b). Wold (2006) notes that in large and complex models with latent variables, PLS-SEM is “virtually without competition.” It has not only drastically reduced the distance between subject matter analysis and statistical technique but also reinvented the modeling of complex systems in domains with access to a steady flow of reliable data. In this context, Wold (1982), and later Chin (1998), expected PLS-SEM to be widely used across disciplines with rich data, such as classical (political) economics, education, health care and medicine, political science, and chemistry. However, management and other social sciences have traditionally had limited access to rich data because surveys that are subject to several restrictions (e.g., the number of questions) have usually provided most of the relevant data. With the ever-increasing availability of secondary data (e.g., from company databases, social media, and customer tracking), this situation has started to change dramatically. In fact, secondary and/or big data and PLS-SEM's soft modeling approach fit hand in glove: “Soft modeling is primarily designed for research contexts that are simultaneously data-rich and theory-skeletal.” (Wold, 1982, p. 29; also see Rigdon, 2013)." (p. 590).