The analysis used data on all drivers aged 16 through 24 who were involved in crashes in which someone was killed during the years 1975-1984 in the 48 States in the continental United States. The data came from the Fatal Accident Reporting System of the National Highway Traffic Safety Administration. The analysis excluded motorcycle fatalities, crashes involving more than three motor vehicles, and drivers not living in the State in which the crash occurred. The results were based on a total of 159,262 driver fatal crash involvements, of which 87,153 took place between 8 p.m. and 5 a.m. Raising the purchase age was estimated to produce a 13-percent reduction in nighttime driver fatal crash involvements. Various State, age, and year combinations showed 8 to 18 percent fewer nighttime crash involvements than would otherwise have occurred. A much smaller effect occurred for daytime crashes, which involve alcohol much less often. Eighty-one percent of the drivers involved in fatal crashes were male. Figure, 19 footnotes, and appended methodological and statistical analysis and figures.