Professor of Operations and Technology Management
Boston University Questrom School of Business
Erol A. Peköz
595 Commonwealth Avenue, Room 607
Boston, MA 02215
Phone: (617) 353-2676
Email: pekoz bu edu
Erol Peköz has a BS degree from Cornell University, and MS and Ph.D degrees in Operations Research from University of California, Berkeley. The research of Professor Peköz is focused in three areas: probability approximations and network science, healthcare quality and provider profiling, and queueing models and reliability for operations. His work appears in academic journals such as Annals of Probability, Annals of Applied Probability, Statistics in Medicine, Bernoulli, Journal of Applied Probability and Medical Care. He has conducted research funded by the Department of Health and Human Services, Agency for Healthcare Research and Quality, the Robert Wood Johnson Foundation, and the Veterans Health Administration. He has also worked as a consultant for Pfizer and Accenture. Professor Peköz has also taught at Harvard, UCLA and also at UC Berkeley, where he received an award for outstanding instruction. At Boston University he was awarded the Broderick Prize for Teaching. For a current CV click here.
· S. Ross, E. Peköz. A Second Course in Probability, ProbabilityBookstore.com, Boston: May 1, 2007.
· M. Brown, E. Peköz and S.M. Ross. Blockchain Double-Spend Attack Duration.
· A. Akkas and E. Peköz. Batching and Waste in Perishable Supply Chains.
· Z. Zhang, E. Peköz and S.M. Ross. Dueling bandit problems.
· E. Peköz, A. Röllin and N. Ross. Occupation statistics for critical branching random walk.
· S. Chen, E. Peköz, N. Pillai, A. Smith, E. Stanley. Peeking into the future: non-Markovian coupling and a wealth exchange model for cryptocurrencies.
· Bhaswar Bhattacharya, Sourav Chatterjee, Persi Diaconis, Xiao Fang, Han Liang Gan, Haiyan Huang, Adrian Röllin, Wenpin Tang, and Jon Wellner. Random walk generated from random permutations: when Stein meets Levy.
Probability Approximations and Network Science
The goal of this research is to better understand the growth and structure of networks, for example those arising in social networks and in the healthcare sector. Here we have developed and tested a number of approximations for models used to predict behavior of these networks.
· I. Adler, Y. Cao, R. Karp, E. Peköz, S. Ross. Random Knockout Tournaments. Operations Research, 65(6):1589-1596 (2019)
· E. Peköz, I. W. McKeague, and Y. Swan. Stein's method and approximating the. Bernoulli, 25(1), 2019, 89–111
· E. Peköz, A. Röllin and N. Ross. Polya urns with immigration at random times. Bernoulli, 25(1), 2019, 189–220.
· M. Brown, E. Peköz and S.M. Ross. Reflections on new directions for an ancient science: reliability and blockchain. A paper from the panel session held at the 10th International
Conference on Mathematical Methods in Reliability, 2018.
· E. Peköz, A. Röllin and N. Ross. Joint degree distributions of preferential attachment random graphs. Advances in Applied Probability, 49, 368–387 (2017)
· E. Peköz, A. Röllin and N. Ross. Generalized gamma approximations with rates for urns, walk and trees. Annals of Probability, Vol. 44, No. 3, (2016), pp. 1776–1816.
· E. Peköz, A. Röllin and N. Ross. Degree asymptotics with rates for preferential attachment random graphs. Annals of Applied Probability, Vol. 23, No. 3 (2013), pp. 1188 – 1218.
· E. Peköz, A. Röllin and N. Ross. Total variation and local limit error bounds for geometric approximation. Bernoulli, 19(2), 2013, 610–632.
· E. Peköz and A. Röllin. Exponential approximation for the non-critical Galton-Watson process and for occupation times of Markov chains. Electronic Journal of Probability, No. 51 (2011), pp. 1381–1393.
· E. Peköz and A. Röllin. New rates for exponential approximation and the theorems of Renyi and Yaglom. Annals of Probability, Vol. 39 (2011), No. 2, 587–608.
· E. Peköz, A. Röllin, V. Cekanavicius and M. Shwartz. A three-parameter binomial approximation. Journal of Applied Probability, 46, no. 4 (2009), 1073-1085.
· E. Peköz. Stein's Method for Geometric Approximation. Journal of Applied Probability, 33, 1996, pp. 707-713.
