Keywords: censored data, Cox regression.
The data are the times, in days, that heroin addicts spend in a clinic. There are two clinics and the covariates are believed to affect the times spent in the clinic by addicts.
|Clinic||1 or 2|
|Status||0 = still in clinic at end of study (censored) or 1 = departed from clinic|
|Time||days spent in clinic|
|Prison||1 = prison record or 0 = no record|
|Dose||methadone dosage (mg/day)|
Data file (tab-delimited text)
|Caplehorn, J. (1991). Methadone dosage and retention of patients in maintenance treatment. Medical Journal of Australia, 154, 195-199.|
|Hand D.J., Daly F., Lunn A.D., McConway K.J., Ostrowski E. (1994). A Handbook of Small Data Sets. London: Chapman and Hall.|
This can be used as an interesting example of stratified Cox regression where stratification is done by clinic.