MORTGAGE PREPAYMENT AND DEFAULT DECISIONS - A POISSON REGRESSION APPROACH

This paper uses an extensive and geographically dispersed sample of si ngle-family fired rate mortgages to assess the prepayment and default behavior of individual homeowners. We make use of Poisson regression t o efficiently estimate the parameters of a proportional hazards model for prepayment and default decisions. Poisson regression for grouped s urvival data has several advantages over partial likelihood methods. F irst, when dealing with time-dependent covariates, it is considerably more efficient in terms of computations. Second, it is possible to est imate full-hazard models which include, for example, functions of time as well as multiple rime scales (i.e., age of the loan and calendar t ime), in a much more straightforward manner than partial likelihood me thods for ungrouped data. Third, Poisson regression can be used to est imate non-proportional hazards models such as additive excess risk spe cifications. Taken together, our data and estimation methodology allow us to obtain a better under-standing of the economic factors underlyi ng prepayment and default decisions.