There are several main points to be made about the software programs that can be used for performing SEM [for my current recommendation, see item (6)].

(1) Many SEM analyses can be performed without using specialized software. That said, there are huge advantages to using one of the specialized packages because of all of the built-in features now available. Many of these features are both very useful and also difficult to replicate using non-specialized statistical software.

(2) There are quite a few software programs currently available for performing structural equation modeling. The first of the widely used programs of this sort was LISREL, which as of this writing is in its eighth generation. A number of other programs are also available including EQS, Amos, CALIS (a module of SAS), SEPATH (a module of Statistica), and Mplus. There is also a module in R, which is available for free.

(3) New users of SEM inevitably wish to know which of these programs is best. One point in this regard is that most of these programs are updated fairly frequently, making any description I might give of the limitations of a program potentially out of date. Another point to make is that different individuals prefer different features. Some want the software that will allow them to get started most quickly, others want the software with the most capabilities, still others want the software that is freely available to them.

(4) Interested individuals can perform internet searches for the programs that interest them and can go to the software developers' web sites to find out the latest features and associated costs. Also, free student editions of the software are available for download for many of these programs. Finally, published reviews can often be found in the journal Structural Equation Modeling and other opinions can be sought by searching the internet. 

(5) Given the above caveats, I will go on to say that as of this writing, Amos, EQS, and LISREL all possess graphical programming capabilities (and graphical display of results).

(6) I currently use two programs, Amos and Mplus. This is not a commercial endorsement and I have no financial interest in either company. I use Amos whenever I am working on a problem that falls within its capabilities (because it is more explicit and makes it easier to communicate with collaborators), or when I want Bayesian solutions. I use Mplus when it has the more advanced features I need. 

(7) A bit of background, for those interested in my reasoning. I first used LISREL for many years, then a few years ago switched to Mplus. I have had week-long courses from the authors of both of these packages and have invested significant effort in being proficient in both. When Amos 7.0 was released in 2007, I felt that I should give it a second look, given the new features, in particular its ability to now deal with categorical response variables. I have been extremely impressed! Most importantly, Amos is a superior product for getting new users up to a level of solid proficiency VERY quickly. The software interface is exceptionally well designed and carefully well thought out. The manual is an extraordinarily well-crafted way of learning the SEM tool box is the shortest amount of time. There are also some very nice training modules on their associated web site (www.amosdevelopment.com).

(8) On another page on this website, I provide the data and Mplus software code for the examples provided in the Appendix to my book, along with a link to the Mplus site where one can download the free version of the software for running these examples. 

(9) I now provide information about Amos on this website, including links to their web page and the Amos programs for the examples provided in my book.

(10) I am happy to receive any comments about your experiences with SEM software or about this material at jim_grace@cox.net.