Biology has equipped humans to process a great deal of information through their senses, especially vision. For many people one of the easiest ways to remember that information is through pictures and other visual aids. A well-designed image can often help others understand complex and abstract ideas (Robinson & Kiewra, 1995). The benefits of a picture even extend into the world of statistics, though we will use the term visual models to refer to these images.
In Chapter 1, a model was defined as a simplified version of reality. This chapter focuses on visual models, which are pictures that people create so that they can understand their data better. Like all models, visual models are simplified, which means that they are inaccurate to some extent. Nevertheless, visual models can help data analysts understand their data before any analysis actually happens.
• Create a frequency table and histogram from raw data.• Describe histograms in terms of their skewness, kurtosis, and number of peaks.• Correctly choose an appropriate visual model for a dataset.• Identify the similarities and differences that exist among histograms, bar graphs, frequency polygons, line graphs, and pie charts.• Read a scatterplot and understand how each person in a dataset is represented in a scatterplot.
To illustrate the most common visual models, we will use data from the same study that we first saw in Chapter 1. This is a study that one of my students conducted on the relationships that people have with their sibling diagnosed with an autism spectrum disorder (Waite et al., 2015). Some of the data in the study are displayed in Table 3.1.
The table shows six variables: ID, sex, age, sibling age, the level of agreement that the subject has with the statement “I feel that my sibling understands me well,” and the level of language development in the sibling with autism. The table also shows how to interpret each number in the table. For example, for the sex variable, male respondents are labeled as “1,” and female respondents are “2.”
One of the simplest ways to display data is in a frequency table. To create a frequency table for a variable, you need to list every value for the variable in the dataset and then list the frequency, which is the count of how many times each value occurs.