Michael Keane (economist)

Last updated

Michael Keane
Mike-keane 1 (cropped).jpg
Michael Keane at UTS in 2008
Born (1961-01-12) January 12, 1961 (age 63)
Suffern, New York
Academic career
Institution Johns Hopkins University
Field Econometrics
Alma mater
Doctoral
advisor		 Robert A. Moffitt
Influences Kenneth Wolpin
John Geweke
James Heckman
ContributionsChoice Modelling, Structural Modelling, Simulation Methods, Panel Data Econometrics
Awards
Information at IDEAS / RePEc

Michael Patrick Keane (born 1961) is an American-born economist; he is the Wm. Polk Carey Distinguished Professor at Johns Hopkins University. Keane was previously a professor at the University of New South Wales and the Nuffield Professor of Economics at the University of Oxford. [1] [2] He is considered one of the world's leading experts in the fields of Choice Modelling, structural modelling, simulation estimation, and panel data econometrics. [3] [4] [5] [6] [7]

Contents

He is also one of the world's leading economists by many measures of research productivity. [8] [9] Keane works in numerous areas including labor economics, econometrics, consumer demand models, marketing, industrial organization, health economics, and trade.

He is currently a chief investigator of the Australian Research Council Centre of Excellence in Population Ageing Research (Cepar). [10] From 2006–10 he was Co-Director of the Centre for the Study of Choice (CenSoC) at UTS. [11] Keane became a dual citizen of Australia in 2010.

Education and career

Keane was born in Suffern, New York, United States in 1961. He and graduated from Xavier High School in Manhattan in 1979. Keane received a B.S. degree from the Massachusetts Institute of Technology in 1983, where he was known as "Peachy" and played the bass guitar. He received a Ph.D. from Brown University in 1990.

In 1993, he became a tenured associate professor at the University of Minnesota, and was promoted to full professor in 1996. He subsequently held full professor positions at New York University (1998–2001) and Yale University (2000-2006).

In 2006, he moved to Australia to take up an Australian Federation Fellowship at the University of Technology Sydney. [12] In 2011, he became an Australian Laureate Fellow at the University of New South Wales. [13]

Keane was elected a Fellow of the Econometric Society (2005), [14] to the Council of the Econometric Society (2009), and a Fellow of the Academy of Social Sciences in Australia (2012). [15] He was the recipient of the John D.C. Little award for the Best Paper in Marketing (1996) and the Kenneth J. Arrow Award for Best Paper in Health Economics (2008). [16] In 2004–05, Keane was the Goldwater Chair of American Institutions at Arizona State University and, subsequently, has been a regular visiting professor there.

Contributions

Keane's work is notable for the fact that it spans a very wide range of substantive and methodological areas. He is best known for work on the following topics:

Discrete choice models

Keane's work on recursive importance sampling (the "GHK" algorithm), contained in his thesis (1990) and published in 1993–1994, made it feasible to estimate a much larger class of discrete choice models than was previously possible. In particular, his thesis developed a fast algorithm for the highly accurate calculation of areas of polyhedrons in very-high-dimensional spaces. While primarily a result in applied mathematics, this result is very useful in economics (and other social sciences) because the choice probabilities in discrete choice models generally have this form. [17] The GHK algorithm is now included in many popular econometrics software packages, including SAS, Stata, GAUSSX, Matlab and R-Cran-Bayesm, [18] and is a standard topic in graduate econometrics texts. [19]

Consumer demand and marketing

A 1996 paper with Tulin Erdem in Marketing Science presented what is now the main economic model of advertising and consumer learning. This paper received the John D.C. Little Award for the Best Paper in Marketing in 1996, and it has had a major impact on the fields of marketing and industrial organization. There is now a large literature on consumer learning based on the Erdem-Keane framework. [20] Erdem and Keane (among others) have argued that their framework can provide an economic explanation for the phenomenon known as brand equity, based on incomplete information and risk aversion. [21] [22] The November 2013 issue of Marketing Science contains an extensive review of the large literature based on the Erdem-Keane framework. [23]

