NotesFAQContact Us
Collection
Advanced
Search Tips
Back to results
ERIC Number: ED669697
Record Type: Non-Journal
Publication Date: 2020-Apr-14
Pages: 7
Abstractor: As Provided
ISBN: N/A
ISSN: N/A
EISSN: N/A
Available Date: 2020-03-30
Measuring the Predictability of Life Outcomes with a Scientific Mass Collaboration
Matthew J. Salganik1; Ian Lundberg1; Alexander T. Kindel1; Caitlin E. Ahearn2; Khaled Al-Ghoneim3; Abdullah Almaatouq4,5; Drew M. Altschul6; Jennie E. Brand2,7; Nicole Bohme Carnegie8; Ryan James Compton9; Debanjan Datta10; Thomas Davidson11; Anna Filippova12; Connor Gilroy13; Brian J. Goode14; Eaman Jahani15; Ridhi Kashyap16,17,18; Antje Kirchner19; Stephen McKay20; Allison C. Morgan21; Alex Pentland5; Kivan Polimis22; Louis Raes23; Daniel E. Rigobon24; Claudia V. Roberts25; Diana M. Stanescu26; Yoshihiko Suhara5; Adaner Usmani27; Erik H. Wang26; Muna Adem28; Abdulla Alhajri29; Bedoor AlShebli30; Redwane Amin31; Ryan B. Amos25; Lisa P. Argyle32; Livia Baer-Bositis33; Moritz Büchi34; Bo-Ryehn Chung35; William Eggert36; Gregory Faletto37; Zhilin Fan38; Jeremy Freese33; Tejomay Gadgil39; Josh Gagné33; Yue Gao40; Andrew Halpern-Manners28; Sonia P. Hashim25; Sonia Hausen33; Guanhua He41; Kimberly Higuera33; Bernie Hogan42; Ilana M. Horwitz43; Lisa M. Hummel33; Naman Jain24; Kun Jin44; David Jurgens45; Patrick Kaminski28,46; Areg Karapetyan47,48; E. H. Kim33; Ben Leizman25; Naijia Liu26; Malte Möser25; Andrew E. Mack26; Mayank Mahajan25; Noah Mandell49; Helge Marahrens28; Diana Mercado-Garcia43; Viola Mocz50; Katariina Mueller-Gastell33; Ahmed Musse51; Qiankun Niu31; William Nowak52; Hamidreza Omidvar53; Andrew Or25; Karen Ouyang25; Katy M. Pinto54; Ethan Porter55; Kristin E. Porter56; Crystal Qian25; Tamkinat Rauf33; Anahit Sargsyan57; Thomas Schaffner25; Landon Schnabel33; Bryan Schonfeld26; Ben Sender58; Jonathan D. Tang25; Emma Tsurkov33; Austin van Loon33; Onur Varol59,60; Xiafei Wang61; Zhi Wang60,62; Julia Wang25; Flora Wang58; Samantha Weissman25; Kirstie Whitaker63,64; Maria K. Wolters65; Wei Lee Woon66; James Wu67; Catherine Wu25; Kengran Yang53; Jingwen Yin38; Bingyu Zhao68; Chenyun Zhu38; Jeanne Brooks-Gunn69,70; Barbara E. Engelhardt25,35; Moritz Hardt71; Dean Knox26; Karen Levy72; Arvind Narayanan25; Brandon M. Stewart1; Duncan J. Watts73,74,75; Sara McLanahan1
Grantee Submission, Proceedings of the National Academies of Science v117 n15 p8398-8403 2020
How predictable are life trajectories? We investigated this question with a scientific mass collaboration using the common task method; 160 teams built predictive models for six life outcomes using data from the Fragile Families and Child Wellbeing Study, a high-quality birth cohort study. Despite using a rich dataset and applying machine-learning methods optimized for prediction, the best predictions were not very accurate and were only slightly better than those from a simple benchmark model. Within each outcome, prediction error was strongly associated with the family being predicted and weakly associated with the technique used to generate the prediction. Overall, these results suggest practical limits to the predictability of life outcomes in some settings and illustrate the value of mass collaborations in the social sciences.
