667 results for search: %E3%80%8C%ED%8A%9C%EB%8B%9D%EB%90%9C%20%ED%8F%B0%ED%8C%85%E3%80%8D%20O6O~5OO~%C6%BC469%20%20%EC%9D%B4%EC%8B%AD%EB%8C%80%EB%85%80%EB%8F%99%EC%95%84%EB%A6%AC%EB%8D%B0%EC%9D%B4%ED%8C%85%20%EC%9D%B4%EC%8B%AD%EB%8C%80%EB%85%80%EB%8F%99%EC%95%84%EB%A6%AC%EB%8F%99%ED%98%B8%ED%9A%8C%E2%98%80%EC%9D%B4%EC%8B%AD%EB%8C%80%EB%85%80%EB%8F%99%EC%95%84%EB%A6%AC%EB%A7%8C%EB%82%A8%D1%87%EC%9D%B4%EC%8B%AD%EB%8C%80%EB%85%80%EB%8F%99%EC%95%84%EB%A6%AC%EB%AA%A8%EC%9E%84%E3%8A%A2%E3%83%A8%E4%9E%8Edesigning/feed/content/colombia/SV-report_2011-04-26.pdf

Celebrating Women in Statistics

kristian lum headshot 2018In 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.

The Statistics of Genocide

Patrick Ball and Megan Price (2018). The Statistics of Genocide. Chance (special issue). February 2018. © 2018 CHANCE.

On or off the record? Detecting patterns of silence about death in Guatemala’s National Police Archive

Tamy Guberek and Margaret Hedstrom (2017). On or off the record? Detecting patterns of silence about death in Guatemala’s National Police Archive. Archival Science. 9 February 2017. © Springer. DOI 10.1007/s10502-017-9274-3.

Tamy Guberek and Margaret Hedstrom (2017). On or off the record? Detecting patterns of silence about death in Guatemala’s National Police Archive. Archival Science. 9 February 2017. © Springer. DOI 10.1007/s10502-017-9274-3.

Working Where Statistics and Human Rights Meet

Robin Mejia and Megan Price (2018). Working Where Statistics and Human Rights Meet. Chance (special issue). February 2018. © 2018 CHANCE.

Data Mining for Good: CJA Drink + Think

At the Center for Justice and Accountability's happy hour, "Drink and Think," Patrick Ball spoke about "Data Mining for Good." The talk included a discussion of how HRDAG brings human rights abusers to justice through data analysis, and HRDAG's work conducting quantitative analysis for truth commissions, NGOs, the UN and other partners. The event was held at Eventbrite. More photos are below. The Center for Justice and Accountability Young Professionals' Committee for Human Rights September 16, 2014 San Francisco, California Link to CJA event page Back to Talks   All photos © 2014 Carter Brooks.

Uncertainty in COVID Fatality Rates

In this Granta article, HRDAG explains that neither the infectiousness nor the deadliness of the disease is set in stone.

Mexico

HRDAG and our partners Data Cívica and the Iberoamericana University created a machine-learning model to predict which counties (municipios) in Mexico have the highest probability of unreported hidden graves. The predictions help advocates to bring public attention and government resources to search for the disappeared in the places where they are most likely to be found. Context For more than ten years, Mexican authorities have been discovering hidden graves (fosas clandestinas). The casualties are attributed broadly—and sometimes inaccurately—to the country’s “drug war,” but the motivations and perpetrators behind the mass murders ...

Clustering and Solving the Right Problem

In our database deduplication work, we’re trying to figure out which records refer to the same person, and which other records refer to different people. We write software that looks at tens of millions of pairs of records. We calculate a model that assigns each pair of records a probability that the pair of records refers to the same person. This step is called pairwise classification. However, there may be more than just one pair of records that refer to the same person. Sometimes three, four, or more reports of the same death are recorded. So once we have all the pairs classified, we need to decide which groups of records refer to the ...

Update of Iraq and Syria Data in New Paper

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 ...

