I think the answer lies in this: http://www.statmethods.net/input/valuelabels.html
Which by the way is a very good source for solutions in R.
Partial cut from that is:
--- To understand value labels in *R*, you need to understand the data structure factor http://www.statmethods.net/input/datatypes.html.
You can use the factor function to create your own value lables.
|# variable v1 is coded 1, 2 or 3 # we want to attach value labels 1=red, 2=blue, 3=green
mydata$v1 <- factor(mydata$v1, levels = c(1,2,3), labels = c("red", "blue", "green")) |
|So I think the answer to use factor principles in R.
What might have to be handled differently are floats, which seldom would be needed (but can).
---
| One alternative to use the xml directly would be to export to Stata format with Manager and then use in R |# input Stata file library(foreign) mydata <- read.dta("c:/mydata.dta") |
Regarding Missing values: What I would do is to compare the direct (simplest) way with the XML with the "import" from Stata and then test the behaviour of missing values. But do be aware that currently there are some problems with import/export in Manager to and from Stata format with missing values.
Stata has many missing values (.a to .z) and most likely the import to R from a Stata file have solved that.
regards Jens Lauritsen EpiData Association