STATISTICAL LITERACY 2003
"Statistical literacy, the ability to follow and understand arguments from data..."
For All Practical Purposes. COMAP
literacy is necessary if they are to read and evaluate reports..."
Practical Statistics For Nursing & Health Care, Jim Fowler
"basic statistical literacy is essential in our
contemporary world..." Making Sense of Data and Statistics in Psychology
by Brian Greer
"Statistical Literacy" is the ability to understand and
critically evaluate statistical results that permeate our daily lives"
Katherine Wallman, 1992 ASA Presidential address
"Many universities now have statistical or numerical literacy
courses in addition to the traditional introductory statistics course.
One lecture explaining the difference between an observational study and a
randomized experiment, and the role of confounding variables in the
interpretation of observational studies would do more to prepare students
for reading the news than a dozen lectures on statistical inference
procedures." Jessica Utts, The American Statistician, May 2003. P. 74.
"The ABS (Australian Bureau of Statistics) regards
literacy as important. It is a life skill that all people should have."
Dennis Trewin, Director
you have huge data sets, which are essentially population, it isnít
the sampling variability that is important. It is the actual figures themselves,
and what are the connections between them. That
is an important part of what I would now put in statistical literacy
-- which I wouldnít have put in 20 or 30 years ago, because there
wasnít so much of this sort of stuff around.
literacy goes beyond numeracy by focusing on reading and
communicating those topics studied in numeracy."
Augsburg College, 3/2003.
talking about simple stuff. Iím talking about percentages,
proportions, ratios, and rates. Itís the sort of thing
that gets handled, if handled at all, in the first week of the
introductory statistics course and then itís assumed that ďHey, we all
know this stuff. We can move on.Ē Yet those of us who
spend our time talking with students know full well that, in fact, this
isnít something they all understand. Their confusion affects the
way they read the newspaper, it affects the way that they vote, and it
affects the way that they understand the world around them.
Speech at Augsburg College, 11/2002.
statistical literacy is today a pressing issue. Not knowing that
statistical arguments are inductions, statistically illiterate people
assign to such arguments the same status as the deductive theorems of
their school days, and thus hold the conclusions to be beyond question.
It is my impression, however, that even in developed societies formal
teaching aimed expressly at enhancing statistical literacy is still a
fledgling enterprise, offered only in scattered locations and to
relatively few people." American Statistician, May 2003, p.
"Statistics is essentially involved with drawing conclusions
from data. Stats is needed on all levels of life. A recent workshop
highlighted the need for statistical literacy among government
officials. After all, it is of little use to pour money into a poverty
relief program, if it doesn't relieve poverty. How do we find out if we
have achieved the aim? We need to decide on what would tell us whether
we have achieved our aim or not. A drive for statistical literacy
in government is about to begin. We also need statistical literacy
among the general public. President Mbeki is aiming for economic
literacy. A pre-requisite is statistical literacy."
Dr. Howard Wainer: "Three
Paradoxes" [30 Jan, 2004]
Joel Best: More Damned Lies & Statistics [1/2004]
Although many know of
Simpson's Paradox, the new graphical technique used to illustrate this
well-known paradox is revolutionary. While some may have heard of
Lord's Paradox, this presentation (based on one by Dr. Donald Rubin)
deserves more attention. But how many have heard of Kelley's paradox?
Read this paper to see how regression to the mean can mislead the
unwary. [Strongly recommended for reflective study. A
shortened version of this paper will be published in TAS.]
Coming this summer will be MDLS: More Damned Lies and
Statistics -- the sequel to "Damned Lies and Statistics."
With his smooth and enchanting style, his interesting stories and his
friendly guidance, Joel gives readers a tour of some other ways that
people use statistics opportunistically. His final chapter
is provocative: Wither Statistical Literacy? Preview
quotes: "Statistical literacy falls between the stools on which
academic departments perch."
Donald Rubin (Chair, Dept. of Statistics, Harvard) gave a one-hour
introductory lecture on "Causal Inference" at the 2003 ASA Joint
Statistical Meeting. Power Point is used to display his slides.
Each slide has full audio.
To hear the audio, open this
file from its current position. Wait 20-60 seconds. [Download does
not include audio]
Dr. Paul Holland (2003) reviews the move (the slippery
slide) from descriptions to comparisons to causation in observational
studies. From the abstract, "Race is often viewed as a causal
variable, and "RACE effects" found from regression analyses are
sometimes given causal interpretations. I argue that this is a mistaken
way to proceed. RACE is not a causal variable in a very important sense
of the word, and yet it does have a significant role in causal studies."