Books
Planetary Causal Inference
Connor Jerzak and I have started a book writing project on what we have denoted Planetary Causal Inference. Planetary Causal Inference is a framework to combining earth observation (EO), machine learning (ML), and causal inference for analyzing old and new topics in the social sciences.
This framework explores how social science can benefit from EO data to advance understanding of humans as a species and their impact on their environment, society, and economy.
Traditional methods relying on tabular data, like surveys and national statistics, are costly and sometimes limited in scope, hindering planetary-scale analysis.
EO data gathered via satellites offer a complementary approach that captures global, real-time information, enabling researchers to study phenomena like urbanization, poverty, conflict, and deforestation at fine spatial and temporal resolutions.
We introduces the emerging field of causally-oriented EO-based ML, where spatial data derived from images are analyzed using advanced ML models to create proxies for social science metrics and for use in causal inference pipelines.
We discuss how these planetary causal inference methods can produce high-resolution insights about global social issues, providing new ways to assess conflict, sustainable development, and a range of other phenomena.
By combining insights from geography, history, and multi-scale analysis, Planetary Causal Inference lays a foundation for researchers to address broad, integrated questions across household, neighborhood, regional, and global scales with a principled approach to inference.
We have created a website for the book planetarycausalinference.org. For updates, sign up at our Lab’s Substack page aiglobaldevelopmentlab.substack.com.
Trinity of Statistical Learning
Together with Xiao-Li Meng, James Bailie, and Kyla Chasalow, we are writing course notes on Deep Statistics 288 that hopefully will turn into a book.
With the aim to enhance concomitantly the rigor and efficiency of data science for scientific inquires, deep statistics emphasizes principled systems thinking throughout the entire data science ecosystem, from data conception to their postmortem examination for scientific reproducibility and replicability.
This course introduces the trinity of multi-source, multi-phase, and multi-resolution statistical learning, and invites participants think through their implications and implementations in the context of AI and Earth Observations (EO) for sustainable human development.
Theoretically, the course contemplates many trade-offs for ‘data science for science’ such as data quality vs. quantity, data privacy vs. utility, statistical vs. computational efficiencies, inferential robustness vs. relevance.
Practically, it scrutinizes issues such as conceptualizing and collecting complex socioeconomic data, handling messy survey and satellite data, assessing uncertainties with black-box learning, and contemplating causal implications from AI-EO data.
High-level overviews of topics such as data collection, messy data, data privacy, causality, uncertainty analysis, and deep learning are provided as needed.
Political Economy and Economic sociology
Back in 2014, Reza Azarian, Bengt Larson, and I edited an anthology in Swedish on Political Economy and Economic sociology, titled “Ekonomisk sociologi : en introduktion”.
The English translation of the theme is the following.
What does money mean in people’s lives? Which roles and power relations shape our interactions in anonymous markets? How should we understand the relationship between the state and the economy, and what role do worker and employer organizations-as well as political organizations-play in shaping this relationship? How does global capitalism function, and what role do the culture of consumerism and its countercultures play? Are there different paths toward a development that is both ecologically and economically sustainable? There are many questions about our society that are both sociologically relevant and economically related.
This book offers a broad introduction to various research traditions and problem areas within the rapidly expanding field of economic sociology. It can be used as a textbook both in sociology courses and in related disciplines interested in the interplay between economy and society.