Healthcare Quality Measurement and Provider Profiling
The goal of this research is to produce better methods for assessing healthcare provider performance with respect to quality and using these to rank providers. Here we have developed and tested a number of new methods that show promise for changing the way healthcare quality is measured and rewarded.
· M Shwartz, EA Peköz, JF Burgess Jr, CL Christiansen, AK Rosen, D Berlowitz. (2014). A Probability Metric for Identifying High-Performing Facilities: An Application for Pay-for-Performance Programs. Medical care 52 (12), 1030-1036.
· Sullivan, J. L., Shwartz, M., Burgess, J. F., Peköz, E. A., Christiansen, C. L., Gerena-Melia, M., Berlowitz, D., (2013). Person Centered Care Practices and Quality in Department of Veterans Affairs Nursing Homes: Is There a Relationship? Medical Care, 51(2), 165-171.
· M. Shwartz, E. Peköz, J. Burgess, C. Christiansen. Shrinkage estimators for composite measure of quality conceptualized as a formative construct. Health Services Research, 2013 Feb; 48(1):271-89.
· M. Shwartz, E. Peköz, A. Labonte, J. Heineke, and J.D. Restuccia. Bringing Small Area Variations in Hospitalization Rates Back to the Hospital: The Propensity to Hospitalize Index – and a Test of Roemer’s Law. Medical Care, Vol. 49, No. 12, pp. 1062-1067, 2011.
· E. Peköz, M. Shwartz, C. Christiansen, D. Berlowitz. Approximate models for aggregate data when individual-level data sets are very large or unavailable. Statistics in Medicine, 29 (2010), pp. 2180–2193.
· Stolzmann K.L., Meterko M., Shwartz M., Young G.J., Peköz E.A., Benzer J.K., Osatuke K., White B. and Mohr D.C. Accounting for Variation in Technical Quality and Patient Satisfaction: The Contribution of Patient, Provider, Team and Medical Center. Medical Care, 48 (2010), no. 8, pp. 676 – 682.
· M. Shwartz, J.Ren, E. Peköz, X.Wang, A. Cohen, J.Restuccia . Estimating a Composite Measure of Hospital Quality from the Hospital Compare Database: Differences When Using a Bayesian Hierarchical Latent Variable Model versus Denominator-Based Weights.
· M. Shwartz, A. Ash, E. Peköz. Risk Adjustment and Risk-Adjusted Provider Profiles. Journal of Healthcare Technology and Management, Volume 7, Number 1-2 (2006), pp. 15 - 42.
· M. Shwartz, E. Peköz, M. Posner, J. Restuccia, L. Iezzoni. Do Variations in Disease Prevalence Limit the Usefulness of Population-Based Hospitalization Rates For Studying Variations in Hospital Admissions? Medical Care. 43(1):4-11, January 2005.
· Ash, M. Shwartz, and E. Peköz. Comparing Outcomes Across Providers. LI. Iezzoni, ed. Risk Adjustment for Measuring Health Care Outcomes, 3rd edition. Health Administration Press, Chicago, IL, 2003.
· E. Peköz, M. Shwartz, L. Iezzoni, A. Ash, M. Posner, J. Restuccia. Comparing the Importance of Disease Rate vs. Practice Style Variations in Explaining Small Area Variations in Hospitalization Rates for Two Respiratory Conditions. Statistics in Medicine, Vol 22, 2003, pp. 1775-1786.
Queueing models and Reliability for Operations
The goal of this research is to develop new methods for predicting congestion and reliability lapses in operations systems. Here we have developed methods for solving a number of challenging models used for forecasting the behavior of complex systems in operations management.
· M. Brown, E. Peköz and S.M. Ross. Finding expectations of monotone functions of binary random variables by simulation, with applications to reliability, finance, and round robin tournaments. In Stochastic Analysis, Stochastic Systems, and Applications to Finance, Allanus Tsoi, David Nualart, George Yin, Editors, 2011.
· M. Brown, E. Peköz and S.M. Ross. Some results for skip-free random walk. Probability in the Engineering and Informational Sciences, 24 (2010), 1–17.
· M. Brown, E. Peköz and S.M. Ross. A Random Permutation Model Arising in Chemistry. Journal of Applied Probability, 45 (2008), no. 4, pp. 1060-1070.
