Quickly create, run, and report structural equation and twin models. See '?umx' to learn more.
umx is a structural equation modelling package designed to make SEM easier to build, modify, and report.
It includes high-level functions for complex models such as multi-group twin models, as well as for graphical model output.
Grab it from CRAN with
The best way to learn what is on offer is to use the help ('?umx' works) and the online tutorial: tbates.github.io
umx stands for "user" OpenMx functions. umx contains over 100 functions which build on OpenMx, and are designed to automate activities such as labelling, setting start values etc., and also provides umxRAM and umxPath functions that make Structural Equation Modeling in R straightforward.
Some highlights include:
umxRAM()# mxModel with an R-like
data =parameter, no need to specify type = "RAM", + auto-discovery of manifests and latents from the paths you write
umxPath()# mxPath on steroids: one-word settings to set
fixedAtand more. Great time-saver!
umxSummary(model)# Get a brief summary of model fit, similar to a journal report (Χ², p, CFI, TLI, & RMSEA). Optionally show the path loadings
plot(model, std=T, digits = 3, file = "name")# Create a graphical representation of model!
umx_time(model)# Report the time taken by a model in a compact programable format
umxModify()*# Modify and run a model. You can add objects, drop or add paths, including by regular-expression label matching), re-name the model, re-run, and even return the comparison. All in 1 line *
umxGetParameters(model, regex = "as_r_2c_[0-9]", free = T)# A powerful assistant to get labels from a model. like
omxGetParametersbut uses regular expressions.
umxACE()# 1-line function handling twin ACE modeling with aplomb paths are labeled, and works with
umxStart()# Add plausible start values to RAM or matrix models, or matrices: very helpful
umxLabel()# Add systematic labels to paths ("var1_to_var2") and matrix cells ("a_r1c1"). This is great for setting, equating and dropping paths by label!
umxHcor(data, use = "pairwise.complete.obs")# Compute appropriate pair-wise correlations for mixed data types.
Dozens more (?umx to see them all). Check out the "family links" in any help file also!
Feel free to use, and improve: Log suggestions using the Github comments. Tell your friends! Get awesome publications :-)
You can install the development version from github: