How do you know that there are more conflict-related deaths than have been reported to the Commission for Reception, Truth and Reconciliation (CAVR, by its Portuguese acronym)?
Where did the method of multiple systems estimation come from?
If you didn't have access to the whole population, how do you know how representative these data are of the entire population? i.e. How do you control for bias?
What are the total conflict-related mortality numbers? How many people were killed and disappeared between 1974 and 1999? And how many people died due to hunger and illness?
What is the margin of error associated with these results?
What is ...
So much of what I learned at HRDAG was intangible, and I'm grateful to have been able to go deep.
One of the three main goals of HRDAG is education and outreach, and to that end we use Creative Commons licenses for all of our blogposts and, whenever possible, for our publications. Using a Creative Commons license makes it clear that educators are free to use HRDAG's publications, in their entirety, and with the peace of mind that they are doing so with our blessing.
Also, the use of the Creative Commons license allows us to participate in and encourage the creation of a digital commons, which we feel helps to advance another one of our goals, the creation of knowledge. We feel that it’s important to offer up our publications for use and reuse ...
We stand with our partners and every organizer fighting for justice.
In early 2006 I joined the Historical Archive of the National Police (Archivo Histórico de la Policía Nacional, or AHPN) without knowing the impact it would have on my future. I started with cleaning, organizing and classifying documents—and learning, with other colleagues, what a historical archive is and how it works.
By April of that year, parallel to these learning processes, I was selected along with 20 other people to begin work on the challenging Quantitative Research project. I started as a "coder," transferring key content from documents into a database. (more…)
Much of the work we do at HRDAG involves estimating the number of undocumented deaths using a statistical technique called multiple systems estimation (MSE, described in more detail here). One of our goals is to make this class of methods more broadly available to human rights researchers. In particular, we are finding that Bayesian approaches are extremely valuable for MSE. Accordingly, we are pleased to offer a new R package called dga (“decomposable graphs approach”) that performs Bayesian model averaging for MSE.
The main function in this package implements a model created by David Madigan and Jeremy York. This model was designed to ...
After almost two months of searching for the perfect fit, we’re very pleased to announce that Josh Shadlen has joined HRDAG as our new technical lead. Finding Josh was no easy feat. We were looking for what many people would call a “data scientist,” that is, someone with expertise in both computer science and statistics. These days, “data science” is one of the hottest fields out there.
Bringing the perfect mix of academic depth and thoughtful reflection, Josh stood out for us. With prior jobs including gigs at Silicon Valley startups and Twitter, he’s got high-level (more…)
Kevin Uhrmacher of the Washington Post prepared a graph that illustrates reported deaths over time, by number of organizations reporting the deaths.
We're thrilled to announce that Tarak Shah has joined our team as our new data scientist.
The Sri Lankan army must explain to the families of the disappeared and missing what happened to an estimated 500 Tamils who disappeared in their custody at the war end on/around 18 May 2009, said two international NGOs who have been collating and analysing lists of names.
Sri Lanka has one of the largest numbers in the world of enforced disappearances but these 500 represent the largest number of disappearances all in one place and time in the country. For a detailed account of the process of estimating the 500 please see: “How many people disappeared on 17-19 May 2009 in Sri Lanka?” .
One of the researchers, a Michigan State PhD candidate named William Isaac, had not previously heard of New Orleans’ partnership with Palantir, but he recognized the data-mapping model at the heart of the program. “I think the data they’re using, there are serious questions about its predictive power. We’ve seen very little about its ability to forecast violent crime,” Isaac said.
Algorithmic tools like PredPol were supposed to reduce bias. But HRDAG has found that racial bias is baked into the data used to train the tools.
This blog is a part of International Justice Monitor’s technology for truth series, which focuses on the use of technology for evidence and features views from key proponents in the field.
As highlighted by other posts in this series, emerging technology is increasing the amount and type of information available, in some contexts, to criminal and other investigations. Much of what is produced by these emerging technologies (Facebook posts, tweets, YouTube videos, text messages) falls in the category we refer to as “found” data. By “found” data we mean data not generated for a specific investigation, but instead, that is generated for ...
Tools like Compas allegedly help judges predict future criminal activities and eliminate bias. HRDAG and partners showed how the tools recycle bias.
Executive director Megan Price is interviewed in The New York Times’ Sunday Review, as part of a series known as “Download,” which features a biosketch of “Influencers and their interests.”
HRDAG director of research Patrick Ball is quoted in this New York Times article about a paper that models death tolls in Gaza.
