How best to aggregate data to a state level?


I am working with a group and we are attempting to examine different effects on voting registration across states from 2000-2013. We are not interested in individual-level data analysis, so we need to aggregate the data to the state level. What is the best way to go about aggregating the data so that we can compare different states’ demographic, economic, and migratory characteristics across this time frame?



As long as proper weights are applied, IPUMS-USA data will be representative at the state level. The person-weight variables indicate how many persons in the population are represented by each sample case, so a state’s population is simply the sum of the PERWTvalues for each respondent in that state. For person-level analyses, use PERWT, and for household-level analyses, use HHWT. You can learn more about sample weights onthis page.

If you are interested in state-level data only, I recommend checking out another MPC project: NHGIS. NHGIS offers many of the official Census tables going back to 1790 at several geographic levels, including state. While NHGIS is primarily focused on mapping data, the summary tables can be extracted independent of shape files as .csv files with optional descriptive headers. Additionally, the Census’ American FactFinder site is another source for Census tables.

I hope this helps.