|
|
The world of statistics has its own specialized terminology that outsiders find puzzling.
 Statistical knowledge is a national resource for efficient planning for the future, whether the subject is medicine or agriculture or urban infrastructure, says IUB statistician Madan Puri. It allows for optimal decision making in areas both scientific and technical. "Statistical thinking," wrote futurist H.G. Wells, "will one day be as necessary for efficient citizenship as the ability to read and write." Photo by Heather Hill |
At the International Statistical Association Conference in Hamilton, Canada, last fall, Madan Puri of IU Bloomington's Department of Mathematics was recognized with an Honorary Fellowship Award for Outstanding Contributions to Statistics and Probability. The name of the award is understandable enough for outsiders, but the association's commendation slips into terminology that only an academic statistician could fathom.
"For pioneering contributions in nonparametric statistics, order statistics, time series, fuzzy sets and measures, asymptotic expansions of the distributions of rank statistics, as well as large deviation results spanning a variety of areas such as analysis of variance, analysis of covariance and multivariate analysis...providing a new direction for the study of time series analysis via rank-based methodology..." Puri was also commended for the "Puri-Sen Era in Mathematical Statistics," and his extensive work in organizing international conferences and serving as editor-in-chief of the Journal of Statistical Planning and Inference.
Internationally, Puri is regarded as one of the most versatile researchers in the field and in 1992 was ranked ninth most prolific author in the world in top statistical journals. That ranking came from a survey carried out for the Natural Sciences and Engineering Research Council of Canada. In 1997, he was ranked fourth most prolific in a report titled Statistics on Statistics: Worldwide Performance Based on Journal Publications in the Period 1985-1995. And among statisticians in universities such as IU that do not have separate departments of statistics, Puri ranks No. 1 in the "prolific" category.
All that said, what of that specialized statistical language? "Fuzzy sets," for example.
| The quiet statisticians have changed our world--not by discovering new facts or technical developments, but by changing the ways we reason, experiment and form our opinions about it.
--Stephen Hawking astrophysicist |
"Fuzzy sets are effective tools for dealing with uncertainties due to vagueness," explained Puri. "In everyday life, we often deal with imprecisely defined properties or quantities--a few books, a long story, a young woman, or a tall man, as examples. A fuzzy set is a class of objects with a continuum of grades of membership."
It is characterized by a membership (characteristic function) which assigns to each object a grade of membership ranging between 0 and 1. The concept, said Puri, was first introduced in order to allow imprecisely defined notions to be properly formulated and manipulated. Its use is widespread, particularly in the fields of pattern recognition and information processing.
In statistics, said Puri, "we quantify the uncertainties due to randomness." While uncertainty is constantly forecast in our everyday lives, decision making does not carry its full implication unless the amount of uncertainty is specified in a meaningful way.
"With quantification of uncertainty, we have found a means to express and convey knowledge in a meaningful way. For instance, weather forecasts are made nowadays in terms of probabilities. 'There is a 30 percent chance of rain tomorrow' is a more logical or useful way of conveying information about the atmospheric conditions than the assertion 'It will rain tomorrow' or 'It will not rain tomorrow.' In other words, chance is no longer an expression of ignorance; on the other hand, it is a way to present our knowledge.
"In decision making, we have to deal with uncertainty. The alternative to avoiding mistakes is not refraining from making decisions. There can be no progress that way. The best we can do is to make decisions in an optimal way by minimizing the risk involved. Inductive reasoning and quantification of uncertainty provide an answer to the problem," said Puri.
The professor shifted his focus from mathematics to statistics after receiving two degrees from Punjab University and earning a doctorate from the University of California at Berkeley.
As an advocate of the value of statistical analysis in many walks of life, Puri has taken his knowledge to many parts of the world.
In addition to speaking engagements at international conferences, he has held visiting professorships at numerous universities as well as collaborating with 78 scholars from 22 countries. He has received Germany's Alexander von Humboldt Foundation Senior U.S. Scientist Award twice and for his 65th birthday in 1996, 52 of his colleagues wrote articles for a book in his honor. Another book, Asymptotics, Nonparam etrics and Time Series Analysis: A Tribute to Madan Lal Puri, for which 43 of Puri's colleagues have written articles, is due for publication this year.
Return to Table of Contents