Keynote addressesBack to Conference information
In this talk we will discuss a highly interactive and interdisciplinary consulting project at the Danish company Novo Nordisk involving the exploration of multivariate data from a fermentation process. The data were comprised of several parallel time series of controlled process inputs and of non-controlled chemical measurements obtained either from the fermentation process itself or the subsequent purification process. Our focus will be on the use of graphical methods as a tool for exploration and for stimulating interdisciplinary discussions. The choice of statistical tools was problem driven, ranging from simple to advanced. Univariate, bivariate and multivariate graphs were used extensively. The consultancy aspects of the project will be a main focus. Specifically we will discuss how the use of a video projector and on-line statistical computations facilitated highly interactive discussions of the results with the clients. Discoveries of patterns in the data were facilitated by the interactive graphics feature of the statistical software, allowing us to trace groups of observations from one graph to another.
Antje Christensen is a statistician at the Danish pharmaceutical company Novo Nordisk, which is located near Copenhagen. She has held that position for five years, which were preceded by position as statistician at the Gallup Institute in Copenhagen, Denmark. A citizen of Germany, she received her PhD from the Ruhr University in Bochum, Germany, in 1996, in the field of knot theory, a branch of pure mathematics. She has spent several years of her studies in various contries, eg. studying in France and the US, as visiting researcher in Japan and Australia, and as high school teacher in Greenland. She has been involved in the formation of ENBIS since 1999. She is married to a mathematician and has two kindergarten-age daughters.
Terra Lycos is the Internet portal of Telefonica group. The company launched in 2001 a company wide management program using Six Sigma methodology (Six Sigma processes improvement) aimed at reducing operating costs and improving quality performance using Six Sigma statistical tools.
The conference explains how Six Sigma methodology was introduced at Terra Lycos, the results until now and includes as example a Six Sigma project using cluster analysis technique, that had as main objective to improve the effectiveness of marketing campaigns of Invertia, the Spanish finance portal of Terra Lycos.
Enrique Barba, 46, born in Barcelona, has a PhD in Telecommunication Engineering (1992), a Master in Organization and Business Management (1990) and a MsC on Telecommunication Engineering (1979) by the Polytecnical University of Catalonia (Barcelona, Spain). He got the Master Black Belt level (1998) of the Six Sigma Initiative in the Consumer Electronics Division of Sony Spain, after being trained in San Diego and Tokyo.
He is currently Senior Vice president of Engineering in Terra Lycos, where he was Vice president of Quality and as such, responsible of the Six Sigma initiative. He has previously worked in Sony, Roca York, Agfa, Thomson and Philips. He is coauthor of the book Six Sigma: an initiative of Total Quality (2001) and author of the books Concurrent Engineering (2001) and The Excelence in the New Product Development Process (1993) (all published in Spanish).
During the past twenty years, manufacturing industries, particularly in the United States, have gone through a tremendous change in the use of statistical methods and tools for product quality. Experimental design and tools for process monitoring are commonly used today to maintain and improve product quality. A natural extension on this area is to turn focus to product reliability, which is defined as "quality over time." This has given rise to programs like Design for Six Sigma and areas like Design for Reliability.
In this talk I will discuss some of the relationship between quality, reliability-engineering, and statistics. I will outline the role of statistics and statisticians in the field of reliability. We provide a brief introduction to the statistical tools used in engineering reliability and make some predictions for the future of statistics in engineering reliability.
Luis A. Escobar is a Professor in the Department of Experimental Statistics, Louisiana State University. He holds a BS from National University, Medellín, Colombia, an MS from the Inter-American Statistical Training Center (CIENES), Santiago, Chile, and a Ph.D. from Iowa State University. His research and consulting interests include statistical analysis of reliability data, accelerated testing, survival analysis, linear and non-linear models. Professor Escobar is an Associate Editor for Lifetime Data Analysis and past Associate Editor for Technometrics. He is a Fellow of the American Statistical Association and an elected member of the International Statistics Institute. Professor Escobar was awarded the 1999 Jack Youden Prize and he has won two awards for outstanding teaching at Louisiana State University. He is the co-author of Reliability Methods for Reliability Data (Wiley 1998), several other book chapters. His publications have appeared in the engineering and statistical literature.