umx (version 1.9.1)

umxRAM: Easy-to-use RAM model maker.

Description

umxRAM expedites creation of RAM models, still without doing invisible things to the model.

Usage

umxRAM(model = NA, ..., data = NULL, name = NA, comparison = TRUE,
  setValues = TRUE, suffix = "", independent = NA,
  remove_unused_manifests = TRUE, showEstimates = c("none", "raw", "std",
  "both", "list of column names"), refModels = NULL,
  thresholds = c("deviationBased", "direct", "ignore", "left_censored"),
  autoRun = getOption("umx_auto_run"), optimizer = NULL)

Arguments

model

A model to update (or set to string to use as name for new model)

...

mx or umxPaths, mxThreshold objects, etc.

data

data for the model. Can be an mxData or a data.frame

name

A friendly name for the model

comparison

Compare the new model to the old (if updating an existing model: default = TRUE)

setValues

Whether to generate likely good start values (Defaults to TRUE)

suffix

String to append to each label (useful if model will be used in a multi-group model)

independent

Whether the model is independent (default = NA)

remove_unused_manifests

Whether to remove variables in the data to which no path makes reference (defaults to TRUE)

showEstimates

Whether to show estimates. Defaults to no (alternatives = "raw", "std", etc.)

refModels

pass in reference models if available. Use FALSE to suppress computing these if not provided.

thresholds

Whether to use deviation-based threshold modeling for ordinal data (if any is detected), direct, or do nothing.

autoRun

Whether to mxRun the model (default TRUE: the estimated model will be returned)

optimizer

optionally set the optimizer (default NULL does nothing)

Value

- mxModel

Details

Like mxModel, you list the theoretical causal paths. Unlike mxModel:

1. You don't need to set type = "RAM"

2. You don't need to list manifestVars (they are detected from path usage)

3. You don't need to list latentVars (detected as anything in paths but not in mxData)

4. You add data like you do in lm, with data =

5. with umxPath you can use powerful verbs like var =

6. You don't need to add labels: paths are automatically labelled "a_to_b" etc.

7. You don't need to set start values, they will be done for you.

8. You don't need to mxRun the model: it will run automatically, and print a summary

umxRAM is like lm, ggplot2 etc.: you give the data in a data = parameter A common error is to include data in the main list, a bit like saying lm(y ~ x + df) instead of lm(y ~ x, data = dd).

nb: unlike mxModel, umxRAM needs data at build time.

If you are at the "sketching" stage of theory consideration, umxRAM supports a simple vector of manifest names to work with.

Comparison with other software

Some software has massive behind-the-scenes defaulting and path addition. I've played with similar features (like auto-creating error and exogenous variances using endog.variances = TRUE and exog.variances = TRUE). Also identification helpers like fix = "latents" and fix = "firstLoadings".

To be honest, these are not only more trouble than they are worth, they encourage errors and poor modeling. I suggest user learn the handful of umxPath short cuts and stay clean and explicit!

References

- http://tbates.github.io, https://github.com/tbates/umx

See Also

umxPath, umxSummary, plot

Other Core Modelling Functions: plot.MxModel, umxDiagnose, umxLatent, umxMatrix, umxPath, umxReduceACE, umxReduceGxE, umxRun, umxSuperModel, umx

Examples

# NOT RUN {
# ===========================
# = Here's a simple example =
# ===========================
m1 = umxRAM("tim", data = mtcars,
	umxPath(c("wt", "disp"), to = "mpg"),
	umxPath("wt", with = "disp"),
	umxPath(v.m. = c("wt", "disp", "mpg"))
)
plot(m1, std=TRUE, means=FALSE)

# ====================================
# = A cov model, with steps laid out =
# ====================================

# 1. For convenience, list up the manifests you will be using
selVars = c("mpg", "wt", "disp")

# 2. Create an mxData object
myCov = mxData(cov(mtcars[,selVars]), type = "cov", numObs = nrow(mtcars) )

# 3. Create the model (see ?umxPath for more nifty options)
m1 = umxRAM("tim", data = myCov,
	umxPath(c("wt", "disp"), to = "mpg"),
	umxPath("wt", with = "disp"),
	umxPath(var = selVars)
)

# 4. Use umxSummary to get standardized parameters, CIs etc.
umxSummary(m1, show = "std")

# 5. Display path diagram
plot(m1)
plot(m1, std = TRUE, resid = "line")

# ===============================
# = Using umxRAM in Sketch mode =
# ===============================
# No data needed: just list variable names!
# Resulting model will be plotted automatically
m1 = umxRAM("what does unique pairs do, I wonder", data = c("B", "C"),
# B<->B, C<->C, B<->C
umxPath(unique.pairs = c("B", "C"))
)

m1 = umxRAM("ring around the rosey", data = c("B", "C"),
# A->B, A->C, B->A, B->C, C->A, C->B
umxPath(fromEach = c("A", "B", "C"))
)
m1 = umxRAM("fromEach with to", data = c("B", "C"),
# B->D, C->D
umxPath(fromEach = c("B", "C"), to= "D")
)
m1 = umxRAM("CFA_play", data = paste0("x", 1:4),
	umxPath("g", to = paste0("x", 1:4)),
	umxPath(var = paste0("x", 1:4)),
	umxPath(v1m0 = "g")
)

# =================================================
# = This is an example of using your own labels:  =
#   umxRAM will not over-ride them                =
# =================================================
m1 = umxRAM("tim", data = myCov,
	umxPath(c("wt", "disp"), to = "mpg"),
	umxPath(cov = c("wt", "disp"), labels = "b1"),
	umxPath(var = c("wt", "disp", "mpg"))
)
omxCheckEquals(m1$S$labels["disp", "wt"], "b1") # label preserved
m1$S$labels
#      mpg             wt            disp
# mpg  "mpg_with_mpg"  "mpg_with_wt" "disp_with_mpg"
# wt   "mpg_with_wt"   "wt_with_wt"  "b1"
# disp "disp_with_mpg" "b1"          "disp_with_disp"
# }