pamr.confusion: A function giving a table of true versus predicted values,...

In pamr: Pam: Prediction Analysis for Microarrays

Description

A function giving a table of true versus predicted values, from a nearest shrunken centroid fit.

Usage

pamr.confusion(fit, threshold, extra=TRUE)

Arguments

fit	The result of a call to pamr.train or pamr.cv
threshold	The desired threshold value
extra	Should the classwise and overall error rates be returned? Default TRUE

Details

pamr.confusion Gives a cross-tabulation of true versus predicted classes for the fit returned by pamr.train or pamr.cv, at the specified threshold.

Author(s)

Trevor Hastie, Robert Tibshirani, Balasubramanian Narasimhan, and Gilbert Chu

Examples

suppressWarnings(RNGversion("3.5.0"))
set.seed(120)
x <- matrix(rnorm(1000*20),ncol=20)
y <- sample(c(1:4),size=20,replace=TRUE)
mydata <- list(x=x,y=y)
mytrain <-   pamr.train(mydata)
mycv <- pamr.cv(mytrain,mydata)
pamr.confusion(mytrain,  threshold=2)
pamr.confusion(mycv,  threshold=2)
 

Example output

Loading required package: cluster
Loading required package: survival
1234567891011121314151617181920212223242526272829301234Fold 1 :123456789101112131415161718192021222324252627282930
Fold 2 :123456789101112131415161718192021222324252627282930
Fold 3 :123456789101112131415161718192021222324252627282930
Fold 4 :123456789101112131415161718192021222324252627282930
  1 2 3 4 Class Error rate
1 0 0 5 0                1
2 0 0 4 0                1
3 0 0 6 0                0
4 0 0 5 0                1
Overall error rate= 0.609
  1 2 3 4 Class Error rate
1 0 0 5 0        1.0000000
2 0 0 4 0        1.0000000
3 0 0 5 1        0.1666667
4 0 0 3 2        0.6000000
Overall error rate= 0.571

pamr documentation built on May 2, 2019, 12:35 p.m.