Dynamic life-cycle models

In a series of joint papers with Kenneth Wolpin, published between 1994 and 2010, Keane developed a major line of research on dynamic life-cycle models of career (i.e., school and work) choices. [24] [25] This line of research is notable both for the methodological contributions on how to estimate these types of models, and for its substantive economic contributions. Methodologically, their method of approximating the solution to computationally intensive dynamic programming problems led to a great expansion in the class of such models that are feasible to implement empirically (i.e., their method made it possible to estimate models with many more choices and state variables than was possible previously). Substantively, their seminal 1997 paper on "The Career Decisions on Young Men" presented the so-called "90 percent result"—i.e., that most of what matters for lifetime earnings has already happened by age 16. This result helped to shift the focus of the human capital literature away from college education and towards early childhood education. This is now a very active area of research in economics, which has been pursued by both Keane and Wolpin and, quite notably, by the Nobel Prize–winning economist James Heckman, [26] among others.

Welfare and transfer programs

His 1998 paper with Robert Moffitt, entitled "Multiple welfare program participation and labor supply," has had great influence on subsequent models of transfer/welfare programs. This was the first paper to account for the very complex budget constraints created when people may participate in several government welfare programs simultaneously. The model predicted that welfare caseloads would drop substantially in response to earnings subsidies (like the Earned Income Tax Credit).

Human capital and labor supply

Michael Keane at the Becker-Friedman Institute, 2013 Keane BFI.jpg
Michael Keane at the Becker-Friedman Institute, 2013

In recent years, Keane has argued persuasively that, due to human capital effects, labor supply elasticities are much larger than the previous consensus of the economics profession would suggest. These views are presented in Imai and Keane (2004), Keane (2010) and Keane and Rogerson (2012). [27] [28] If correct, his views imply that welfare losses from income taxation are much higher than was previously thought. Recently, Keane gave a keynote lecture summarizing this work at the 2015 annual meeting of the Royal Economic Society. [29] His Cowles lecture at the 2011 summer meeting of the Econometric Society also dealt with this topic.

Modelling expectations

Keane's papers with David Runkle (1990, 1998) are considered fundamental contributions in the literature on how people form expectations. These papers showed that the widespread empirical failure of "rational expectations" was in fact due to a set of econometric and data problems (such as the failure to account for aggregate economic shocks and the effects of data revisions).

Panel data econometrics

The recursive importance sampling algorithm developed in Keane's 1994 Econometrica paper made it possible to estimate panel data discrete choice models with complex serial correlation patterns. This approach is now widely used to model discrete dynamic processes in marketing and labor economics. Keane's 1992 Journal of Business and Economic Statistics paper with David Runkle developed a new approach for estimating linear panel data models in cases where the available instruments are predetermined but not strictly exogenous. This is a very common case that includes all dynamic panel data models as a leading example. Chamberlain (1982) noted that the Keane-Runkle approach was not fully efficient because it fails to use all available instruments. Keane and Runkle (1992) responded that the use of additional instruments would be unwise as it would generate bias due to the "many instrument problem." Nevertheless, the development of more efficient panel data estimators based on more instruments became a major research program in the 90s. Examples of this line of research are well-known papers by Arellano-Bond (1991), Ahn-Schmidt (1995), Arellano-Bover (1995) and Blundell-Bond (1998). For a review of the literature see Baltagi (2005) chapter 8. [30] More recent work, such as Ziliak (1997), [31] supports Keane and Runkle (1992)'s original argument that use of additional instruments may cause severe bias. [32]

Econometric methodology

Keane is well known as a champion of the "structural econometrics" school, which emphasizes the important role of economic theory in empirical work. This contrasts with the "experimental school" which has become very popular in the last 20 years. The latter seeks to use "natural experiments" to substitute for economic theory. He has written a number of articles on the importance of theory and the limitations of experiments (see Keane 2010a, 2010b). [33]

Other areas

In addition, Keane has done significant work in many other areas, such as health economics, child development, international trade, political economy, experimental economics, and development economics.

