You want to change the order of columns in a data frame.

To reorder columns by their numeric position:

dat <- dat[c(1,3,2)]

To reorder by column name:

dat <- dat[c("col1", "col3", "col2")]

The previous examples use list-style indexing. A data frame is essentially a list of vectors, and indexing into it as a list will return another data frame. You can get the same effect with matrix-style indexing:

library(gcookbook) # For the data set
anthoming

 angle expt ctrl
   -20    1    0
   -10    7    3
     0    2    3
    10    0    3
    20    0    1

anthoming[c(1,3,2)]     # List-style indexing

 angle ctrl expt
   -20    0    1
   -10    3    7
     0    3    2
    10    3    0
    20    1    0

# Putting nothing before the comma means to select all rows
anthoming[, c(1,3,2)]   # Matrix-style indexing

 angle ctrl expt
   -20    0    1
   -10    3    7
     0    3    2
    10    3    0
    20    1    0