題目:Methodology and Critical Thinking in Modeling-Data Envelopment Analysis (DEA)
主講人:黃志民 教授 (美國Adelphi大學(xué)商學(xué)院)
時間:2017年6月14日(周三)下午14:30-16:30
地點:主樓六層
主講人簡介:
黃志民,美國Adelphi大學(xué)商學(xué)院教授,The University of Texas at Austin運(yùn)營管理博士 (1991),Journal of Modeling in Management 主編,International Journal of Information Technology and Decision Making,International Journal of Sustainable Society,International Journal of Society Systems Science等雜志的編委,曾擔(dān)任OMEGA: International Journal of Management Science副主編,主編了包括 Annals of Operations Research等多個雜志的特刊,同時為30多個國際性雜志及許多基金和出版社審閱論文和書稿。黃志民在管理、經(jīng)濟(jì)、運(yùn)籌等一流學(xué)術(shù)刋 物上共發(fā)表文章80多篇,其中,有2篇發(fā)表在決策科學(xué)學(xué)科排名第1的雜志Decision Sciences上,有11篇發(fā)表在運(yùn)籌學(xué)學(xué)科排名前3、DEA領(lǐng)域排名第1的雜志European Journal of Operational Research上,有1篇收集在由世界著名管理經(jīng)濟(jì)學(xué)家Cooper等編輯的“數(shù)據(jù)包絡(luò)分析手冊”(Handbook of DEA)一書中。根據(jù)SCI和SSCI的統(tǒng)計數(shù)據(jù),到2017年5月,黃志民共有70篇論文被檢索,并被5,000多篇論文引用。被引用最多的兩篇論文 是:“Polyhedral Cone-Ratio DEA Models with an Illustrative Application to Large Commercial Banks,”(發(fā)表在Journal of Econometrics)和“Cone Ratio Data Envelopment Analysis and Multi- objective Programming,” (發(fā)表在International Journal of Systems Science),被引用次數(shù)分別達(dá)到780多次和560多次。 這些文章中涉及到的一個重要領(lǐng)域是數(shù)據(jù)包絡(luò)分析,該理論體系是由運(yùn)籌學(xué)泰斗、管理科學(xué)創(chuàng)始人Charnes和Cooper在1978年建立 (Charnes是黃志民的博士學(xué)位導(dǎo)師, 曾入圍1974年諾貝爾經(jīng)濟(jì)學(xué)獎最終3人角逐名單)。 黃志民和Charnes、Cooper進(jìn)一步發(fā)展了數(shù)據(jù)包絡(luò)分析有關(guān)理論和模型,他們發(fā)表的文章中有5篇創(chuàng)立了經(jīng)典理論,有2篇建立了經(jīng)典模型,而以他們 名字命名的“錐比率”Cone Ratio DEA模型和“滿意度”Satisficing模型被學(xué)術(shù)界認(rèn)為是最有影響的DEA模型之一。在供應(yīng)鏈研究方面,黃志民教授是合作廣告 (cooperative advertising)這一領(lǐng)域的主要開創(chuàng)者。目前,在合作廣告這一領(lǐng)域引用次數(shù)最多的3 篇論文(論文引用次數(shù)分別達(dá)到377, 283, 247次),黃志民教授都是其主要作者。
內(nèi)容介紹:
This presentation deals with modeling development of evaluating activities of organizations such as business firms, government agencies, hospitals, educational institutions, etc. Problems and limitations are incurred in traditional attempts to evaluate efficiency when multiple outputs and multiple inputs need to be taken into account. Data Envelopment Analysis (DEA) can be used to deal with some of these problems. The relatively new approach embodied in DEA does not require the user to prescribe weights to be attached to each input and output, as in the usual index number approaches, and it also does not require prescribing the functional forms that are needed in statistical regress approaches to these topics. We are going to provide a systematic presentation of major developments of few important DEA models that have appeared in the literature.
(承辦:能源與環(huán)境政策研究中心,科研與學(xué)術(shù)交流中心)