This chapter discussed the Hawthorne effect, a measurement problem that can arise when people are award they are being studied. In public opinion surreys, similar measurement issues, social desirability effects, can distort expressed levels of support for controversial social policies, such as affirmative action programs that give hiring preferences to blacks. As you can imagine, this problem is often heightened when respondents are aware of the demographic characteristics of the interviewer's race or sex. Consider an example, using respondent's knowledge of the interviewer's sex. The $2012$ General Social Survey asks respondents the following question: $"$Do you happen to have in your home or garage any guns or revolvers? $1)$ yes, $2)$ no$,3)$ refused."