macs (version 1.0)

rtree: Tree-based analysis of rare variants to analyze genomic data.

Description

Fit a rtree model

Usage

rtree(data, method = c("entropy", "gini"), alpha = 0.01,cost = NULL)

Arguments

data

inputs data.frame. The first column of the data refers to the response and the other columns are the covariates.

method

defines the splitting rule, that is, 'entropy' for the entropy criterion and 'gini' for the Gini criterion.

alpha

determines the significance threshold by which rtree prunes the tree based on the chi-square test of independence between the distributions of the response in any two daughter nodes.

cost

defines misclassification cost of each category. It is a vector whose dimension is the same as the levels of response variable. Default value is a vector with all elements 1.

Value

nnd

the total number of nodes in the tree.

dt

the sequence number of a left daughter node for each internal node.

pt

the sequence number of the parent node for any daughter node.

spv

the splitting variable used to split a given node.

spvl

the cut-off value of the splitting variable above.

final_counts

the table that contains the number of observations in each node.

varcatg

a numerical indicator for the category of each variable. Value '-1' points to the response variable, '1' to oridinal variables, an integer greater than 1 to a nominal variable with the number of levels equal to the integer.

nodeclass

the class membership of a terminal node which depends on the choice of the misclassification cost.

p_value

the p-value of the chi-square test performed at each internal node. It forms the basis to prune the offspring nodes of any internal node. More details in Recursive Partitioning and Applications [Zhang and Singer].

call

the call by which this object is generated.

learning.data

the data that are actually used in rtree and tarv.

Details

The object rtree function produces can be used to run plot.ctree and forecast.ctree function.

References

Zhang, H. and Singer, B. (1999) Recursive partitioning in the health sciences. Springer Verlag.

See Also

plot.ctree, forecast.ctree

Examples

# NOT RUN {
library(macs)
set.seed(1234)
data <- data.frame(y = sample(1:3, 1000, replace = TRUE),
                   n = sample(1:4, 1000, replace = TRUE,
                                        prob = c(0.1, 0.3, 0.2, 0.4)),
                   o1 = sample(1:50, 1000, replace = TRUE),
                   o2 = sample(1:30, 1000, replace = TRUE),
                   o3 = sample(1:10, 1000, replace = TRUE),
                   o4 = sample(1:60, 1000, replace = TRUE),
                   o5 = sample(1:20, 1000, replace = TRUE),
                   o6 = sample(1:40, 1000, replace = TRUE))
data[,2] <- as.factor(data[,2])
result <- rtree(data, method = "entropy", alpha = 0.01, cost = NULL)
plot(result)
# }