Beware of “on the
average”: We dif-
ferentiated between
the median and mean
with examples dealing
Statistical Literacy Course
with family income
Title and Description
and President George
W. Bush’s 2005 claim
Course Title:
Class
that “[O]n the average,
the folks who sign up
Numbers in Everyday Life
1
for the prescription drug
Course Description: Open a newspaper
program are going to save
Subject Specifics
or turn on a TV—numbers are everywhere,
$1,300 per year.”
Class 1: Examples and
from political polls to health studies to
What is data mining?: We sports. They can provide valuable, even
Basic Concepts
illustrated the basic concepts by life-and-death information, or mislead.
Course goal and overview: We
discussing how coaches in the This course will provide insight into
reviewed the major goals of the
National Basketball Association
interpreting numbers and being well-
course and mentioned that we
use the Advanced Scout data
informed citizens. Seasoned experts (all
would not be discussing account-
mining software to formulate
PhDs) will help you understand the latest
ing numbers (or giving investment
and assess game strategies.
statistics from medical studies, public
advice), government statistics, or
opinion polls, business, and industry
statistical methods, per se. Class 2: Public
to this week’s media and more.
Studies of marriage on lon-
Opinion Polls and
gevity and impact of New York
Election Forecasts
State Clean Indoor Act: To dif- What is a poll?: We discussed
ferentiate correlation and causality, why we need polls, described a
we examined studies linking mar- poll as a process from construct-
riage to longevity and the assertion ing a questionnaire to commu-
that “fewer New Yorkers have been nicating the results, consid-
treated for heart attacks since the ered different interviewing
state’s wide-ranging no smoking methods, gave examples of
law took effect four years ago.” improperly phrased ques-
Study of impact of prayer on
tions, and described the
outcome of bypass surgery:
1936 Literary Digest poll
This first example of a planned
and its deficiencies.
study was triggered by a local How polls are conducted:
newspaper headline (incorrectly) We differentiated between
asserting that “study finds prayer the sampling frame and pop-
may make patients worse.” ulation and described various
That magical bell-shaped curve:
participant selection methods.
We described when one might
We illustrated the difficulty in
Class
expect observations to follow a
conducting polls with an exam-
2
normal distribution—and when
ple from the 2008 presidential
not. This was illustrated by the
primaries in which two polls con-
time-tested example of having
ducted by the same organization
When to trust a poll: We sum-
class participants compare histo-
at the same time disagreed.
marized problems inherent in
grams of their birthdates within Why polls work: We defined pre-election polls and used a New
a month (a number between 1 and illustrated margin of error, York Times sidebar, “How the Poll
and 31) with the averages of their polling precision, accuracy, and Was Conducted,” to review key
birthdates and those of their two the effects of sample size and components of a well-constructed
closest relatives. This led to class nonrespondents. We then poll. We cautioned that polls, no
discussion of common phenomena described problems induced by matter how well-executed, may
one would and would not expect the change from land-based to produce results that differ from
to be normally distributed. cellular pho nes. the eventual outcome.
FEBRUARY 2009 AMSTAT NEWS 17
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84