The name is absent

predictor variables are restricted to be time-constant and the unobserved heterogeneity
distribution is assumed to be characterized by two mass points.

As can be seen in Table 5 an increase in the delay between high school graduation
and college enrollment significantly raises the dropout hazard for both those first entering
two-year institutions and those first entering four-year institutions. The impact of an
increase in enrollment delay on the graduation hazard, while negative both for individuals
first entering two-year and for individuals first entering four-year institutions is
statistically significant only for those first entering two-year institutions.

To assess the magnitude of the effect of delaying enrollment on the probability of
four-year college completion both for those who first enter a two-year institution and for
those who first enter a four-year institution, simulations were performed in which an
individual’s enrollment delay was alternatively set to 0 (enrollment immediately after high
school) and 1 (enrollment after delaying one year ). The college dropout and completion
hazards from these simulations are presented in Figures 6 and 7, respectively, for those
who first enter a four-year institution and Figures 8 and 9, respectively, for those who
first enter a two-year institution. From these hazard estimates, one can show that the
estimated probability of obtaining a four-year degree when the delay until college
enrollment increases from 0 to 1 year declines by 27.7 percent and 25.4 percent for those
first entering four-year and two-year institutions, respectively.

22

<<   22   23   24   25   26   27   28   >>

More intriguing information