Description
plotSEMM is a statistical graphing package written by Bethany E. Kok, Jolynn Pek, Sonya K. Sterba and Daniel J. Bauer for the statistical program R.
plotSEMM generates semiparametric estimates of the regression function for two latent variables. A mixture of linear structural equation models must first be fit to the data. The mixing probabilities and latent variable model parameters are then input into the program to create the diagnostic graphs required by Bauer (2005).
Click here for an example of plotSEMM output.
For more information about the nonlinear mixed models this program supports and the ways in which this program can be used, see the following sources:
Bauer, D.J. (2005). A semiparametric approach to modeling nonlinear relations among latent variables. Structural Equation Modeling: A Multidisciplinary Journal, 12(4), 513-535.
Pek, J., Sterba, S., Kok, B.E. & Bauer, D.J. (in prep). Visualizing nonlinear relations among latent variables: An online plotting utility and R package.
Download
plotSEMM can be downloaded at the Comprehensive R Archive Network (CRAN), which also provides instructions for installing the package once it is downloaded.
You can also download the most recent version of plotSEMM here. Right-click and select "Save As."
If you wish to use plotSEMM but do not have R installed, you can access the plotSEMM functionality through an online calculator running on Javascript. Graphical image quality will be somewhat lessened and the graphs are not customizable when using the online calculator.
Version Notes
plotSEMM 1.0 released 3/11/08
Contact Bethany E. Kok with questions about plotSEMM.