Selected papers

Related Research Articles

Econometrics is an application of statistical methods to economic data in order to give empirical content to economic relationships. More precisely, it is "the quantitative analysis of actual economic phenomena based on the concurrent development of theory and observation, related by appropriate methods of inference." An introductory economics textbook describes econometrics as allowing economists "to sift through mountains of data to extract simple relationships." Jan Tinbergen is one of the two founding fathers of econometrics. The other, Ragnar Frisch, also coined the term in the sense in which it is used today.

Articles in economics journals are usually classified according to JEL classification codes, which derive from the Journal of Economic Literature. The JEL is published quarterly by the American Economic Association (AEA) and contains survey articles and information on recently published books and dissertations. The AEA maintains EconLit, a searchable data base of citations for articles, books, reviews, dissertations, and working papers classified by JEL codes for the years from 1969. A recent addition to EconLit is indexing of economics journal articles from 1886 to 1968 parallel to the print series Index of Economic Articles.

Sir David Forbes Hendry, FBA CStat is a British econometrician, currently a professor of economics and from 2001 to 2007 was head of the economics department at the University of Oxford. He is also a professorial fellow at Nuffield College, Oxford.

Structural estimation is a technique for estimating deep "structural" parameters of theoretical economic models. The term is inherited from the simultaneous equations model. Structural estimation is extensively using the equations from the economics theory, and in this sense is contrasted with "reduced form estimation" and other nonstructural estimations that study the statistical relationships between the observed variables while utilizing the economics theory very lightly. The idea of combining statistical and economic models dates to mid-20th century and work of the Cowles Commission.

<span class="mw-page-title-main">Structural break</span> Econometric term

In econometrics and statistics, a structural break is an unexpected change over time in the parameters of regression models, which can lead to huge forecasting errors and unreliability of the model in general. This issue was popularised by David Hendry, who argued that lack of stability of coefficients frequently caused forecast failure, and therefore we must routinely test for structural stability. Structural stability − i.e., the time-invariance of regression coefficients − is a central issue in all applications of linear regression models.

Kenneth E. Train is an Adjunct Professor of Economics at the University of California, Berkeley, United States. He is also Vice President of NERA Economic Consulting, Inc. in San Francisco, California. He received a Bachelors in Economics at Harvard and PhD from UC Berkeley. He specializes in econometrics and regulation, with applications in energy, environmental studies, telecommunications and transportation.

The methodology of econometrics is the study of the range of differing approaches to undertaking econometric analysis.

Following the development of Keynesian economics, applied economics began developing forecasting models based on economic data including national income and product accounting data. In contrast with typical textbook models, these large-scale macroeconometric models used large amounts of data and based forecasts on past correlations instead of theoretical relations. These models estimated the relations between different macroeconomic variables using regression analysis on time series data. These models grew to include hundreds or thousands of equations describing the evolution of hundreds or thousands of prices and quantities over time, making computers essential for their solution. While the choice of which variables to include in each equation was partly guided by economic theory, variable inclusion was mostly determined on purely empirical grounds. Large-scale macroeconometric model consists of systems of dynamic equations of the economy with the estimation of parameters using time-series data on a quarterly to yearly basis.

Manuel Arellano is a Spanish economist specialising in econometrics and empirical microeconomics. Together with Stephen Bond, he developed the Arellano–Bond estimator, a widely used GMM estimator for panel data. This estimator is based on the earlier article by Arellano's PhD supervisor, John Denis Sargan, and Alok Bhargava. RePEc lists the paper about the Arellano-Bond estimator as the most cited article in economics.

<span class="mw-page-title-main">LIMDEP</span>

LIMDEP is an econometric and statistical software package with a variety of estimation tools. In addition to the core econometric tools for analysis of cross sections and time series, LIMDEP supports methods for panel data analysis, frontier and efficiency estimation and discrete choice modeling. The package also provides a programming language to allow the user to specify, estimate and analyze models that are not contained in the built in menus of model forms.

