Talk by: Richard A. Berk, Distinguished Professor of Statistics and Sociology, UCLA

Title: Using Data Mining to Detect Fraud: An Application to Environmental Monitoring

Abstract: Through international agreements, the purse-seine fishery for tuna in the eastern Pacific Ocean is closely monitored. One of the goals is to prevent incidental mortality of marine species, and stiff penalties are imposed when this occurs. There are strong incentives, therefore, to underreport such mortality. In this talk, ensemble statistical procedures (a form of data mining) will be applied to official records from the fishery to identify suspicious data and the individuals who are likely to be responsible. The findings have more general applicability for monitoring regulatory compliance.

1. Just Punishment: An Empirical Study of the Federal Sentencing Guidelines (with Peter H. Rossi). New York: Aldine de Gruyter, 1997.
2. Regression Analysis: A Constructive Critique. Newbury Park, CA: Sage Publications, 2003.
3. "Multilevel Statistical Models and Ecological Scaling," (with Jan de Leeuw) in Scaling and Uncertainty Analysis in Ecology: Methods and Applications, Jianguo Wu et al. (eds.), Columbia University Press, Forthcoming, 2005.
4. "Data Mining within a Regression Framework," in Data Mining and Knowledge Discovery Handbook: A Complete Guide for Practitioners and Researchers, Oded Maimon and Lior Rokach (eds.), Kluwer Academic Publishers, 2005.

1. "Statistical Difficulties in Determining the Role of Race in Capital Cases: A Re-analysis of Data from the State of Maryland," (with Azusa Li and Laura Hickman), Journal of Quantitative Criminology, forthcoming, 2005.
2. "New Claims about Executions and General Deterrence: Deja Vu All Over Again?" Journal of Empirical Legal Studies, 2(2): 303-330, 2005.
3. "An Introduction to Ensemble Methods for Data Analysis," Sociological Methods and Research, forthcoming, 2005.
4. "Developing a Practical Forecasting Screener for Domestic Violence Incidents," (with Yan He and Susan Sorenson), Evaluation Review, 29(4): 358-382, 2005.