Powerpoint

Correlation and Causation
Part III – Causation
This video is designed to accompany
pages 19-24
in
Making Sense of Uncertainty
Activities for Teaching Statistical Reasoning
Van-Griner Publishing Company
Human Inference Point
Two variables can be highly associated and no causal
links exist at all.
Human inferences from graphs and numbers that
suggest association, or exhibit strong correlation, have
to be made carefully.
So Said the CDC
April 28, 2000 / 49(16);346-9
Alcohol Policy and Sexually Transmitted Disease Rates --- United States, 1981--1995
Gonorrhea Rates
• higher beer taxes were associated with lower
gonorrhea rates among young adults
Amount of Beer Tax
The Big Leap
April 28, 2000 / 49(16);346-9
Alcohol Policy and Sexually Transmitted Disease Rates --- United States, 1981--1995
• Implication of “cause and effect”
from evidence only of
association.
Gonorrhea Rates
• A beer tax increase of $0.20 per six-pack could
reduce overall gonorrhea rates by 8.9%.
Beer Tax
• Always dangerous to do. This claim in particular was
widely challenged - in part on disposable income
arguments.
Causation or Not?
LDL Levels
Student Grades
What do you think?
Hours Exercised
Final Exam Score
Life Expectancy at Birth
Time Spent Studying
Quiz Average
GNP per capita
Gender or Socialization?
The Old Horse
Correlation does not imply causation.
Need to be able to discern the strength of the
association and the credibility of any implied causation.
Not unlike a discussion of confounding, you need to be
on the look out for a third variable that might be
responsible for the association you see between the
original two variables.
Diet Drink Dilemma
Digital Bits Skeptic
Skepticism. Critical thinking. Podcast. Community.
• A study at the Utah Health Sciences center found that the more
diet soda in a person’s diet, the more likely that person was to
become overweight or obese. “After adjusting for age, sex and
ethnicity, Williams found that regular soft drinks were no longer
significantly linked to the incidence of becoming overweight or
obese, but diet soft drinks were.”
•
• The media will pick up a press release about this study and
report that diet soda can make you fat ….
Diet Drink Dilemma
Digital Bits Skeptic
Skepticism. Critical thinking. Podcast. Community.
• Of the people that consume a lot of
fast food, those that are starting to
experience weight gain are more
likely to choose diet soda than
those that haven’t experienced
weight gain. So, diet soda
consumption is probably highly
correlated with people who have a
slowing metabolism and a habit of
eating fast food. Perhaps, it is not
the diet soda that is the problem,
but the type of restaurant where
large portions of diet soda often
accompany the food.
Diet Drink Dilemma
New study is wake-up call for diet soda drinkers.
Ryan Jaslow / CBS News/ June 29, 2011, 10:09 AM
• Researchers divided mice into two groups, one of which ate food
laced with the popular sweetener aspartame. After three months,
the mice eating aspartame-chow had higher blood sugar levels than
the mice eating normal food. The authors said in a written
statement their findings could "contribute to the associations
observed between diet soda consumption and the risk of diabetes
in humans."
•
• "Artificial sweeteners could have the effect of triggering appetite but
unlike regular sugars they don't deliver something that will squelch
the appetite," Sharon Fowler, obesity researcher at UT Health
Science Center at San Diego and a co-author on both of these
studies, told the Daily Mail. She also said sweeteners could inhibit
brain cells that make you feel full.
One-Sentence Reflection
Association doesn’t imply causation
because of other variables that may be
influencing the relationships, but could
be evidence of it.