For both conceptual and statistical reasons, Bachman's conclusion is too strong, although it may simply be premature. Conceptually, the victim-offender relationship is important because it helps both the victim and others define whether or not an action is rape and whether or not reporting the crime to the police would be worthwhile. Statistically, in view of prior findings, Bachman could justifiably have used a one-tailed test of significance. In any case, her results are not significantly different from those of a comparable prior study, which found that the victim-offender relationship was important. Furthermore, Bachman's argument of changing societal standards over time calls for a time-series analysis of victim survey data. A table of reporting percentages for victims of stranger and nonstranger rapists over the past 19 years indicates an increase in reporting of nonstranger rapes over time, although over the entire time period, rapes by strangers were more likely to be reported to the police than were rapes by nonstrangers. For Bachman's paper, see NCJ-144624. Table and 23 references (Author abstract modified)