Title:      Back to the Future: Modeling Time Dependence in
Binary Data

Authors:    David Carter, Curtis S. Signorino

Entrydate:  2007-07-17 20:03:53

Keywords:   

Abstract:   Since Beck, Katz, and Tucker (1998), the use of time
dummies or splines has become the standard method to model
temporal dependence in binary data. There are potential problems
with both of these approaches, especially in the case of time
dummies. We propose a
simpler alternative: using t, t^2, and t^3 to approximate the
hazard. This cubic polynomial is trivial to implement and avoids
problems with time dummies such as quasi-complete separation and
issues with splines such as interpretation or knot selection. 
It
also accommodates non-proportional hazards in a more
straightforward way than either time dummies or splines. Monte
Carlo analysis and reanalysis of numerous published empirical
results are used to show that our method performs as well as
splines and better than time dummies. Non-proportional hazards
are also simple to model with a
cubic polynomial. We present new results with data from Crowley
and Skocpol (2001) to demonstrate how to model and interpret a
non-proportional hazard.

http://polmeth.wustl.edu/retrieve.php?id=710