<span class="mw-page-title-main">NLOGIT</span>

NLOGIT is an extension of the econometric and statistical software package LIMDEP. In addition to the estimation tools in LIMDEP, NLOGIT provides programs for estimation, model simulation and analysis of multinomial choice data, such as brand choice, transportation mode and for survey and market data in which consumers choose among a set of competing alternatives.

<span class="mw-page-title-main">Zvi Eckstein</span> Israeli economist

Zvi Eckstein is a full professor, dean, Arison School of Business and Tiomkin School of Economics at The Interdisciplinary Center Herzliya - IDC. Emeritus Professor at the Eitan Berglas School of Economics, Tel Aviv University. Head, the Aaron Economic Policy Institute, IDC, Herzliya. University of Pennsylvania, the Wharton School, Finance Department, Judith C. and William G. Bollinger Visiting Professor. Served as deputy governor, Bank of Israel (2006-2011). The Walras-Bowely Lecturer, the Econometric Society, North America Summer Meetings, Pittsburgh, US, June 19, 2008. Fellow of the Econometric Society.

Andrew Donald Roy was a British economist who is known for the Roy model of self-selection and income distribution and Roy's safety-first criterion.

<span class="mw-page-title-main">John Rust</span> American economist and econometrician (born 1955)

John Philip Rust is an American economist and econometrician. John Rust received his PhD from MIT in 1983 and taught at the University of Wisconsin, Yale University and University of Maryland before joining Georgetown University in 2012. John Rust was awarded the Frisch Medal in 1992 and became a fellow of the Econometric Society in 1993.

Peter Arcidiacono is an American economist and econometrician. He received his PhD from Wisconsin in 1999 and has taught at Duke University ever since. He became a fellow of the Econometric Society in 2018.

Dynamic discrete choice (DDC) models, also known as discrete choice models of dynamic programming, model an agent's choices over discrete options that have future implications. Rather than assuming observed choices are the result of static utility maximization, observed choices in DDC models are assumed to result from an agent's maximization of the present value of utility, generalizing the utility theory upon which discrete choice models are based.

Robert Allen Moffitt is an American economist; he is currently the Krieger-Eisenhower Professor of Economics at Johns Hopkins University. His areas of research include the economics of tax and transfer programs, especially welfare programs, the analysis of earnings instability in the labor market, the economics of the family, and applied microeconometrics.

Petra Elisabeth (Crockett) Todd is an American economist whose research interests include labor economics, development economics, microeconomics, and econometrics. She is the Edward J. and Louise W. Kahn Term Professor of Economics at the University of Pennsylvania, and is also affiliated with the University of Pennsylvania Population Studies Center, the Human Capital and Equal Opportunity Global Working Group (HCEO), the IZA Institute of Labor Economics and the National Bureau of Economic Research.

Stéphane Bonhomme is a French economist currently at the University of Chicago, where he is the Ann L. and Lawrence B. Buttenwieser Professor of Economics. Bonhomme specializes in microeconometrics. His research involves latent variable modeling, modeling of unobserved heterogeneity in panel data, and its applications in labor economics, in particular the analysis of earnings inequality and dynamics.

<span class="mw-page-title-main">Yingyao Hu</span> American economist (born 1972)

Yingyao Hu 胡颖尧 is a Chinese American economist, the Krieger-Eisenhower professor of economics, and currently Vice Dean for Social Sciences, Krieger School of Arts & Sciences, Johns Hopkins University.

