In this story, Guerrini discusses the impact of HRDAG’s work in Guatemala, especially the trials of General José Efraín Ríos Montt and Colonel Héctor Bol de la Cruz, as well as work in El Salvador, Syria, Kosovo, and Timor-Leste. Multiple systems estimation and the perils of using raw data to draw conclusions are also addressed.
Megan Price and Patrick Ball are quoted, especially in regard to how to use raw data.
“From our perspective,” Price says, “the solution to that is both to stay very close to the data, to be very conservative in your interpretation of it and to be very clear about where the data came from, how it was collected, what its limitations might be, and to a certain extent to be skeptical about it, to ask yourself questions like, ‘What is missing from this data?’ and ‘How might that missing information change these conclusions that I’m trying to draw?’”

Amanda Taub of Vox has interviewed HRDAG executive director about the UN Office of the High Commissioner of Human Right’s release of HRDAG’s third report on reported killings in the Syrian conflict.
From the article:
Patrick Ball, Executive Director of the Human Rights Data Analysis Group and one of the report’s authors, explained to me that this new report is not a statistical estimate of the number of people killed in the conflict so far. Rather, it’s an actual list of specific victims who have been identified by name, date, and location of death. (The report only tracked violent killings, not “excess mortality” deaths from from disease or hunger that the conflict is causing indirectly.)

In this story, Carl Bialik of FiveThirtyEight interviews HRDAG executive director Patrick Ball about the process of de-duplication, integration of databases, and machine-learning in the recent enumeration of reported casualties in Syria.
New reports of old deaths come in all the time, Ball said, making it tough to maintain a database. The duplicate-removal process means “it’s a lot like redoing the whole project each time,” he said.

Huffington Post Politics writer Matt Easton interviews Patrick Ball, executive director of HRDAG, about the latest enumeration of killings in Syria. As selection bias is increasing, it becomes harder to see it: we have the “appearance of perfect knowledge, when in fact the shape of that knowledge has not changed that much,” says Patrick. “Technology is not a substitute for science.”

HRDAG executive director Megan Price is interviewed by Mother Jones. An excerpt: “Violence can be hidden,” says Price. “ISIS has its own agenda. Sometimes that agenda is served by making public things they’ve done, and I have to assume, sometimes it’s served by hiding things they’ve done.”

In this interview with Colombian newspaper El Espectador, Patrick Ball is quoted as saying “la gente que no conoce de álgebra nunca debería hacer estadísticas” (people who don’t know algebra should never do statistics).

In this week’s “Top Picks,” IRIN interviews HRDAG executive director Patrick Ball about giant data sets and whether we can trust them. “No matter how big it is, data on violence is always partial,” he says.

Carl Bialik of 538 Politics interviews HRDAG executive director Patrick Ball in an article about the recently released Bureau of Justice Statistics report about the number of annual police killings, both reported and unreported. As Bialik writes, this is a math puzzle with real consequences.

On Wednesday, February 4, in Pristina, international experts praised the Humanitarian Law Centre’s database on victims of the Kosovo conflict, the Kosovo Memory Book. HRDAG executive director Patrick Ball is quoted in the article that appeared in Balkan Transitional Justice.

An excerpt: The “It breaks the human” report released by the human rights group Amnesty International highlights new statistics from the Human Rights Data Analysis Group, or HRDAG, an organization that uses scientific approaches to analyze human rights violations.

Kristian Lum, lead statistician at the Human Rights Data Analysis Group (and letter signatory), fears that “in order to flag even a small proportion of future terrorists, this tool will likely flag a huge number of people who would never go on to be terrorists,” and that “these ‘false positives’ will be real people who would never have gone on to commit criminal acts but will suffer the consequences of being flagged just the same.”

In her work on statistical issues in criminal justice, Lum has studied uses of predictive policing—machine learning models to predict who will commit future crime or where it will occur. In her work, she has demonstrated that if the training data encodes historical patterns of racially disparate enforcement, predictions from software trained with this data will reinforce and—in some cases—amplify this bias. She also currently works on statistical issues related to criminal “risk assessment” models used to inform judicial decision-making. As part of this thread, she has developed statistical methods for removing sensitive information from training data, guaranteeing “fair” predictions with respect to sensitive variables such as race and gender. Lum is active in the fairness, accountability, and transparency (FAT) community and serves on the steering committee of FAT, a conference that brings together researchers and practitioners interested in fairness, accountability, and transparency in socio-technical systems.