Publication Type: Journal Articles; Reports - Research
Education Level: N/A
Audience: N/A
Language: English
Sponsor: Institute of Education Sciences (ED); National Science Foundation (NSF); Eunice Kennedy Shriver National Institute of Child Health and Human Development (NICHD) (DHHS/NIH)
Authoring Institution: N/A
IES Funded: Yes
Grant or Contract Numbers: R305B140009; 1760052; P2CHD047879; R01HD36916; R01HD39135; R01HD40421
Department of Education Funded: Yes
Author Affiliations: 1Department of Sociology, Princeton University, Princeton, NJ; 2Department of Sociology, University of California, Los Angeles, CA; 3Hawaz, Riyadh, Saudi Arabia; 4Sloan School of Management, Massachusetts Institute of Technology, Cambridge, MA; 5Media Lab, Massachusetts Institute of Technology, Cambridge, MA; 6Mental Health Data Science Scotland, Department of Psychology, The University of Edinburgh, Edinburgh, United Kingdom; 7Department of Statistics, University of California, Los Angeles, CA; 8Department of Mathematical Sciences, Montana State University, Bozeman, MT; 9Human Computer Interaction Lab, University of California, Santa Cruz, CA; 10Discovery Analytics Center, Virginia Polytechnic Institute and State University, Arlington, VA; 11Department of Sociology, Cornell University, Ithaca, NY; 12GitHub, San Francisco, CA; 13Department of Sociology, University of Washington, Seattle, WA; 14Social and Decision Analytics Laboratory, Fralin Life Sciences Institute, Virginia Polytechnic Institute and State University, Arlington, VA; 15Institute for Data, Systems and Society, Massachusetts Institute of Technology, Cambridge, MA; 16Department of Sociology, University of Oxford, Oxford, United Kingdom; 17Nuffield College, University of Oxford, Oxford, United Kingdom; 18School of Anthropology and Museum Ethnography, University of Oxford, Oxford, United Kingdom; 19Program for Research in Survey Methodology, Survey Research Division, RTI International, Research Triangle Park, NC; 20School of Social and Political Sciences, University of Lincoln, Brayford Pool, Lincoln, United Kingdom; 21Department of Computer Science, University of Colorado, Boulder, CO; 22Center for the Study of Demography and Ecology, University of Washington, Seattle, WA; 23Department of Economics, Tilburg School of Economics and Management, Tilburg University, Tilburg, The Netherlands; 24Department of Operations Research and Financial Engineering, Princeton University, Princeton, NJ; 25Department of Computer Science, Princeton University, Princeton, NJ; 26Department of Politics, Princeton University, Princeton, NJ; 27Department of Sociology, Harvard University, Cambridge, MA; 28Department of Sociology, Indiana University, Bloomington, IN; 29Department of Nuclear Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA; 30Computational Social Science Lab, Social Science Division, New York University Abu Dhabi, Abu Dhabi, United Arab Emirates; 31Bendheim Center for Finance, Princeton University, Princeton, NJ; 32Department of Political Science, Brigham Young University, Provo, UT; 33Department of Sociology, Stanford University, Stanford, CA; 34Department of Communication and Media Research, University of Zurich, Zurich, Switzerland; 35Center for Statistics & Machine Learning, Princeton University, Princeton, NJ; 36Department of Mechanical and Aerospace Engineering, Princeton University, Princeton, NJ; 37Statistics Group, Department of Data Sciences and Operations, Marshall School of Business, University of Southern California, Los Angeles, CA; 38Department of Statistics, Columbia University, New York, NY; 39Center for Data Science, New York University, New York, NY; 40Department of Industrial Engineering and Operations Research, Columbia University, New York, NY; 41Department of Molecular Biology, Princeton University, Princeton, NJ; 42Oxford Internet Institute, University of Oxford, Oxford, United Kingdom; 43Graduate School of Education, Stanford University, Stanford, CA; 44Department of Computer Science, Ohio State University, Columbus, OH; 45School of Information, University of Michigan, Ann Arbor, MI; 46Center for Complex Networks and Systems Research, Indiana University, Bloomington, IN; 47Department of Computer Science, Masdar Institute, Khalifa University, Abu Dhabi, United Arab Emirates; 48Research Institute for Mathematical Sciences, Kyoto University, Kyoto, Japan; 49Department of Astrophysical Sciences, Princeton University, Princeton, NJ; 50Department of Neuroscience, Princeton University, Princeton, NJ; 51Department of Electrical Engineering, Princeton University, Princeton, NJ; 52Dataiku, New York, NY; 53Department of Civil and Environmental Engineering, Princeton University, Princeton, NJ; 54Department of Sociology, California State University, Dominguez Hills, Carson, CA; 55School of Media and Public Affairs, George Washington University, Washington, DC; 56Center for Data Insights, MDRC, Oakland, CA; 57Social Science Division, New York University Abu Dhabi, Abu Dhabi, United Arab Emirates; 58Department of Economics, Princeton University, Princeton, NJ; 59Center for Complex Network Research, Northeastern University Networks Science Institute, Boston, MA; 60Luddy School of Informatics, Computing, & Engineering, Indiana University, Bloomington, IN; 61School of Social Work, David B. Falk College of Sport and Human Dynamics, Syracuse University, NY; 62School of Public Health, Indiana University, Bloomington, IN; 63The Alan Turing Institute, London, United Kingdom; 64Department of Psychiatry, University of Cambridge, Cambridge, United Kingdom; 65School of Informatics, University of Edinburgh, Edinburgh, United Kingdom; 66Department of Marketplaces & Yield Data Science, Expedia Group, Seattle, WA; 67Department of the Applied Statistics, Social Science, and Humanities, New York University, New York, NY; 68Department of Engineering, University of Cambridge, Cambridge, United Kingdom; 69Department of Human Development, Teachers College, Columbia University, New York, NY; 70Department of Pediatrics, Vagelos College of Physicians and Surgeons, Columbia University, New York, NY; 71Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA; 72Department of Information Science, Cornell University, Ithaca, NY; 73Department of Computer and Information Science, University of Pennsylvania, Philadelphia, PA; 74Annenberg School of Communication, University of Pennsylvania, Philadelphia, PA; 75Operations, Information and Decisions Department, University of Pennsylvania, Philadelphia, PA