Measuring the predictability of life outcomes with a scientific mass collaboration.

Autor:	Salganik MJ; Department of Sociology, Princeton University, Princeton, NJ 08544; mjs3@princeton.edu mclanaha@princeton.edu., Lundberg I; Department of Sociology, Princeton University, Princeton, NJ 08544., Kindel AT; Department of Sociology, Princeton University, Princeton, NJ 08544., Ahearn CE; Department of Sociology, University of California, Los Angeles, CA 90095., Al-Ghoneim K; Hawaz, Riyadh 12363, Saudi Arabia., Almaatouq A; Sloan School of Management, Massachusetts Institute of Technology, Cambridge, MA 02142.; Media Lab, Massachusetts Institute of Technology, Cambridge, MA 02139., Altschul DM; Mental Health Data Science Scotland, Department of Psychology, The University of Edinburgh, Edinburgh EH8 9JZ, United Kingdom., Brand JE; Department of Sociology, University of California, Los Angeles, CA 90095.; Department of Statistics, University of California, Los Angeles, CA 90095., Carnegie NB; Department of Mathematical Sciences, Montana State University, Bozeman, MT 59717., Compton RJ; Human Computer Interaction Lab, University of California, Santa Cruz, CA 95064., Datta D; Discovery Analytics Center, Virginia Polytechnic Institute and State University, Arlington, VA 22203., Davidson T; Department of Sociology, Cornell University, Ithaca, NY 14853., Filippova A; GitHub, San Francisco, CA 94107., Gilroy C; Department of Sociology, University of Washington, Seattle, WA 98105., Goode BJ; Social and Decision Analytics Laboratory, Fralin Life Sciences Institute, Virginia Polytechnic Institute and State University, Arlington, VA 22203., Jahani E; Institute for Data, Systems and Society, Massachusetts Institute of Technology, Cambridge, MA 02139., Kashyap R; Department of Sociology, University of Oxford, Oxford OX1 1JD, United Kingdom.; Nuffield College, University of Oxford, Oxford OX1 1NF, United Kingdom.; School of Anthropology and Museum Ethnography, University of Oxford, Oxford OX2 6PE, United Kingdom., Kirchner A; Program for Research in Survey Methodology, Survey Research Division, RTI International, Research Triangle Park, NC 27709., McKay S; School of Social and Political Sciences, University of Lincoln, Brayford Pool, Lincoln LN6 7TS, United Kingdom., Morgan AC; Department of Computer Science, University of Colorado, Boulder, CO 80309., Pentland A; Media Lab, Massachusetts Institute of Technology, Cambridge, MA 02139., Polimis K; Center for the Study of Demography and Ecology, University of Washington, Seattle, WA 98105., Raes L; Department of Economics, Tilburg School of Economics and Management, Tilburg University, 5037 AB Tilburg, The Netherlands., Rigobon DE; Department of Operations Research and Financial Engineering, Princeton University, Princeton, NJ 08544., Roberts CV; Department of Computer Science, Princeton University, Princeton, NJ 08544., Stanescu DM; Department of Politics, Princeton University,Princeton, NJ, 08544., Suhara Y; Media Lab, Massachusetts Institute of Technology, Cambridge, MA 02139., Usmani A; Department of Sociology, Harvard University, Cambridge, MA 02138., Wang EH; Department of Politics, Princeton University,Princeton, NJ, 08544., Adem M; Department of Sociology, Indiana University, Bloomington, IN 47405., Alhajri A; Department of Nuclear Science and Engineering, Massachusetts Institute of Technology, Cambridge, MA 02139., AlShebli B; Computational Social Science Lab, Social Science Division, New York University Abu Dhabi, 129188 Abu Dhabi, United Arab Emirates., Amin R; Bendheim Center for Finance, Princeton University, Princeton, NJ 08544., Amos RB; Department of Computer Science, Princeton University, Princeton, NJ 08544., Argyle LP; Department of Political Science, Brigham Young University, Provo, UT 84602., Baer-Bositis L; Department of Sociology, Stanford University, Stanford, CA 94305., Büchi M; Department of Communication and Media Research, University of Zurich, Zurich, Switzerland, ZH-8050., Chung BR; Center for Statistics & Machine