QPRC Plenary Speaker Abstracts
Statistical Aspects of Forecasting and Planning for Hurricanes
Plenary Speaker: Ronald L. Iman, Southwest Technology Consultants
email: ron "AT" swtechcon.comAbstract
The very active 2004 and 2005 Atlantic hurricane seasons followed by the inactive 2006 season demonstrates the difficulty in forecasting the frequency and potential landfall site of hurricanes. The devastating landfall of Hurricane Katrina on the Gulf Coast and the much publicized concerns that climate change is altering hurricane frequency and intensity provides many examples of the use and misuse of statistics. While the massive news media coverage serves an indication of the interest and importance of these events, from a scientific standpoint much of the "information" in these media reports was of dubious accuracy, especially where statistics, data and decision making are concerned. These examples indicate many opportunities to advance the state of the art of hurricane forecasting and planning through the intelligent applications of statistical analyses. This presentation reviews hurricane modeling efforts and considers several issues related to hurricane planning and forecasting.
Beyond Boredom: The Issue of Data Quality
Plenary Speaker: Lionel Galway, RAND Corporation
email: galway "AT" rand.orgAbstract
The conference theme “Statistics: From Data to Information to Decision Making” presupposes data as an input. The decisions to be made include process control, allocation of resources, prognosis of challenges, and a great deal of statistical ingenuity and professional recognition focuses on analyzing data to produce information that can inform decisions. All statisticians know that data quality is a critical part of insuring that the rest of the process is meaningful, but even the mention of insuring data quality induces sleepiness and yawns. Little or no formal attention is paid to this area apart from a few practitioners. However, data costs money to collect, store, and analyze, and bad data means wasted resources. We suggest a basic set of tools and ideas to help diagnose and improve data quality, and suggest that this should be part of the knowledge base of quantitative professionals.
