Download the dataset and other associated files
You will automatically download a number of files. It is important to look at them before you begin working with the data. Often datasets come with a “codebook” file. This file usually includes the survey questions and responses (in the form of frequency distributions). This particular study does not come with a traditional codebook, instead, there is a “topline report.” Here is a description of all the files that will be included in your download:
- A copy of the questionnaire that was used.
- A topline report that includes “the exact question wording and sequencing, along with results from the current poll and previous polls in which the question was asked.” Unfortunately, the topline report only includes percentages, not raw numbers.
- A methodology file describing how the data were collected.
- A readme file with additional methodological information.
- The datafile. It is already formatted for SPSS! (You can tell because the postscript is .sav which is an SPSS data type). The name of the data file you downloaded will be Feb16 Race_cleaned.sav.
We will refer to the datafile we download from Pew as the original data. We call it that because it is the data as we receive it—before we make any changes at all. This is where a person trying to reproduce our work would start. Save a copy of Feb16 Race_cleaned.sav in your Original-Data folder.
The Metadata folder is for information about your dataset so this is where we will put the other files Pew gave us. Save the topline, the questionnaire, the methodology, and the readme files in the Metadata folder (which is inside your Original-Data folder). Call them something like as RaceAttitudes-Questionairre.doc, RaceAttitudes-Methodology, RaceAttitudes-topline.doc, and RaceAttitudes-readme.txt.