678 results for search: %EB%82%A8%EA%B5%AC%ED%9C%B4%EA%B2%8C%ED%85%94%E3%81%ACjusobot%E3%80%81%EF%BD%830m%E2%99%99%EB%82%A8%EA%B5%AC%EA%B1%B4%EB%A7%88%E2%99%A9%EB%82%A8%EA%B5%AC%EC%97%85%EC%86%8C%E2%9C%88%EB%82%A8%EA%B5%AC%EB%A6%BD%EB%B0%A9%20%EB%82%A8%EA%B5%AC%EB%8B%AC%EB%A6%BC/feed/content/colombia/SV-report_2011-04-26.pdf
James E Johndrow, Kristian Lum and D B Dunson (2018). Theoretical limits of microclustering for record linkage. Biometrika. 19 March 2018. © 2018 Oxford University Press. DOI 10.1093/biomet/asy003.
John E Johndrow, Kristian Lum and D B Dunson (2018). Theoretical limits of microclustering for record linkage. Biometrika. 19 March 2018. © 2018 Oxford University Press. DOI 10.1093/biomet/asy003.
Shira Mitchell, Al Ozonoff, Alan Zaslavsky, Bethany Hedt-Gauthier, Kristian Lum and Brent Coull (2013). A Comparison of Marginal and Conditional Models for Capture-Recapture Data with Application to Human Rights Violations Data. Biometrics, Volume 69, Issue 4, pages 1022–1032, December 2013. © 2013, The International Biometric Society. DOI: 10.1111/biom.12089.
Shira Mitchell, Al Ozonoff, Alan Zaslavsky, Bethany Hedt-Gauthier, Kristian Lum and Brent Coull (2013). A Comparison of Marginal and Conditional Models for Capture-Recapture Data with Application to Human Rights Violations Data. Biometrics, , Issue 4, pages 1022–1032, December 2013. © 2013, The International Biometric Society. DOI: 10.1111/biom.12089.
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.
FiveThirtyEight
Carl Bialik
August 23, 2014
Link to story on FiveThirtyEight
Related blogpost (Updated Casualty Count for Syria)
Back to Press Room
Kevin Uhrmacher of the Washington Post prepared a graph that illustrates reported deaths over time, by number of organizations reporting the deaths.
Washington Post
Kevin Uhrmacher
August 22, 2014
Link to story on Washington Post
Related blogpost (Updated Casualty Count for Syria)
Back to Press Room
How do police officer booking decisions affect tools relied upon by judges?
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 ...
This week The Statistical Journal of the IAOS published a new(ish) paper by Megan Price and Patrick Ball. The open-access paper, Selection bias and the statistical patterns of mortality in conflict, is a revisiting and updating of both the Iraq and Syria examples used in an earlier paper, Big Data, Selection Bias, and the Statistical Patterns of Mortality in Conflict, which was published last year inThe SAIS Review of International Affairs (JHU Press, 2014).
HRDAG believes that the concerns highlighted by these examples are important for a wide variety of audiences, including both the foreign policy readers reached by The SAIS Review and the ...
We are pleased to announce that HRDAG will be supported by two additions to our Advisory Board, Julie Broome and Frank Schulenburg.
We’ve worked with Julie for many years, getting to know her when she was Director of Programmes at The Sigrid Rausing Trust. She is now the Director of London-based Ariadne, a network of European funders and philanthropists. She worked at the Trust for seven years, most notably Head of Human Rights, before becoming Director of Programmes in 2014. Before joining the Trust she was Programme Director at the CEELI Institute in Prague, where she was responsible for conducting rule of law-related trainings for judges and ...
Donating to HRDAG
Thank you for your interest in making a donation to the Human Rights Data Analysis Group to help us use science to support our partners in the human rights world.
You can make a donation by credit card on the Community Partners® Network for Good page. HRDAG is a "project of Community Partners," and right below the section on payment information, you'll be able to select "Human Rights Data Analysis Group" from a drop-down menu. (On most browsers, if you use this link, HRDAG will be pre-selected on the drop-down menu.)
This transaction will appear on your credit card statement as "Network for Good."
If you donate by check, ...
The online version of the 2019 Year-End Review will appear in January 2020.
Next week, on June 11, Oxford University Press officially puts Counting Civilian Casualties: An Introduction to Recording and Estimating Nonmilitary Deaths in Conflict on the market. This textbook, edited by Taylor B. Seybolt, Jay D. Aronson, and Baruch Fischhoff, responds to the increasing concern for civilians in conflict and aims to promote scientific dialogue by highlighting the strengths and weaknesses of the most commonly used casualty recording and estimation techniques.
HRDAG is very well represented here, as our colleagues have co-authored four chapters, and Nicholas Jewell, who sits on our Science Committee, has co-authored a fifth. ...
Kristian Lum: “The historical over-policing of minority communities has led to a disproportionate number of crimes being recorded by the police in those locations. Historical over-policing is then passed through the algorithm to justify the over-policing of those communities.”
Mailing List Subscription
We use Mailchimp to help us keep track of community members who want to stay informed about what HRDAG is doing and thinking. If you self-subscribe to our list, we will never share your contact information. We will never subscribe anyone who does not explicitly agree to a subscription.
Over the course of a year, we mail quarterly letters and fundraising letters, as well as one or two updates as events demand. If, during the course of a fundraising campaign, you make a donation, we will do our best to remove you from the remainder of fundraising mailings that year. We may use your contact information to invite you to ...
We have specified "Some Rights Reserved" on our website, instead of the more conventional "All Rights Reserved." This is because some of our web content is covered by a Creative Commons license, which means that it may be copied and even re-purposed, with some stipulations. We have made this decision because HRDAG wants to contribute to the digital commons, defined by Creative Commons as "a pool of content that can be copied, distributed, edited, remixed, and built upon, all within the boundaries of copyright law."
Our Creative Commons License
We are using the Attribution-NonCommercial-ShareAlike license, also known as the BY-NC-SA license. Here is ...
“If you’re not careful, you risk automating the exact same biases these programs are supposed to eliminate,” says Kristian Lum, the lead statistician at the San Francisco-based, non-profit Human Rights Data Analysis Group (HRDAG). Last year, Lum and a co-author showed that PredPol, a program for police departments that predicts hotspots where future crime might occur, could potentially get stuck in a feedback loop of over-policing majority black and brown neighbourhoods. The program was “learning” from previous crime reports. For Samuel Sinyangwe, a justice activist and policy researcher, this kind of approach is “especially nefarious” because police can say: “We’re not being biased, we’re just doing what the math tells us.” And the public perception might be that the algorithms are impartial.
Richard Conibere, Jana Asher, Kristen Cibella, Jana Dudukovic, Rafe Kaplan, and Patrick Ball. Sierra Leone Statistical Appendix, A Report by the Benetech Human Rights Data Analysis Group and the American Bar Association Central European and Eurasian Law Initiative to the Truth and Reconciliation Commission. October 5, 2004.
Weapons of Math Destruction: invisible, ubiquitous algorithms are ruining millions of lives. Excerpt:
As Patrick once explained to me, you can train an algorithm to predict someone’s height from their weight, but if your whole training set comes from a grade three class, and anyone who’s self-conscious about their weight is allowed to skip the exercise, your model will predict that most people are about four feet tall. The problem isn’t the algorithm, it’s the training data and the lack of correction when the model produces erroneous conclusions.
