Measuring the frequency of regular behaviors: Comparing the "typical week" to the "past week"

Social scientists often measure the frequency with which people perform behaviors executed regularly throughout their daily lives, but there is no standard approach to this measurement task. some investigators have asked respondents about their behavior during a "usual" or "typical" day, week, or month, whereas others sought to describe the same sorts of behavior patterns by asking about the most recent day, week, or month. This paper compares the validity of "typical" week and "past" week reports for assessing habitual behavior patterns using data from the 1989 National Election Study Pilot, in which respondents were randomly assigned to report TV news program and newspaper exposure during either a typical week or the past week. The predictive validity of the measures was assessed using objective tests of current events knowledge and identification of political figures, as well as self-assessments of political knowledge. The typical week questions consistently manifested superior predictive validity, especially among the most educated respondents.