predict.pamCat: Predict Method for pamCat Objects

Description

Predicts the classes of new observations based on a Prediction Analysis of Categorical Data.

Usage

# S3 method for pamCat
predict(object, newdata, theta = NULL, add.nvar = FALSE,
   type = c("class", "prob"), ...)

Arguments

object

an object of class pamCat.

newdata

a numeric matrix consisting of the integers between 1 and \(n_{cat}\), where \(n_{cat}\) is the number of levels each of the variables in newdata must take. Each row of newdata must represent the same variable as the corresponding row in the matrix data used to produce object. Each column corresponds to an observation for which the class should be predicted.

theta

a strictly positive numeric value specifying the value of the shrinkage parameter of the Prediction Analysis that should be used in the class prediction. If NULL, then the value of theta will be used that has led to the smallest misclassification rate in the initial Prediction Analysis generating object.

add.nvar

should the number of variables used in the class prediction be added to the output?

type

either "class" or "prob". If "class", then the predicted classes will be returned. Otherwise, the probabilities for the classes are returned.

…

Ignored.

Value

If add.nvar = FALSE, the predicted classes or the class probabilities (depending on type). Otherwise, a list consisting of

pred

a vector or matrix containing the predicted classes or the class probabilities, respectively.

n.var

the number of variables used in the prediction.

References

Schwender, H.\ (2007). Statistical Analysis of Genotype and Gene Expression Data. Dissertation, Department of Statistics, University of Dortmund.

Examples

Run this code

# NOT RUN {
# Generate a data set consisting of 2000 rows (variables) and 50 columns.
# Assume that the first 25 observations belong to class 1, and the other
# 50 observations to class 2.

mat <- matrix(sample(3, 100000, TRUE), 2000)
rownames(mat) <- paste("SNP", 1:2000, sep = "")
cl <- rep(1:2, e = 25)

# Apply PAM for categorical data to this matrix, and compute the
# misclassification rate on the training set, i.e. on mat.

pam.out <- pamCat(mat, cl)
pam.out

# Now generate a new data set consisting of 20 observations, 
# and predict the classes of these observations using the
# value of theta that has led to the smallest misclassification
# rate in pam.out.

mat2 <- matrix(sample(3, 40000, TRUE), 2000)
rownames(mat2) <- paste("SNP", 1:2000, sep = "")
predict(pam.out, mat2)

# Another theta, say theta = 4, can also be specified.

predict(pam.out, mat2, theta = 4)

# The class probabilities for each observation can be obtained by

predict(pam.out, mat2, theta = 4, type = "prob") 

# }