References

  1. ↑ "Academic Experience" (PDF). ifs.org.uk. Retrieved 27 September 2018.
  2. ↑ "Michael Keane arrives". business.unsw.edu.au. 25 August 2017. Retrieved 27 September 2018.
  3. ↑ "Professor Michael Keane". assa.edu.au. Archived from the original on 10 September 2017. Retrieved 10 September 2017. According to the Academy of the Social Sciences in Australia, " He is considered one of the world's leading experts in the fields of Choice Modelling, structural modelling, simulation estimation, and panel data econometrics."
  4. ↑ "Nuffield Professorship of Economics". ox.ac.uk/. Retrieved 10 September 2017. According to the University of Oxford Nuffield Professorship announcement, "He is a world leader in choice modelling, the statistical technique that involves developing mathematical models to predict how individuals or companies make different types of decisions."
  5. ↑ "Michael Keane". Bfi.uchicago.edu. Retrieved 21 February 2015. According his profile at the Becker-Friedman Institute at the University of Chicago, "Michael Keane is a distinguished behavioral economist and econometrician and a world leader in choice modeling."
  6. ↑ "Prestigious joint appointment for Michael Keane". business.unsw.edu.au. Retrieved 10 September 2017. According to the UNSW Business School appointment announcement, "He is widely known for his seminal contributions in empirical microeconomics and econometrics. His methodological innovations are used extensively in a variety of applied fields including labour economics, health economics and marketing."
  7. ↑ "Michael P Keane". ifs.org.uk. Retrieved 10 September 2017. According to the Institute for Fiscal Studies profile, "Keane is best known for work on simulation methods (e.g., the "GHK algorithm") and for contributions to the theory and application of dynamic discrete choice models."
  8. ↑ "As of September 2017 Keane has over 16,000 citations on Google scholar" . Retrieved 10 September 2017.
  9. ↑ And, according to the IDEAS/RePEc October 2013 rankings of economists by several measures of research productivity, he ranks 110th among all economists in the world, 5th in the United Kingdom, 37th in the world over the past 10 years, and 1st among all economists in the 1990 PhD cohort. In terms of total journal pages, weighted by journal impact factors and number of co-authors, he is 23rd in the world and 5th in the world over the last 10 years.
  10. ↑ "Cepar Homepage". Cepar.edu.au. Retrieved 15 January 2014.
  11. ↑ "UTS: About – Study of Choice". Censoc.uts.edu.au. 15 October 2012. Archived from the original on 26 January 2014. Retrieved 15 January 2014.
  12. ↑ "UTS tops economics rankings in Australia". Theaustralian.com.au. 29 August 2013. Retrieved 15 January 2014.
  13. ↑ "Australian Laureate Fellows at UNSW". Research.unsw.edu.au. 19 June 2013. Archived from the original on 16 January 2014. Retrieved 15 January 2014.
  14. ↑ "Welcome to the website of The Econometric Society An International Society for the Advancement of Economic Theory in its Relation to Statistics and Mathematics". Econometricsociety.org. 3 January 2003. Archived from the original on 10 December 2008. Retrieved 15 January 2014.
  15. ↑ "Academy Fellow – Professor Michael Keane FASSA". Academy of the Social Sciences in Australia. Retrieved 25 November 2023.
  16. ↑ "Arrow Award Winners | iHEA | International Health Economics Association". Archive.healtheconomics.org. 10 July 2007. Archived from the original on 2 January 2014. Retrieved 15 January 2014.
  17. ↑ See Skrondal, Anders and Sophia Rabe-Hesketh (2004), "Generalized Latent Variable Modeling," London: Chapman & Hall/CRC, pp. 173–4, where they state "In econometrics the GHK simulator is very popular for models with multi-normal latent responses, for instance probit panel (longitudinal) models (e.g., Keane, 1994, Geweke, et al., 1994). This is probably because the simulator has been shown to outperform other simulators although it is relatively easy to implement."
  18. ↑ "Cappellari L. and Jenkins, S.P. (2003), "Multivariate probit regression using simulated maximum likelihood," The Stata Journal, Vol. 3:3, pp. 278–94". Stata-journal.com. Retrieved 15 January 2014.
  19. ↑ Greene, William H. (2003). "Basic textbook discussion of the algorithm" (Fifth ed.). Econometric Analysis. pp. 931–33. Retrieved 21 February 2015.
