I just returned from the Full Count IPUMS data workshop at the Data-Intensive Research Conference that was hosted by the Network on Data Intensive Research on Aging and IPUMS. The theme of this conference was “Linking Records”.
It was the best workshop and conference that I’ve ever attended. I’d attended the conference remotely in the past. But attending the workshop was exceptional. Myself and about 20 other people were flown to the Minneapolis Population Center and put up in a hotel during our stay (that made the conference a low-stress affair). The whole workshop was well organized, the speakers built on one another’s content, and there was a hands-on lab for us to complete. I felt my human capital growing by the hour.
I do some economic history and I’ve used historical census data in my work. But I had just barely grazed the opportunities that are available from linking individual records between censuses. I started some linking work earlier this summer, but the workshop was eye-opening. I got to rub elbows with the people who create, clean, and maintain the digital census data. Of course I’ve read the data documentation, but that’s different from talking to the curators and hearing how they think about the data.
I got to hear from leaders in the field of record linking, linking methods, and the data sets that can be linked. There is an amazing amount of linkable data out there. A lot of that data is accessible by the public and there’s “restricted data” with more details that can be accessed too. There are also multiple linking methods and an entire field of study that evaluates the quality of linked records. I came away knowing how to think about my linked data and the things that referees would expect to see as a matter of course.
The conference mostly featured applied work in order to exhibit the possibilities. We were all in the same presentation hall, so we had all seen the same content and we had plenty to talk about during the breaks. We were more focused than I’ve ever experienced at a large national or regional conference. Further, each day ended on the earlier side with the social hours ending around 5:30. That meant that I could go back to the hotel room and investigate more the things that I had learned that day and then follow up with folks the next day.
Everyone was very patient and kind and excited about the data. There was a variety of experience levels and familiarity with the data. The ranks ranged from undergraduate students up through full professors and everyone was generous with their time. Not everyone used “historical” data. Plenty of people used linkable modern data. There was something for everyone.
Ultimately, I can’t recommend the workshop enough to anyone who does research with individuals and laments the limitations of their data sets. Experimentalists, you *may* be able to access individuals’ census data! If the data is linkable, then the limits may be less restrictive than you know! If you can’t attend the workshop, then I at least recommend attending the conference remotely. Historically, I would have it up on one of my monitors while I worked, giving special attention to the talks that I found most interesting. As an aside, wouldn’t that be great generally? Just to have a queue of presentations that you can mainline into your office with no pressure to look like you’re paying attention, with some big hefty golden nuggets scattered throughout. What a world we live in!
You should attend the workshop and conference if you ever have the opportunity.
Economist Writing Every Day 