2. In a survey, indicators consist of questionnaire items. One could ask, as in the 2004 and 2006 General Social Survey, how often have you done each of the following things in the past year? For each item, indicate if you have done this (1) more than once a week, (2) once a week, (3) once a month, (4) at least 2 or 3 three times in the past year, (5) once in the past year, or (6) not at all in the past year.

a. Given blood.
b. Given food or money to a homeless person.
c. Done volunteer work for a charity.

3. (a) ordinal; (b) ratio; (c) nominal; (d) ordinal; (e) ordinal.

4. Error may be created by personal differences in (1) ability to articulate or write, (2) prior knowledge of the material, (3) fatigue or health, and (4) mental preparedness or confidence; by situational effects such as (5) distracting noise or an oppressively warm room temperature; and by features of the test such as (6) a set of questions that are too difficult or unrepresentative of the material and (7) lack of clarity in the instructions for taking the exam or in one or more individual questions. (1) and (2) create systematic error insofar as they bias the test in favor of persons possessing characteristics other than that which is being tested; (6) creates systematic error by underestimating the extent to which all students know the material. The other sources of error create random or chance differences in the scores of individuals taking the test. Random errors affect reliability, which in turn affects validity. Systematic errors affect validity; however, they do not reveal themselves in tests of reliability since they do not cause measures to fluctuate randomly either from one respondent to the next or from one administration of the measure to the next.

5. Underreporting domestic violence would result in systematic error because the error is in only one direction. Systematic errors undermine validity; but if individuals and/or groups consistently underreport, this would have no effect on reliability

6. (a) “Donating blood” fits the conceptual definition of altruism: it is an act of helping that is unlikely to be motivated by anticipated rewards. A drawback to this question, however, is that those who do not give blood may be unable to do so or may choose not to because of the fear and anxiety associated with blood donation. So, this question should not stand alone as a measure of altruism but should be included in a larger set of questions that tap other ways of behaving altruistically.

(b) It is possible that someone could be compensated or in other ways rewarded for “helping someone pack and move,” in which case this would not be an altruistic act.

(c) It seems likely that most people will be motivated to become a “big brother” or “big sister” purely to help those in need. But some students may do so to build up their resumes.

In short, all three questions appear to tap altruistic acts but also may be subject to systematic error. That is why the best strategy in measuring a complex concept like altruism is to use multiple questions, each of which may be subject to different sources of error. In chapter 13 we further discuss the logic and value of using multiple indicators to measure concepts.

The reliability of multiple-item (composite) measures is almost always assessed with an internal consistency estimate such as Cronbach’s alpha. To assess validity, you must examine the association of the new composite measure with one or more existing measures of altruism or with measures of other variables such as empathy with which altruism should be associated.