  20. ↑ Weitz, Barton; Wensley, Robin (22 June 2009). Branding and Brand Equity : SAGE Knowledge. Knowledge.sagepub.com. doi:10.4135/9781848608283. ISBN   9781412921206 . Retrieved 21 February 2015.
  21. ↑ "Google Scholar Citations". 31 December 1998. Retrieved 21 February 2015.
  22. ↑ Tülin Erdem; Joffre Swait (June 2004). "Brand Credibility, Brand Consideration, and Choice". Journal of Consumer Research. 31 (1). The University of Chicago Press: 191–198. doi: 10.1086/383434 . JSTOR   383434.
  23. ↑ Ching, A. T.; Erdem, T. L.; Keane, M. P. (2013). "Invited Paper—Learning Models: An Assessment of Progress, Challenges, and New Developments". Marketing Science. 32 (6): 913–938. doi:10.1287/mksc.2013.0805.
  24. ↑ Heckman, J.; Lochner, L.; Todd, P. (2006). "Handbook of the Economics of Education". p. 441. Retrieved 21 February 2015. Keane and Wolpin (1997) and Eckstein and Wolpin (1999) pioneered the estimation of dynamic discrete choice models for analyzing schooling choices.
  25. ↑ Belzil, Christian (2007). "The return to schooling in structural dynamic models: A survey" (PDF). European Economic Review. 51 (5). Scienedirect.com: 1059–1105. doi:10.1016/j.euroecorev.2007.01.008. S2CID   10552331. In his survey of the human capital literature, Belzil (2007) states that "The first stage consists of seminal work on schooling and earnings by Becker (1964, 1967) and Mincer (1958). The second stage, which culminates in Willis and Rosen (1979), is largely influenced by the econometric self-selection literature (Heckman, 1976). Finally, the recent literature, stimulated by Keane and Wolpin (1997), uses stochastic dynamic programming techniques, and forms a third stage ..."
  26. ↑ "The Economics and Econometrics of Human Development by James Heckman". YouTube. 7 November 2013. Retrieved 21 February 2015.
  27. ↑ Prescott, Edward C. (2006). "Nobel Lecture: The Transformation of Macroeconomic Policy and Research". Journal of Political Economy. 114 (2): 203–235. doi:10.1086/503205. JSTOR   10.1086/503205.
  28. ↑ Becker-Posner Blog "Is Raising Marginal Tax Rates on Higher Income Individuals a Good Idea?" July 15, 2012, In discussing Keane and Rogerson (2012), Becker states: "... on the job investments in human capital ... bias downwards the micro estimates of labor supply elasticities that are based on variations in hours worked over the lifecycle. This bias is especially large at younger ages where most of these investments occur since the true earnings at these ages is much larger than the observed wages at these ages because younger workers are raising their future wages through investments in their human capital. This bias helps explain why computed elasticities of labor supply are usually greater for older workers ... These and other corrections to simple interpretations of the micro evidence on labor responses to changes in tax rates clearly suggest that aggregate labor responses to tax rates may be quite large."
  29. ↑ "First Sight Media: Presentation".
  30. ↑ Baltagi, Badi (2005). "The Econometric Analysis of Panel Data" (3rd ed.). Chichester: John Wiley & Sons. Retrieved 21 February 2015.
  31. ↑ Ziliak, James P (2 February 1997). "Efficient Estimation with Panel Data When Instruments Are Predetermined: An Empirical Comparison of Moment-Condition Estimators". Journal of Business & Economic Statistics. 15 (4). Ideas.repec.org: 419–431. doi:10.1080/07350015.1997.10524720 . Retrieved 15 January 2014.
  32. ↑ See the well-known reference on panel data by Baltagi (2005), pp. 151–52, where he states: "Ziliak (1997) performs an extensive set of Monte Carlo experiments for a dynamic panel data model ... Ziliak finds that the downward bias of GMM is quite severe as the number of moment conditions expands, outweighing the gains in efficiency. Interestingly, Ziliak finds that the forward filter 2SLS estimator proposed by Keane and Runkle (1992) performs best in terms of the bias/efficiency tradeoff and is recommended."
  33. ↑ See also the discussion by Rosenzweig, Mark; Wolpin, Kenneth (2000). "Natural 'Natural Experiments' in Economics". Journal of Economic Literature . 38 (4): 827–74. doi:10.1257/jel.38.4.827. JSTOR   2698663.
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.