CODEWITHSUNDEEP
rstatistics
A Khats
A Khats

Reputation: 31

How to subset table and use values for statistical calculation

I have a data frame which looks like this:

table1

 SNo. C1   C2 C3  C4 C5  
 1. A*01   17 116 78 141
 2. A*02   30 1   65 256
 3. A*03   --------------
 4. A*04   --------------
 5.----------------------

For each row I want to calculate Odds ratio and 95% Confidence Interval using fisher.test() function which requires 2x2 table. When I provide numbers manually to do the test it works fine: fisher.test(matrix(c(17, 116,78, 141), ncol = 2, byrow = TRUE)) But when I do fisher.test(matrix(c(table1[1,2:5]), ncol=2, byrow=T)) it gives me this error:

all entries of 'x' must be nonnegative and finite

Please suggest what am I doing wrong

Upvotes: 0

Views: 90

Answers (1)

thelatemail
thelatemail

Reputation: 93813

You're not passing the right input to the function. When you do so, it works fine. E.g.:

dat <- read.table(text="SNo. C1   C2 C3  C4 C5  
1. A*01   17 116 78 141
2. A*02   30 1   65 256",header=TRUE)

apply(
  dat[-(1:2)],
  1,
  function(x) fisher.test(matrix(x,nrow=2,byrow=TRUE)) 
)

#[[1]]
#
#        Fisher's Exact Test for Count Data
#...
#odds ratio 
# 0.2658521 
#
#
#[[2]]
#
#        Fisher's Exact Test for Count Data
#...
#odds ratio 
#  116.4649

Upvotes: 2

Related Questions