betareg (version 2.4-0)

betatree: Beta Regression Trees

Description

Fit beta regression trees via model-based recursive partitioning.

Usage

betatree(formula, partition,
  data, subset = NULL, na.action = na.omit, 
  link = "logit", link.phi = "log", control = betareg.control(),
  ...)
betaReg(control = betareg.control())

Arguments

formula

symbolic description of the model of type y ~ x or y ~ x | z, specifying the variables influencing mean and precision of y, respectively. For details see betareg

partition

symbolic description of the partitioning variables, e.g., ~ p1 + p2. The argument partition can be omitted if formula is a three-part formula of type y ~ x | z | p1 + p1.

data, subset, na.action

arguments controlling formula processing.

link

character specification of the link function in the mean model (mu). Currently, "logit", "probit", "cloglog", "cauchit", "log", "loglog" are supported. Alternatively

link.phi

character specification of the link function in the precision model (phi). Currently, "identity", "log", "sqrt" are supported. Alternatively, an object of class "link-glm" can be supplied.

control

a list of control arguments for the beta regression specified via betareg.control.

...

further control arguments for the recursive partitioning passed to mob_control.

Value

• betatree() returns an object of S3 class "betatree" which is a list containing only a single element of S4 class "mob" (because this is currently not exported from the party package).

  betaReg returns an S4 object of class "StatModel" that fits beta regression models with the specified control arguments. When applied to data, it returns S3 objects of class "betaReg" inheriting from "betareg".

encoding

latin1

Details

Beta regression trees are an application of model-based recursive partitioning (implemented in mob, see Zeileis et al. 2008) to beta regression (implemented in betareg, see Cribari-Neto and Zeileis 2010). For plugging in betareg into mob some glue is required which is provided by betaReg. See also Gr�n at al. (2011) for more details.

Various methods are provided for "betatree" objects, most of them inherit their behavior from "mob" objects (e.g., print, summary, coef, etc.). The plot method employs the node_bivplot panel-generating function.

betaReg is a wrapper function that creates a "StatModel" object with certain fitting parameters passed on to betareg.fit for fitting beta regression models. It is the S4 interface required for plug-in to mob. The user does not have to call this directly but can simply use the betatree interface.

References

Cribari-Neto, F., and Zeileis, A. (2010). Beta Regression in R. Journal of Statistical Software, 34(2), 1--24. http://www.jstatsoft.org/v34/i02/.

Gr�n, B., Kosmidis, I., and Zeileis, A. (2011). Extended Beta Regression in R: Shaken, Stirred, Mixed, and Partitioned. Working Paper 2011-22. Working Papers in Economics and Statistics, Research Platform Empirical and Experimental Economics, Universit�t Innsbruck. http://EconPapers.RePEc.org/RePEc:inn:wpaper:2011-22

Zeileis, A., Hothorn, T., and Hornik K. (2008). Model-Based Recursive Partitioning. Journal of Computational and Graphical Statistics, 17(2), 492--514.

See Also

betareg, betareg.fit, mob

Examples

## data with two groups of dyslexic and non-dyslexic children
data("ReadingSkills", package = "betareg")
## additional random noise (not associated with reading scores)
set.seed(1071)
ReadingSkills$x1 <- rnorm(nrow(ReadingSkills))
ReadingSkills$x2 <- runif(nrow(ReadingSkills))
ReadingSkills$x3 <- factor(rnorm(nrow(ReadingSkills)) > 0)

## fit beta regression tree: in each node
##   - accurcay's mean and precision depends on iq
##   - partitioning is done by dyslexia and the noise variables x1, x2, x3
## only dyslexi is correctly selected for splitting
bt <- betatree(accuracy ~ iq | iq, ~ dyslexia + x1 + x2 + x3,
  data = ReadingSkills, minsplit = 10)
plot(bt)

## inspect result
coef(bt)
sctest(bt)
summary(bt, node = 2)
summary(bt, node = 3)