· E. Peköz, S. Ross, S. Seshadri. How Nearly Do Arriving Customers See Time-Average Behavior? Journal of Applied Probability, 45 (2008), no. 4, pp. 963-971.
· E. Peköz, S. Ross. Relating Customer and Time Averages Using ‘Forward’ Coupling From the Past. Journal of Applied Probability, 45 (2008), no. 2, pp. 568-574.
· Medical Care, Volume 46, Number 8, August 2008, pp. 778-785.
· M. Brown, E. Peköz and S.M. Ross. Coupon Collecting. Probability in the Engineering and Informational Sciences, 22 (2008), pp. 221-229.
· S. Ziya, H. Ayhan, R. Foley, E. Peköz. A Monotonicity Result for a G/GI/c Queue with Balking or Reneging. Journal of Applied Probability, 43 (2006), no. 4, pp. 1201-1205.
· E. Peköz. A Compound Poisson Approximation Inequality. Journal of Applied Probability, 43 (2006), no. 1, pp. 282--288.
· E. Peköz, J. Blanchet. Heavy Traffic Limits via Brownian Embeddings. Probability in the Engineering and Informational Sciences, 20 (2006), pp. 595-598
· E. Peköz and S.M. Ross. Compound random variables. Probability in the Engineering and Informational Sciences, 18 (2004), no. 4, 473-484.
· E. Peköz. Samuelson's Fallacy of Large Numbers and Optional Stopping. Article reprinted in Paul A. Samuelson: Critical Assessments of Contemporary Economists, John Cunningham Wood and Michael McLure (eds.), New York: Routledge, 2004.
· E. Peköz, R. Righter, and C. Xia. Characterizing Losses During Busy Periods in Finite Buffer Systems. Journal of Applied Probability, 40, 1, March 2003, pp. 250-256.
· E. Peköz. Some Memoryless Bandit Policies. Journal of Applied Probability, 40, 1, March 2003, pp. 250-256.
· E. Peköz and N. Joglekar. Poisson Traffic Flow in a General Feedback Queue. Journal of Applied Probability, 39, 2002, pp. 630-636.
· E. Peköz. Optimal Policies for Multi-server Non-preemptive Priority Queues. Queueing Systems: Theory and Applications, 42, 2002, pp. 91-101.
· E. Peköz. Samuelson's Fallacy of Large Numbers and Optional Stopping. Journal of Risk and Insurance, 2002, Vol. 69, No. 1, pp. 1-7.
· E. Peköz and M. Lapre. Inequalities for Queues with a Learning Server. Queueing Systems: Theory and Applications, 37, 2001, pp. 337-347.
· E. Peköz. More on Using Forced to Idle Time to Improve Performance in Polling Models. Probability in the Engineering and Informational Sciences, 13, 1999, pp. 489 - 496.
· E. Peköz. Ignatov's Theorem and Correlated Record Values. Statistics and Probability Letters, 43, 1999, pp. 107-111.
· E. Peköz. On the Mean Number of Refusals in a Busy Period. Probability in the Engineering and Informational Sciences, 13, 1999, pp. 71-74.
· E. Peköz and S.M. Ross. Mean Cover Times for Coupon Collecting and Star Graphs. In Advances in Applied Probability and Stochastic Processes, Academic Publishers, Boston, January 1999.
· E. Peköz. A Note on Reliability Inequalities Via Conditional Inequalities. Journal of Applied Probability, 36, 1999, pp. 1251-1254.
· E. Peköz and S.M. Ross. Estimating the Mean Cover Time for a Semi-Markov Process Via Simulation. Probability in the Engineering and Informational Sciences, 11, 1997, pp. 267-271.
· S. Hershkorn, E. Peköz, and S.M. Ross. Policies without Memory for the Infinite-Armed Bernoulli Bandit under the Average-Reward Criteria. Probability in the Engineering and Informational Sciences, 10, 1996, pp. 21-28.
· E. Peköz and S.M. Ross. A Simple Derivation of Exact Reliability Formulas for Linear and Circular Consecutive k-of-n:F Systems. Journal of Applied Probability, 32, 1995, pp. 554-557.
· E. Peköz and S.M. Ross. Improving Poisson Approximations. Probability in the Engineering and Informational Sciences, 8, 1994, pp. 449-462.