A semtree.control object contains parameters that determine the tree
growing process. These parameters include choices of different split
candidate selection procedures and hyperparameters of those. Calling the
constructor without parameters creates a default control object. A number of
tree growing methods are included in with this package: 1. "naive" splitting
takes the best split value of all possible splits on each covariate. 2.
"fair" selection is so called because it tests all splits on half of the
data, then tests the best split value for each covariate on the other half
of the data. The equal footing of each covariate in this two phase test
removes bias from testing variables with many possible splits compared to
those with few. 3. "fair3" does the phases described above, with an
additional step of retesting all of the split values on the best covariate
found in the second phase. Variations in the sample from subsetting are
removed and bias in split selection further reduced. 4. "crossvalidation"
partitions the data for maximizing splits on each variable, then comparing
maximum splits across each variable on the rest of the data.
semtree.control(
method = "naive",
min.N = 20,
max.depth = NA,
alpha = 0.05,
alpha.invariance = NA,
folds = 5,
exclude.heywood = TRUE,
progress.bar = TRUE,
verbose = FALSE,
bonferroni = FALSE,
use.all = FALSE,
seed = NA,
custom.stopping.rule = NA,
mtry = NA,
report.level = 0,
exclude.code = NA,
score.tests = list(nominal = "LMuo", ordinal = "maxLMo", metric = "maxLM"),
information.matrix = "info",
scaled_scores = TRUE,
linear = TRUE,
min.bucket = 10,
naive.bonferroni.type = 0,
missing = "ignore",
use.maxlm = FALSE,
strucchange.from = 0.15,
strucchange.to = NULL,
strucchange.nrep = 50000
)Default: "naive". One out of
c("fair","fair3","naive","cv") for either an unbiased two-step
selection algorithm, three-step fair algorithm, a naive take-the-best, or a
cross-validation scheme.
Default: 10. Minimum sample size per a node, used to determine whether to continue splitting a tree or establish a terminal node.
Default: NA. Maximum levels per a branch. Parameter for limiting tree growth.
Default: 0.05. Significance level for splitting at a given node.
Default: NA. Significance level for invariance tests. If NA, the value of alpha is used.
Default: 5. Defines the number of folds for the "cv"
method.
Default: TRUE. Reports whether there is an identification problem in the covariance structure of an SEM tested.
Default: NA. Option to disable the progress bar for tree growth.
Default: FALSE. Option to turn on or off all model messages during tree growth.
Default: FALSE. Correct for multiple tests with Bonferroni type correction.
Treatment of missing variables. By default, missing values stay in a decision node. If TRUE, cases are distributed according to a maximum likelihood principle to the child nodes.
Default: NA. Set a random number seed for repeating random fold generation in tree analysis.
Default: NA. Otherwise, this can be a boolean function with a custom stopping rule for tree growing.
Default: NA. Number of sample columns to use in SEMforest analysis.
Default: 0. Values up to 99 can be used to increase the number of onscreen reports for semtree analysis.
Default: NA. NPSOL error code for exclusion from model fit evaluations when finding best split. Default: Models with errors during fitting are retained.
A list of score-based test statistics from the strucchange package to be used for different variable types.
A function to extract the covariance matrix for the coefficients of the fitted model.
If TRUE (default), a scaled cumulative score process is used for identifying a cutpoint.
If TRUE (default), the structural equation model is assumed to be linear without any nonlinear parameter constraints. The runtime is much smaller for linear MxRAM-type models than for models with nonlinear constraints on the parameters.
Minimum bucket size to continue splitting
Default: 0. When set to zero, bonferroni correction for the naive test counts the number of dichotomous tests. When set to one, bonferroni correction counts the number of variables tested.
Missing value treatment. Default is ignore
Use MaxLm statistic
Strucchange argument. See their package documentation.
Strucchange argument. See their package documentation.
Strucchange argument. See their package documentation.
A control object containing a list of the above parameters.
Brandmaier, A.M., Oertzen, T. v., McArdle, J.J., & Lindenberger, U. (2013). Structural equation model trees. Psychological Methods, 18(1), 71-86.
# NOT RUN {
# create a control object with an alpha level of 1%
my.control <- semtree.control(alpha=0.01)
# set the minimum number of cases per node to ten
my.control$min.N <- 10
# print contents of the control object
print(my.control)
# }
Run the code above in your browser using DataLab