ROC AUC in SPSS and time censored data

Home Forums Methodspace discussion ROC AUC in SPSS and time censored data

Viewing 1 post (of 1 total)
  • Author
    Posts
  • #2191
    Ruth
    Member

    Hi,

    I am exploring AUC for a risk tool that classifies people as low, medium and high (coded 1, 2 and 3) with the outcomes at 12 months as event (coded as 1), non event (coded as 0) and censored due to time at risk (meaning that the person has not been at risk for the full 12 months, coded as -1).

    For ROC AUC do I delete my time at risk censored people (-1) or leave them in? If I leave them in, how do I let SPSS know I have coded the censored people as -1 as it only seems to let me define the event (as 1).

    Thanks 🙂

Viewing 1 post (of 1 total)
  • You must be logged in to reply to this topic.