Dear all,

I am wondering if anybody can help us to select the competing risks
duration model. In our project, we are interested in the outcomes of
low-level insurgency. Our data codes the outcome of low-level insurgency as
follows: 1) escalation to civil war, 2) negotiated settlements, 3)
de-escalation of violence, 4) state victory, and 5) ongoing conflicts.
Given five insurgency outcomes, we have used the competing risks Cox model.
Recently, we are thinking of using Fine and Gray’s (1999) competing risks
proportional hazard model because it is much easier to interpret cumulative
incidence functions (CIF).

However, our concern is that in Fine and Gray’s model the subhazard
indicates the instantaneous probability of failure from cause *i* at time *t
*“given either no failure before t or failure from another cause before *t*.”
This might mean that subjects who experience competing events are still
remain in future risk pools. In our data each conflict ends when any of
five outcomes occur. As this model is not used widely in political science,
I am wondering if using Fine and Gray’s model would be appropriate.

Thank you for any help.

Sincerely,

Kiyoung

**********************************************************
             Political Methodology E-Mail List
   Editors: Ethan Porter        <[log in to unmask]>
            Gregory Whitfield   <[log in to unmask]>
**********************************************************
        Send messages to [log in to unmask]
  To join the list, cancel your subscription, or modify
           your subscription settings visit:

          http://polmeth.wustl.edu/polmeth.php

**********************************************************