Title:      Models of Path Dependence with an Empirical
Application

Authors:    John Jackson, Ken Kollman

Entrydate:  2007-07-17 17:12:06

Keywords:   Path dependence, partisanship, non-linear least
squares

Abstract:   It is now commonplace in the social sciences to
describe an outcome or process as path dependent.  By path
dependence, researchers generally mean that the sequence of
events prior to the observation of the outcome has explanatory
power.    The paper develops models that have both path
dependent and non-path dependent properties, depending upon the
value of a particular parameter.  The paper then uses non-linear
least squares and a Monte Carlo simulation to explore how well
this parameter can be estimated, meaning how well scholars can
discriminate betwen the two processes.  The methodology is
applied to the evolution of attitudes on aid to minorities and
partisanship between 1956 and 2000.  The results are consistent
with the path dependent model.

http://polmeth.wustl.edu/retrieve.php?id=709