| cmc.df {multimix} | R Documentation |
Contraceptive Method Choice data
Description
This dataset is a subset of the 1987 National Indonesia Contraceptive Prevalence Survey. The cases are 1473 married women who were either not pregnant or do not know if they were at the time of interview.
Usage
data(cmc.df)
Format
A data.frame with 1473 rows and 10 columns:
- age
Wife's age
- edu
Wife's education
- eduh
Husband's education
- nborn
Number of children ever born
- islam
Wife's religion
- working
Wife is now working?
- husocc
Husband's occupation
- sol
Standard-of-living index
- medex
Media exposure
- method
Contraceptive method used
Details
The variables 'age' (in years) and 'nborn' (ranging from 0 to 16) would normally be treated as continuous; 'nborn' is skew and might well be transformed. The remaining 8 variables are categorical.
The variables 'edu', 'eduh' and 'sol' take values '1,2,3,4', #' they are ordinal with 1 = low and 4 = high. The variable 'husocc' takes the same 4 values, but it is not clear if the order has any significance.
The variables 'islam', 'working', and 'medex' are binary-valued with 0=Non-Islam, 1=Islam for 'islam'; 0=Yes, 1=No for 'working'; and 0=Good, 1=Not good for 'medex'.
The variable 'method' is ternary: 1=No-use, 2=Long-term, 3=Short-term.
Source
Tjen-Sien Lim 'Contraceptive Method Choice' 1997, UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science.