【量化历史网上讲座系列】(Quantitative History Webinar Series)由香港大学陈志武和马驰骋教授联合发起，旨在介绍前沿量化历史研究成果、促进同仁交流，推广量化方法在历史研究中的应用。本系列讲座由国际量化历史学会、香港大学经管学院和香港人文社会研究所全力支持和承办。从2023年开始，本系列讲座得到中国香港特别行政区研究资助局卓越学科领域计划的重要资助 (项目编号[AoE/B-704/22-R])。
第95场讲座信息
Predictive Modelling the Past: A New Machine Learning Method Applied to Seven Centuries of Wages
主讲人：Meredith Paker, Assistant Professor, Department of Economics, Grinnell College
讨论人：Yuqi Chen, PhD candidate, Department of History, Peking University (will join the Centre of Quantitative History as a Postdoctoral Fellow in December 2024)
时 间：2024年11月07日 10:00 - 11:30 （北京时间，星期四）
讲座语言：英文
注册链接及二维码：
https://hku.zoom.us/webinar/register/8717014797742/WN_pIDVkaRsTY-SVXJSE0NY4w#/registration
讲座介绍
Economists are increasingly interested in the ‘very long run,’ yet research on the distant past has been hampered by the scarcity of economic data available for many centuries ago. Meredith Paker of Grinnell College and her co-authors introduce a new framework to peer into the past despite the scarcity of data in earlier periods. They use state-of-the-art machine learning predictive modeling methods and best-practice forecasting techniques to develop robust predictions of historical economic time series, treating the past as the prediction window.
To demonstrate the usefulness of this new method, they apply this framework to the seven centuries of English wage data at the heart of debates on long-run living standards. Their new approach generates predictions with improved accuracy and generalizability compared to existing regression-based interpolations. This new long-run wage series deviates from established estimates with the largest variation at key points of economic and social change. In this Quantitative History Webinar, Meredith Paker will discuss the implications for our understanding of long-run economic development.
Meredith Paker’s co-authors: Judy Stephenson (University College London) and Patrick Wallis (The London School of Economics and Political Science)
“量化历史研究”公众号由陈志武（香港大学郑裕彤基金讲席教授、原耶鲁大学教授）及其团队——林展（中国人民大学）、熊金武（中国政法大学）、何石军（武汉大学）、蒋勤（上海交通大学）、彭雪梅（中山大学）等人负责。向学界和业界朋友，定期推送量化历史研究经典、前沿文献。同时作为“量化历史讲习班”信息交流平台。喜欢我们的朋友请搜寻公众号：QuantitativeHistory，或扫描下面二维码关注。
我们也诚邀八方学人发送电邮建言献策。邮箱: lianghualishi@163.com。
点击“阅读原文”查看网站更多相关信息
