3

I need some help with coding factors for a logistic regression.

What I have are six dummy variables representing income brackets. I want to convert these into a single ordered factor for use in a logistic regression.

My data frame looks like: 

    INC1 INC2 INC3 INC4 INC5 INC6
1      0    0    1    0    0    0  
2     NA   NA   NA   NA   NA   NA  
3      0    0    0    0    0    1  
4      0    0    0    0    0    1  
5      0    0    1    0    0    0  
6      0    0    0    1    0    0  
7      0    0    1    0    0    0  
8      0    0    0    1    0    0

What I want it to look like:

    INC
1   INC3  
2   NA   
3   INC6  
4   INC6  
5   INC3 
6   INC4  
7   INC3  
8   INC4

This must be a common (and simple) operation, but my searches have not turned up a concise answer for how to perform this re-coding. Any help is very much appreciated.

tonytonov
  • 25,060
  • 16
  • 82
  • 98
Blair
  • 33
  • 6

1 Answers1

4

Here's a solution based on another answer that keeps the NA values and converts to an ordered factor. 

> inc
  INC1 INC2 INC3 INC4 INC5 INC6
1    0    0    1    0    0    0
2   NA   NA   NA   NA   NA   NA
3    0    0    0    0    0    1
4    0    0    0    0    0    1
5    0    0    1    0    0    0
6    0    0    0    1    0    0
7    0    0    1    0    0    0
8    0    0    0    1    0    0
> inc$F = factor(apply(inc, 1, function(x) names(x)[x == 1]),levels=names(inc),ordered=TRUE)

> inc
  INC1 INC2 INC3 INC4 INC5 INC6    F
1    0    0    1    0    0    0 INC3
2   NA   NA   NA   NA   NA   NA <NA>
3    0    0    0    0    0    1 INC6
4    0    0    0    0    0    1 INC6
5    0    0    1    0    0    0 INC3
6    0    0    0    1    0    0 INC4
7    0    0    1    0    0    0 INC3
8    0    0    0    1    0    0 INC4
> inc$F
[1] INC3 <NA> INC6 INC6 INC3 INC4 INC3 INC4
Levels: INC1 < INC2 < INC3 < INC4 < INC5 < INC6

This will break if you have more than one 1 in a row.

Spacedman
  • 92,590
  • 12
  • 140
  • 224
  • 1
    Looks great. I was almost there but forgot I could create a function within apply to search for 1. Thank you! – Blair Jan 04 '13 at 17:21
  • @user16352, Welcome to Stack Overflow. Generally, it's also good when you are asking a question to show a little bit of what you tried. That way, even if someone isn't able to answer your question, they might be able to point you in the right direction. – A5C1D2H2I1M1N2O1R2T1 Jan 04 '13 at 17:24
  • Thanks for the pointer Anandam, I will add what I was doing next time. I didn't want to make the post too big so I left it out. – Blair Jan 04 '13 at 18:37