It is a myth that data speaks for itself. The analyst speaks for the data. The analyst chooses what questions to ask, what analyses to run, and how they are interpreted and summarized.
I use excerpts from a paper by Gilliam et al. on the media portrayal of crime to walk through one set of choices made by a group of analysts. (The excerpts also highlight the need for reading a paper fully than relying on the abstract alone.)
Abstract
![](https://i0.wp.com/gojiberries.io/wp-content/uploads/2021/09/crime_1.png?resize=565%2C96)
White Violent Criminals Are Overrepresented
![](https://i0.wp.com/gojiberries.io/wp-content/uploads/2021/09/crime_2.png?resize=600%2C234)
White Nonviolent Criminals Are Overrepresented
![](https://i0.wp.com/gojiberries.io/wp-content/uploads/2021/09/crime_3.png?resize=600%2C163)
Relative Underrepresentation Between Violent and Nonviolent Crime is a Problem
![](https://i0.wp.com/gojiberries.io/wp-content/uploads/2021/09/crime_4.png?resize=600%2C240)
![](https://i0.wp.com/gojiberries.io/wp-content/uploads/2021/09/crime_5.png?resize=600%2C241)
Compare the above with the following figure and interpretation from Reaching Beyond Race by Sniderman and Carmines. Rather than focus on the middle two peaks: 28 vs. 43, Sniderman and Carmines write: “we were struck by the relative absence of racial polarization.” (Added on 10/4/2023)
![](https://i0.wp.com/gojiberries.io/wp-content/uploads/2023/10/PXL_20231004_192345807-1024x768.jpg?resize=600%2C450&ssl=1)