Data on weather and aggravated assaults were obtained to determine whether the curvilinear relationship between temperature and violence previously observed in Minneapolis, Minnesota (E.G. Cohn and J. Rotton, 1997), could be replicated. The data consisted of calls for services received by police in Dallas between January 1, 1994, and December 31, 1995. Controlling for holidays, school closings, time of day, day of the week, season of the year, and their interactions, moderator-variable autoregression analyses indicated that assaults were an inverted U-shaped function of temperature. Replicating past research, the curvilinear relationship was dominant during daylight hours and spring months, whereas linear relationships were observed during nighttime hours and other seasons. The results are interpreted in terms of routine activity theory and the negative affect escape model of aggression.