NHGIS Census Data Workflow using Stata and Python, Miami-Dade County 1990 Block Groups

This data archive provides Stata .do files and a Jupyter Notebook for the cleaning, manipulation, exploration, and mapping of Block Group and County level data. The data workflow is meant to provide useful tools and code to any researcher working Census data at the block group level or other geographic levels. The benefit of using NHGIS data is the ability to obtain older datasets not easily available for download from the Census. Additionally, NHGIS provides the data in a standardized format with codebooks. <br><br>The workflow is broken out into sub-tasks: obtain data, clean data, and explore data. Each task is designed to be completed prior to the subsequent task. The workflow follows guidance from Long (2009).<br><br>Stata .do file features:<br>Loops, local and global macros, and other advanced functions for generating and manipulating variablesCommands to generate and export descriptive statistics tables, histograms, boxplots and between-area analyses to Microsoft Word and image filesJupyter Notebook features:<br>Code and markdown commentary to read in and map the output file from Stata and merge with shapefilesThe data used in this workflow example is used in analysis by Peacock et al. (2014), and Zhang and Peacock (2009). <br><br><br>