2.2 Summarizing Data

Imagine a dataset containing a hundred respondents and just five variables. Such a dataset would have 500 data points and, while that may seem like a lot, a dataset of this size is considered rather small. Typically, datasets used in sociology (and other social sciences) tend to be larger. What this tells you is that there is an enormous amount of information housed within even an average dataset.

Just like a library containing thousands and thousands of books but no catalog, unless we have the means to make sense of the information – order it, systematize it, categorize it – that information is all but useless. In the previous section, I discussed exploring a dataset in SPSS’s Data View. While that’s a useful (and necessary) task to do before working with any dataset, it doesn’t provide anything more than a sort of global view of the variables in it.

In order to understand any variables better and to be able to fully use the information they contain, we need tools to allow us to zoom in each individual variable, as it were, and to organize that information in a meaningful way.

Two of the most widely used such tools for exploring variables and presenting their information in a summarized, easy to understand way are, as you well know, tables and graphs. In the next section I start by introducing frequency tables; then we will end this chapter with introducing graphical displays.