Literature Index

In the third part of a series, advice for teachers on moving students engaged in Internet science projects beyond collecting and uploading data to analyzing data from many sites is presented. The advice deals with what is involved in a data-centered investigation and with leading such investigations by using reliable data, beginning with familiar contexts, using data with salient trends, and working with representations that students understand.

Statistics uses scientific tools but also requires the art of flexible and creative reasoning.

A standard topic in many Introductory Statistics courses is the analysis of dependent samples. A simple graphical approach that is particularly relevant to dependent sample comparisons is presented, illustrated and discussed in the context of analyzing five real data sets. Each data set to be presented has been published in a textbook, usually introductory. Illustrations show that comprehensive graphical analyses often yield more nuanced, and sometimes quite different interpretations of data than are derived from standard numerical summaries. Indeed, several of our findings would not readily have been revealed without the aid of graphic or visual assessment. Several arguments made by John Tukey about data analysis are seen to have special force and relevance.

Statistical questions suffuse the favric of our society at almost all folds. When Bill Krusak and I offered that ovservation in an Amstat News artical just over a decade ago, the universe of our immediate concern was the federal statistical system--a universe that to some may have seemed rather parochial. Our principal intent in sharing out views with the members of ASA was to underscore the pervasiveness of statistics produced by the federal govenment in out professional and personal lives. The urgency in our voices stemmed from what we perceived to be "penny-wise but poiund0foolish decision" that would undermine the quality of data for research, program planning, allocation of resources, and policy evaluation--by academics, buiness leaders, government officials, and citizens--for years to come (Druskal and Wallman 1982).<br>It is not my mission tonight to revisit either historic or recent tragedies and triumphs of the federal statisital system. Many have written and spoken on these matters; several of my predecessors have discussed these issues, and how the ASA might respond to them, intheir presidential addresses to out membershp. I will, hoever, use the milieu of federal statistic as the opening scene for elaborating my hope that by enhancing statistical literacy we may succeed in enriching our society. My aims for the remarks I will share with you this evening are three:<br>--to underscore the importance of strengthening understanding of statistics and statistical thinking among all sectors of our population;<br>--to highlight some avenue we can pursue to enhance our citizens' statistical literacy; and<br>--to suggest some ways that individual statisticians and the American Statistical Association can enrich our society.