Kristian Lum, Erwin Ma and Mike Baiocchi (2017). The causal impact of bail on case outcomes for indigent defendants in New York City. Observational Studies 3 (2017) 39-64. 31 October 2017. © 2017 Institute of Mathematical Statistics.
Kristian Lum, Erwin Ma and Mike Baiocchi (2017). The causal impact of bail on case outcomes for indigent defendants in New York City. Observational Studies 3 (2017) 39-64. 31 October 2017. © 2017 Institute of Mathematical Statistics.
Patrick Ball (2016). The case against a golden key. Foreign Affairs. September 14, 2016. ©2016 Council on Foreign Relations, Inc. All Rights Reserved.
Patrick Ball (2016). The case against a golden key. Foreign Affairs. September 14, 2016. ©2016 Council on Foreign Relations, Inc. All Rights Reserved.
New paper in Biometrika, co-authored by HRDAG's Kristian Lum and James Johndrow: Theoretical limits of microclustering in record linkage.
In a CNN interview predicting a Nobel Peace Prize winner, Henrik Urdal from PRIO talks about his shortlist and HRDAG.
This morning I got a query from a journalist asking for our data from the report we published yesterday. The journalist was hoping to create an interactive infographic to track the number of deaths in the Syrian conflict over time. Our data would not support an analysis like the one proposed, so I wrote this reply.
We can't send you these data because they would be misleading—seriously misleading—for the purpose you describe. Here's why:
What we have is a list of documented deaths, in essence, a highly non-random sample, though a very big one. We like bigger samples because we think that they must be closer to true. The mathematical justificat...
The data science field is always changing, which means that I'll always be learning.
What follows is an elaborate criss-crossing of collaborations—retreat is a time to embrace the productivity that comes with being in the same room.
It was July of 2006, I’d spent five years working at a local human rights NGO in Bogotá, and I had reached retirement age. But then a whole new world opened up for me to discover. Tamy Guberek, then HRDAG Latin America coordinator, whom I had met at the NGO, approached me about becoming part of the HRDAG Colombia team as a research/administrative assistant. Over a cup of suitably Colombian coffee, the deal was quickly "signed.” My responsibilities ranged from fundraising to translations, from support in data gathering for estimates on homicides and disappearances in various regions of Colombia to editorial support to different Benetech-HRDAG ...
Kristian Lum (2017). Limitations of mitigating judicial bias with machine learning. Nature. 26 June 2017. © 2017 Macmillan Publishers Limited, part of Springer Nature. All rights reserved. Nature Human Behavior. DOI 10.1038/s41562-017-0141.
.
Kristian Lum (2017). Limitations of mitigating judicial bias with machine learning. Nature. 26 June 2017. © 2017 Macmillan Publishers Limited, part of Springer Nature. All rights reserved. Nature Human Behavior. DOI 10.1038/s41562-017-0141.
On November 26, HRDAG colleague Anita Gohdes was awarded the German Dissertation Prize for the Social Sciences. The patron of the prize is the President of the German Parliament, Norbert Lammert, who presented Anita with the award.
Anita’s dissertation, “Repression 2.0: The Internet in the War Arsenal of Modern Dictators,” investigates the role played by social media networks in modern dictatorships, such as President Assad’s regime in Syria. On one hand, Anita argues, social media can help opposition groups to organize more effectively, but on the other hand, the same networks allow regimes to monitor and manipulate the population. ...
But while HRDAG’s estimate relied on the painstaking efforts of human workers to carefully weed out potential duplicate records, hashing with statistical estimation proved to be faster, easier and less expensive. The researchers said hashing also had the important advantage of a sharp confidence interval: The range of error is plus or minus 1,772, or less than 1 percent of the total number of victims.
“The big win from this method is that we can quickly calculate the probable number of unique elements in a dataset with many duplicates,” said Patrick Ball, HRDAG’s director of research. “We can do a lot with this estimate.”
Dr. Patrick Ball recently visited the Plutopia News Network podcast for a wide-ranging, inspiring conversation about his work for the Human Rights Data Analysis Group.
Patrick spoke about how he first discovered human rights work during his time in El Salvador with the Peace Brigades International. That led to his ongoing work as a statistician and computer programmer working to assess and analyze human rights violations. He also unpacked some common statistical techniques used by researchers at Human Rights Data Analysis Group, such as multiple systems estimation, which uses multiple different datasets to gain insights into the data we don't ...
We stand with our partners and every organizer fighting for justice.
Help Us Advance Justice And Human Rights
Your donations enable HRDAG to use data science and help our partners
answer important questions about human rights and patterns of mass violence.
Or Write a Check
If you prefer to donate by check, please make it payable to: “Community Partners for HRDAG”
Mail it to:
Community Partners
P. O. Box 741265
Los Angeles, CA 90074-1265
Today we’re very pleased to hear of the verdict finding Hissène Habré guilty of crimes against humanity. Habré, president of Chad from 1982 to 1990, has been sentenced to life in prison in Dakar, Senegal, where he was tried. He is the first former head of state to be tried and found guilty of crimes against humanity in one country (Chad) by the courts of another country (Senegal). Here’s more on the verdict from The Guardian.
The verdict resonates especially with HRDAG because of our role in the trial. In September 2015, director of research Patrick Ball testified as an expert witness about the very high rates of prison mortality in ...
HRDAG contributes to the project by helping to classify, filter, extract, and standardize the records so that they can be useful in the database.