Learning, Princeton University, Princeton, NJ 08544., Eggert W; Department of Mechanical and Aerospace Engineering, Princeton University, Princeton, NJ 08544., Faletto G; Statistics Group, Department of Data Sciences and Operations, Marshall School of Business, University of Southern California, Los Angeles, CA 90089., Fan Z; Department of Statistics, Columbia University, New York, NY 10027., Freese J; Department of Sociology, Stanford University, Stanford, CA 94305., Gadgil T; Center for Data Science, New York University, New York, NY 10011., Gagné J; Department of Sociology, Stanford University, Stanford, CA 94305., Gao Y; Department of Industrial Engineering and Operations Research, Columbia University, New York, NY 10027., Halpern-Manners A; Department of Sociology, Indiana University, Bloomington, IN 47405., Hashim SP; Department of Computer Science, Princeton University, Princeton, NJ 08544., Hausen S; Department of Sociology, Stanford University, Stanford, CA 94305., He G; Department of Molecular Biology, Princeton University, Princeton, NJ 08544., Higuera K; Department of Sociology, Stanford University, Stanford, CA 94305., Hogan B; Oxford Internet Institute, University of Oxford, Oxford OX1 3JS, United Kingdom., Horwitz IM; Graduate School of Education, Stanford University, Stanford, CA, 94305., Hummel LM; Department of Sociology, Stanford University, Stanford, CA 94305., Jain N; Department of Operations Research and Financial Engineering, Princeton University, Princeton, NJ 08544., Jin K; Department of Computer Science, Ohio State University, Columbus, OH 43210., Jurgens D; School of Information, University of Michigan, Ann Arbor, MI 48104., Kaminski P; Department of Sociology, Indiana University, Bloomington, IN 47405.; Center for Complex Networks and Systems Research, Indiana University, Bloomington, IN 47405., Karapetyan A; Department of Computer Science, Masdar Institute, Khalifa University, 127788 Abu Dhabi, United Arab Emirates.; Research Institute for Mathematical Sciences, Kyoto University, Kyoto 606-8502, Japan., Kim EH; Department of Sociology, Stanford University, Stanford, CA 94305., Leizman B; Department of Computer Science, Princeton University, Princeton, NJ 08544., Liu N; Department of Politics, Princeton University,Princeton, NJ, 08544., Möser M; Department of Computer Science, Princeton University, Princeton, NJ 08544., Mack AE; Department of Politics, Princeton University,Princeton, NJ, 08544., Mahajan M; Department of Computer Science, Princeton University, Princeton, NJ 08544., Mandell N; Department of Astrophysical Sciences, Princeton University, Princeton, NJ 08544., Marahrens H; Department of Sociology, Indiana University, Bloomington, IN 47405., Mercado-Garcia D; Graduate School of Education, Stanford University, Stanford, CA, 94305., Mocz V; Department of Neuroscience, Princeton University, Princeton, NJ 08544., Mueller-Gastell K; Department of Sociology, Stanford University, Stanford, CA 94305., Musse A; Department of Electrical Engineering, Princeton University, Princeton, NJ, 08544., Niu Q; Bendheim Center for Finance, Princeton University, Princeton, NJ 08544., Nowak W; Dataiku, New York, NY 10010., Omidvar H; Department of Civil and Environmental Engineering, Princeton University, Princeton, NJ 08544., Or A; Department of Computer Science, Princeton University, Princeton, NJ 08544., Ouyang K; Department of Computer Science, Princeton University, Princeton, NJ 08544., Pinto KM; Department of Sociology, California State University, Dominguez Hills, Carson, CA 90747., Porter E; School of Media and Public Affairs, George Washington University, Washington, DC 20052., Porter KE; Center for Data Insights, MDRC, Oakland, CA 94612., Qian C; Department of Computer Science, Princeton University, Princeton, NJ 08544., Rauf T; Department of Sociology, Stanford University, Stanford, CA 94305., Sargsyan A; Social Science Division, New York University Abu Dhabi, 129188 Abu Dhabi, United Arab Emirates., Schaffner T; Department of Computer Science, Princeton