Читать книгу Elementary Regression Modeling - Roger A. Wojtkiewicz - Страница 22

Measurement involves assigning to a unit of analysis a value that captures a certain characteristic of a unit of analysis. For example, the number of credit hours taken in a semester may be assigned to each student, and then the mean number of credit hours taken by students can be calculated. Likewise, each student can be assigned to one of the categories of type of major, and then the percentage of students in each type of major can be calculated.

Researchers refer to the characteristic of the units of analysis that is being measured as a variable. Thus, a variable is a characteristic of a unit that will vary across units. The word variable implies that a characteristic varies across units of analysis. Social scientists generally have no interest in analyzing characteristics that do not vary across units of analysis. Variables contain different amounts of information. Some are merely names, others are names that have hierarchical order, and still others provide measurements in standard units.

Collecting data involves the measurement of variables. One widely used method for collecting data is survey research. Survey research is where a respondent provides information that allows measurement of a variable about a unit of analysis. The unit of analysis may be the respondent or some other unit. The examples in this book use public-use data from the High School Longitudinal Study of 2009 (HSLS). In the data used here, the basic unit of analysis is a student who was a junior in high school in the United States in the spring of 2012. The student provided information for variables as did parents.