Criminology by Larry J. Siegel disagrees, asserting that while it decreases your chance of being robbed, it increases your chances of being injured or killed.
edit: Zimring and Zuehl's study shows that robberies with "active noncooperation" (refusal to hand over money, attempt to flee, resistence with force) had a death rate fourteen higher than those where the victims cooperated, and that victims who simply denied having money (but did not otherwise resist) had a death rate twice as high as those who cooperate.
However, in the same paragraph it cites Gary Kleck on the use of guns, and it says that potential victims should be encouraged to fight back, and that resistance with a gun is significantly better than the other forms of resistance (and a conclusion that it is better to fight than to flee).
It's a surprising conclusion for me (I'm mostly anti-guns, though I'd prefer some other option like, say, tasers, to be available for self-defense)
Kleck's advice is for rape victims, not robbery victims.
The first citations I can find in google scholar indicate that the odds of being killed during/after rape is roughly two orders of magnitude higher than the odds of being killed during/after a "cooperative" robbery, thus the differing calculus.
I found the opposite on his abstract (though Googling around says that his claims are often disputed):
"This study assessed the impact of sixteen types of victim self protection (SP) actions on three types of outcomes of criminal incidents: first, whether the incident resulted in property loss, second, whether it resulted in injury to the victim, and, third, whether it resulted in serious injury. Data on 27,595 personal contact crime incidents recorded in the National Crime Victimization Survey for the 1992 to 2001 decade were used to estimate multivariate models of crime outcomes with logistic regression. Results indicated that self-protection in general, both forceful and non forceful, reduced the likelihood of property loss and injury, compared to nonresistance. A variety of mostly forceful tactics, including resistance with a gun, appeared to have the strongest effects in reducing the risk of injury, though some of the findings were unstable due to the small numbers of sample cases. The appearance, in past research, of resistance contributing to injury was found to be largely attributable to confusion concerning the sequence of SP actions and injury. In crimes where both occurred, injury followed SP in only 10 percent of the incidents. Combined with the fact that injuries following resistance are almost always relatively minor, victim resistance appears to be generally a wise course of action."