University, Princeton, NJ 08544., Schnabel L; Department of Sociology, Stanford University, Stanford, CA 94305., Schonfeld B; Department of Politics, Princeton University,Princeton, NJ, 08544., Sender B; Department of Economics, Princeton University, Princeton, NJ 08544., Tang JD; Department of Computer Science, Princeton University, Princeton, NJ 08544., Tsurkov E; Department of Sociology, Stanford University, Stanford, CA 94305., van Loon A; Department of Sociology, Stanford University, Stanford, CA 94305., Varol O; Center for Complex Network Research, Northeastern University Networks Science Institute, Boston, MA 02115.; Luddy School of Informatics, Computing, & Engineering, Indiana University, Bloomington, IN 47408., Wang X; School of Social Work, David B. Falk College of Sport and Human Dynamics, Syracuse University, NY 13244., Wang Z; Luddy School of Informatics, Computing, & Engineering, Indiana University, Bloomington, IN 47408.; School of Public Health, Indiana University, Bloomington, IN 47408., Wang J; Department of Computer Science, Princeton University, Princeton, NJ 08544., Wang F; Department of Economics, Princeton University, Princeton, NJ 08544., Weissman S; Department of Computer Science, Princeton University, Princeton, NJ 08544., Whitaker K; The Alan Turing Institute, London NW1 2DB, United Kingdom.; Department of Psychiatry, University of Cambridge, Cambridge CB2 0SZ, United Kingdom., Wolters MK; School of Informatics, University of Edinburgh, Edinburgh EH8 9AB, United Kingdom., Woon WL; Department of Marketplaces & Yield Data Science, Expedia Group, Seattle, WA 98119., Wu J; Department of the Applied Statistics, Social Science, and Humanities, New York University, New York, NY 10003., Wu C; Department of Computer Science, Princeton University, Princeton, NJ 08544., Yang K; Department of Civil and Environmental Engineering, Princeton University, Princeton, NJ 08544., Yin J; Department of Statistics, Columbia University, New York, NY 10027., Zhao B; Department of Engineering, University of Cambridge, Cambridge CB2 1PZ, United Kingdom., Zhu C; Department of Statistics, Columbia University, New York, NY 10027., Brooks-Gunn J; Department of Human Development, Teachers College, Columbia University, New York, NY 10027.; Department of Pediatrics, Vagelos College of Physicians and Surgeons, Columbia University, New York, NY 10032., Engelhardt BE; Department of Computer Science, Princeton University, Princeton, NJ 08544.; Center for Statistics & Machine Learning, Princeton University, Princeton, NJ 08544., Hardt M; Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA 94720., Knox D; Department of Politics, Princeton University,Princeton, NJ, 08544., Levy K; Department of Information Science, Cornell University, Ithaca, NY 14853., Narayanan A; Department of Computer Science, Princeton University, Princeton, NJ 08544., Stewart BM; Department of Sociology, Princeton University, Princeton, NJ 08544., Watts DJ; Department of Computer and Information Science, University of Pennsylvania, Philadelphia, PA 19104.; Annenberg School of Communication, University of Pennsylvania, Philadelphia, PA 19104.; Operations, Information and Decisions Department, University of Pennsylvania, Philadelphia, PA 19104., McLanahan S; Department of Sociology, Princeton University, Princeton, NJ 08544; mjs3@princeton.edu mclanaha@princeton.edu.
Jazyk:	angličtina
Zdroj:	Proceedings of the National Academy of Sciences of the United States of America [Proc Natl Acad Sci U S A] 2020 Apr 14; Vol. 117 (15), pp. 8398-8403. Date of Electronic Publication: 2020 Mar 30.
DOI:	10.1073/pnas.1915006117
Abstrakt:	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. Competing Interests: Competing interest statement: B.E.E. is on the scientific advisory boards of Celsius Therapeutics and Freenome, is currently employed by Genomics plc and Freenome, and is on a year leave-of-absence from Princeton University. (Copyright © 2020 the Author(s). Published by PNAS.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu