Michael Wolf (statistician) explained

Michael Wolf
Birth Date:	1 June 1967
Birth Place:	Germany
Institutions:	University of Zurich
Movement:	Econometrics, statistics
Alma Mater:	Stanford University
Contributions:	Shrinkage Estimation of Covariance Matrices; Subsampling; and Multiple Testing.
Repec Prefix:	e
Repec Id:	pwo206

Michael Wolf (born June 1, 1967) holds the Chair of Econometrics and Applied Statistics in the Department of Economics at the University of Zurich, Switzerland. He was previously Professor at UCLA, Charles III University of Madrid, and Pompeu Fabra University.

Biography

Wolf was born in Germany, where he obtained a bachelor's degree in mathematics from the University of Augsburg. From 1991 he studied statistics at Stanford University (M.Sc. 1995, Ph.D. 1996).

Wolf is known for his work on shrinkage estimation of large-dimensional covariance matrices. While originally motivated by Markowitz portfolio selection, the linear shrinkage estimator he developed in collaboration with Olivier Ledoit has been widely adopted by other researchers in a variety of scientific fields such ascancer research,^[1] chemistry,^[2] civil engineering,^[3] climatology,^[4] electrical engineering,^[5] genetics,^[6] geology,^[7] neuroscience,^[8] psychology,^[9] speech recognition,^[10] etc. The common feature between these applications is that the dimension of the covariance matrix is not negligible with respect to the size of the sample. In this case the usual estimator, the sample covariance matrix, is inaccurate and ill-conditioned. By contrast, the Ledoit-Wolf estimator is more accurate and guaranteed to be well-conditioned, even in the difficult case where matrix dimension exceeds sample size.

Michael Wolf also co-wrote the book on Subsampling, a resampling method inspired by the jackknife that constitutes an alternative to the bootstrap. In the field of multiple testing, he introduced new procedures to control the family-wise error rate that are more powerful than previous methods, by taking into account the dependence between test statistics. He also worked on procedures to control generalized error rates, such as the generalized family-wise error rate, the false discovery proportion and the false discovery rate.

Michael Wolf served on the editorial board of the Annals of Statistics and Statistics and Probability Letters. In 2004, he won the Distinguished Researcher award from the Generalitat of Catalonia. He was invited to give the prestigious Gumbel Lecture at the Annual Meeting of the German Statistical Society in Cologne in 2008.

Selected publications

Books

• Book: Politis . Dimitris N.. Romano . Joseph P.. Wolf . Michael. 1999 . Subsampling . Springer Series on Statistics. 978-0-387-98854-2.

Articles on Shrinkage Estimation of Covariance Matrices

• Ledoit . Olivier . Wolf . Michael . December 2003 . Improved estimation of the covariance matrix of stock returns with an application to portfolio selection . Journal of Empirical Finance . 10 . 5 . 603–621 . 10.1016/S0927-5398(03)00007-0 . dead . https://web.archive.org/web/20141205062053/http://www.econ.uzh.ch/faculty/wolf/publications/jef.pdf . 2014-12-05 . 10016/10089 . 14422126 . free .
• Ledoit . Olivier . Wolf . Michael . February 2004 . A well-conditioned estimator for large-dimensional covariance matrices . . 88 . 2 . 365–411 . 10.1016/S0047-259X(03)00096-4 . 10016/10087 . dead . https://web.archive.org/web/20141205062201/http://www.econ.uzh.ch/faculty/wolf/publications/wellCond.pdf . 2014-12-05 . free .
• Ledoit . Olivier . Wolf . Michael . Summer 2004 . Honey, I shrunk the sample covariance matrix . . 30 . 4 . 110–119 . 10.3905/jpm.2004.110 . 10230/560 . 219237399 . 2015-01-21 . https://web.archive.org/web/20150121084907/http://www.econ.uzh.ch/faculty/wolf/publications/honey.pdf . 2015-01-21 . dead . free .

Articles on Subsampling

• Romano . Joseph P. . Wolf . Michael . September 2001 . Subsampling intervals in autoregressive models with linear time trend . . 69 . 5 . 1283–1314 . 10.1111/1468-0262.00242 . 10016/6400 . 2015-01-21 . https://web.archive.org/web/20150923233232/http://www.econ.uzh.ch/faculty/wolf/publications/etcaSub.pdf . 2015-09-23 . dead . free .
• Gonzalo . Jesús . Wolf . Michael . August 2005 . Subsampling inference in threshold autoregressive models . . 127 . 2 . 201–224 . 10.1016/j.jeconom.2004.08.004 . 10016/3218 . 2015-01-21 . https://web.archive.org/web/20150121084213/http://www.econ.uzh.ch/faculty/wolf/publications/joe.pdf . 2015-01-21 . dead . free .

Articles on Multiple Testing

• Romano . Joseph P. . Wolf . Michael . March 2005 . Exact and approximate stepdown methods for multiple hypothesis testing . . 100 . 469 . 94–108 . 10.1198/016214504000000539 . 10230/576 . 219594470 . 2015-01-21 . https://web.archive.org/web/20150121084940/http://www.econ.uzh.ch/faculty/wolf/publications/jasa.pdf . 2015-01-21 . dead . free .
• Romano . Joseph P. . Wolf . Michael . July 2005 . Stepwise multiple testing as formalized data snooping . . 73 . 4 . 1237–1282 . 10.1111/j.1468-0262.2005.00615.x . 10.1.1.198.2473 . 10230/1216 . 2015-01-21 . https://web.archive.org/web/20150121083551/http://www.econ.uzh.ch/faculty/wolf/publications/etca.pdf . 2015-01-21 . dead .
• Romano . Joseph P. . Wolf . Michael . August 2007 . Control of generalized error rates in multiple testing . . 35 . 4 . 1378–1408 . 10.1214/009053606000001622 . 0710.2258 . 14195701 . 2015-01-21 . https://web.archive.org/web/20150121084255/http://www.econ.uzh.ch/faculty/wolf/publications/annals_2007.pdf . 2015-01-21 . dead .

External links

• Official University of Zurich webpage
• Google Scholar Citation page

Notes and References

1. Dohun. Pyeon. Michael A.. Newton. Paul F.. Lambert. Johan A. . den Boon. Srikumar. Sengupta. Carmen J.. Marsit. Craig D.. Woodworth. Joseph P.. Connor. Thomas H.. Haugen. Elaine M.. Smith. Karl T.. Kelsey. Lubomir P.. Turek. Paul. Ahlquist. May 2007. Fundamental differences in cell cycle deregulation in human papillomavirus–positive and human papillomavirus–negative head/neck and cervical cancers . . 67. 10. 4605–4619 . 10.1158/0008-5472.CAN-06-3619 . 17510386. 2858285.
2. Syuan-Ming. Guo. Jun. He. Nilah. Monnier. Guangyu. Sun. Thorsten. Wohland. Mark. Bathe. March 2012. Bayesian approach to the analysis of fluorescence correlation spectroscopy data II: Application to simulated and in vitro data . . 84. 9. 3880–3888 . 10.1021/ac2034375. 22455375. 1721.1/92290. 30293080. free.
3. Vibration–based damage diagnosis in a laboratory cable–stayed bridge model via an RCP–ARX model based method. Michaelides. Pavlos G.. Apostolellis. Panagiotis G.. Fassois. Spilios D.. July 2011. Institute of Physics. . 305. Proceedings of the 9th International Conference on Damage Assessment of Structures (DAMAS 2011). http://iopscience.iop.org/1742-6596/305/1/011001. 012104 . Oxford, United Kingdom . 10.1088/1742-6596/305/1/012104. free.
4. Ribes. Aurélien. Azaïs. Jean-Marc. Planton. Serge . October 2009. Adaptation of the optimal fingerprint method for climate change detection using a well-conditioned covariance matrix estimate . . 33. 5. 707–722 . 10.1007/s00382-009-0561-4. 2009ClDy...33..707R. 53388815.
5. Adaptive-beamforming-based multiple targets signal separation . Wei . Zhe . Huang . Jianguo . Hui . Yuejiao . September 2011 . Institute of Electrical and Electronics Engineers. Proceedings of the 2011 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC). https://ieeexplore.ieee.org/xpl/conhome/6046214/proceeding. 1–4 . Xi'an, China . 10.1109/ICSPCC.2011.6061572 .
6. Lin. Ja-an. Hongtu. Zhu. Rebecca. Knickmeyer. Martin. Styner. John. Gilmore. Joseph G.. Ibrahim. September 2012. Projection regression models for multivariate imaging phenotype . Genetic Epidemiology . 36. 6. 631–641 . 10.1002/gepi.21658 . 22807230 . 3418398.
7. Elsheikh . Ahmed H.. Wheeler. Mary F.. Hoteit. Ibrahim. June 2013. An iterative stochastic ensemble method for parameter estimation of subsurface flow models . . 242 . 696–714 . 10.1016/j.jcp.2013.01.047. 2013JCoPh.242..696E.
8. Varoquaux. Gaël. Alexandre. Gramfort. Jean-Baptiste. Poline. Bertrand. Thirion. September 2012. Markov models for fMRI correlation structure: Is brain functional connectivity small world, or decomposable into networks? . 1202.0836. Journal of Physiology - Paris . 106. 5. 212–221 . 10.1016/j.jphysparis.2012.01.001. 22326672. 15305005.
9. Markon. Kristian E.. February 2010. Modeling psychopathology structure: a symptom-level analysis of Axis I and II disorders. . 40. 2. 273–288 . 10.1017/S0033291709990183. 19515267. 34441286 .
10. Diagonal priors for full covariance speech recognition. Bell. Peter. King. Simon. November 2009 . Institute of Electrical and Electronics Engineers. Proceedings of the 2009 IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU). https://ieeexplore.ieee.org/xpl/conhome/5357590/proceeding. 113–117 . Merano, Italy . 10.1109/ASRU.2009.5373344.