Reflections: Growing and Learning in Guatemala

As a woman, mother and sociologist who is curious about the patterns of our political past in Guatemala, I feel privileged to know and work with the HRDAG team. Collaborating and learning from people like Patrick, Megan, Suzanne, Beatriz and Tamy has been an invaluable gift. I have discovered many things, both human and academic. For example, I’ve learned new ways of seeing what seemed everyday and simple, to discover that not only do the social sciences and statistics work hand in hand, but that they are critical for understanding Guatemala’s reality. Twenty years ago, on 29 December, 1996, Guatemala made history by signing the Guatemala Peace ...

Featured Video

Kristian Lum, lead statistician at HRDAG | Predictive Policing: Bias In, Bias Out | 56 mins

Stay informed about our work

#mc_embed_signup{background:#fff; clear:left; font:14px Helvetica,Arial,sans-serif; } /* Add your own Mailchimp form style overrides in your site stylesheet or in this style block. We recommend moving this block and the preceding CSS link to the HEAD of your HTML file. */ #mc_embed_signup .mc-field-group input { display: block; width: 100%; padding: 8px 0; text-indent: 2%; color: #333 !important; } Subscribe * indicates required Email Address * First Name Last Name Organization (function($) {window.fnames = new ...

Publications

From time to time, we issue our own scientific reports that focus on the statistical aspects of the data analysis we have done in support of our partners. These reports are non-partisan, and they leave the work of advocacy to our partners. You can search our publications by keyword or by year.

Guatemala CIIDH Data

Welcome to the web data resource for the International Center for Human Rights Research (Centro Internacional para Investigaciones en Derechos Humanos, or CIIDH). Here you will find raw data on human rights violations in Guatemala during the period 1960-1996. You're welcome to use it for your own statistical analyses. ASCII delimited (csv) Resource Information Data Dictionary Value Labels File Structure (Variables) These files are between 300-700 kilobytes. The data are stored in a zipped compression format. For an explanation of how the data are structured and what the variables represent, see the data dictionary. If you use ...

Historic verdict in Guatemala—Gen.Efraín Ríos Montt found guilty

I've been working with various projects in Guatemala to document mass violence since 1993, so in 2011, when Claudia Paz y Paz asked me to revisit the analysis I did for the Commission for Historical Clarification examining the differential mortality rates due to homicide for indigenous and non-indigenous people in the Ixil region, I was delighted. We have far better data processing and statistical methods than we had in 1998, plus much more data. I think the resulting analysis is a conservative lower bound on total homicides of indigenous people. (more…)

Hunting for Mexico’s mass graves with machine learning

“The model uses obvious predictor variables, Ball says, such as whether or not a drug lab has been busted in that county, or if the county borders the United States, or the ocean, but also includes less-obvious predictor variables such as the percentage of the county that is mountainous, the presence of highways, and the academic results of primary and secondary school students in the county.”

¿Quién le hizo qué a quién? Planear e implementar un proyecto a gran escala de información en derechos humanos.

Patrick Ball (2008). “¿Quién le hizo qué a quién? Planear e implementar un proyecto a gran escala de información en derechos humanos.” (originally in English at AAAS) Translated by Beatriz Verjerano. Palo Alto, California: Benetech.

Who Did What to Whom? Planning and Implementing a Large Scale Human Rights Data Project

/whodidwhattowhom/contents.html

Patrick Ball. Who Did What to Whom? Planning and Implementing a Large Scale Human Rights Data Project. © 1996 American Association for the Advancement of Science.

Weighting for the Guatemalan National Police Archive Sample: Unusual Challenges and Problems.”

Gary M. Shapiro, Daniel R. Guzmán, Paul Zador, Tamy Guberek, Megan E. Price, Kristian Lum (2009).“Weighting for the Guatemalan National Police Archive Sample: Unusual Challenges and Problems.”In JSM Proceedings, Survey Research Methods Section. Alexandria, VA: American Statistical Association.

Predictive policing tools send cops to poor/black neighborhoods

100x100-boingboing-logoIn this post, Cory Doctorow writes about the Significance article co-authored by Kristian Lum and William Isaac.

Our work has been used by truth commissions, international criminal tribunals, and non-governmental human rights organizations. We have worked with partners on projects on five continents.

Donate

HRDAG

Selected projects

Stay informed about our work

©2024 Human Rights Data Analysis Group. Some rights reserved.
HRDAG is a non-profit project of Community Partners®
Privacy Policy