Abstract
In this paper, post-disaster recovery processes of the households are formulated by use of the multi-staged exponential hazard model. As the result, the Markovian transition probability model is employed to represent them. The recovery states of the households are categorized into several ranks, and giving consideration to liquidity constraints, their recovery processes are characterized by hazard models. The Markovian transition probabilities between the recovery states which are defined for the fixed intervals between the investigation points in time, are described by the exponential hazard models. The disaster recovery process of households is investigated by the empirical data set of the households sacrificed by the 2004 October flood in Toyooka City.
