A study by the New York City government of a program to prevent homelessness found that over 90 percent of families who signed up to receive job training, counseling services, and emergency money did not end up in homeless shelters. But one expert noted that just because 90 percent of the families stayed out of shelters did not prove that the program was effective. Rather, it was possible that people who sought out help from the program were simply more resourceful to begin with and better at patching together various means of housing aid [Buckley, 2010]. Relate this challenge to the New York homelessness study to the problems faced by economists trying to assess the causal effects of economic policy. How could you design an experimental study to estimate the impact of job training, counseling services, and emergency money on homelessness?