Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

How Not to be Lied to with Statistics

Numerous techniques for saying what you want to say using statistics
by

Ron Buelow

on 27 September 2016

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of How Not to be Lied to with Statistics

How Not to be Lied to with Statistics
How People Say What They Want to Say with the Backing of Statistics
References:

Best, Joel, “Damned Lies and Statistics”, 2001, University of
California Press, Ltd.

Crossen, Cynthia, “Tainted Truth”, 1994, Simon & Shuster

Huff, Darrell, “How to Lie With Statistics”, 1982,
W.W. Norton Co., Inc.
“Don't be buffaloed by experts and elites. Experts often possess more data than judgment.” General (Colin Powell)
References:

Best, Joel, “Damned Lies and Statistics”, 2001, University of
California Press, Ltd.

Crossen, Cynthia, “Tainted Truth”, 1994, Simon & Shuster

Huff, Darrell, “How to Lie With Statistics”, 1982,
W.W. Norton Co., Inc.
“Much of the debate over global warming is really beside the point, because the key assumption -- that there is a scientific consensus on climate change -- is false. In fact, many mainstream scientists say there is insufficient knowledge of the magnitude of natural climatic variations, especially solar radiation and ocean currents, to gauge how large the human impact is by comparison.” (George H. Taylor, state climatologist for Oregon and president of the American Association of State Climatologists)
In 1999, former Vice President Al Gore told schoolchildren that the summer heat wave on the East Coast was evidence for global warming.
Make Assumptions
Promoters of global warming fears … have been busy blaming storms, floods, droughts, disease, and all kinds of misfortunes on the atmospheric increase of greenhouse gases. Former President Bill Clinton, in New Zealand, blamed it all on the use of energy.
“Drought occurs in almost every region on earth on a somewhat regular basis,” said Charles H.V. Ebert, SUNY Distinguished Professor in the Department of Geography. “Patterns of relatively wet, dry, hot or cold weather usually run in six- to-eight-year cycles. But media attention, combined with our poor memories of past weather, tend to generate unjustified alarm for our climatic future.” According to Ebert, hot spells have been occurring for thousands of years and each one is followed by a cooling period. People just don't remember, because “our memories are short.”
Make Assumptions
Former Vice President Al Gore attributed the devastating 1997 flood on the Red River in North Dakota and Minnesota to a combination of El Nino and climate change.
An article in USA Weekend (August 29, 1999) by two Weather Channel meteorologists, Colin Marquis and Stu Ostro, argues that the weather is pretty much the same as it has always been, only that our perceptions have changed. One of the reasons why we may think the weather is wilder is the massive growth in media coverage.
Make Assumptions
Make Assumptions
Flood damages and fatalities have generally increased in the last 25 years. Reason: more rain and floods?
This can be attributed entirely to the “nearly uninhibited growth along the nation's coasts.”
Overwhelm Your Audience
With Impressive Data
Overwhelm Your Audience
Overwhelm Your Audience
With Percent Lies
With Terminology
Television ad in London:
“Get property in Corby 156%
cheaper than in London!”
Don’t Pay Attention to Scale
Change Scale on y-axis to Your Liking
Don't Show Whole Graph
Use Pictograph to Represent 3-D
Use Perspective to Stretch Truth
Use Larger Scale for Scatterplots
Many Lies on One Graph
Make Assumptions
Overwhelm Your Audience
Graph Related Lies
Use of "Average"
Bias Problems
Withhold Important Facts
Keep Doing Studies Until Results are Right
Definition of Terms
Danger in Prediction
Use of “Average”
Graph Related Lies
Used Loosely
Doesn't Mean Very Much
"Often an average -- whether mean or median, specified or unspecified -- is such an oversimplification that it is worse than useless. Knowing nothing about a subject is frequently healthier than knowing what is not so, and a little learning may be a dangerous thing."
"Altogether too much of recent American housing, for instance, has been planned to fit the statisticially average family of 3.6 persons. Translated into reality this means 3 or 4 persons, which, in turn, means 2 bedrooms. And this size family, "average" though it is, actually makes up a minority of all families."
"We build average houses for average families," say the builders -- and neglect the majority that are larger or smaller. Some areas, in consequence of this, have been overbuilt with 2 bedroom houses, under built in respect to smaller and larger units. So here is a statistic whose misleading incompleteness has had expensive consequences.
“Common sense has somehow failed in the face of the convincingly precise and authoritative 3.6. It has somehow outweighed what everybody knows from observation: that many families are small and quite a few are large.”(Huff, pp. 43-44)
Misleading Conclusions
Do half of the wage earners
earn less than the average?
“Bearing in mind the few Welshmen who, for one reason or another, have the misfortune to have only one leg and the even fewer who have no legs at all, then each Welshman on average has only 1.9995 legs. It can therefore be stated in all honesty that 99.95% of Welshmen have more than the average number of legs.”
Bias Problems
Sample Too Small
Extrapolate From Few Data Points
Sample Not Random
Scientific Elitism
I am reminded of this in many global warming articles in the press today. Here is one that caught my eye today. There is nothing unusual about it, it just is the last one I saw:

The writer said he has decided to run because he wants to be able to look at his children in 20 or 30 years and be able to say that he took action to try to address important challenges facing humanity. He cited climate change as a “huge” concern, noting that this was driven home during a trip he took to the Arctic three weeks ago.

“The thing that was most striking was how the speed of climate change is accelerating—how it’s much worse than anyone really wants to believe,” Byers said. “To give you a sense of this, we flew over Cumberland Sound, which is a very large bay on the east coast of Baffin Island. This was three weeks ago; there was no ice.”

Do you see the single data point: Cumberland Sound three weeks ago had no ice. Incredibly, from this single data point, he not only comes up with a first derivative (the world is warming) but he actually gets the second derivative from this single data point (change is accelerating). Wow!
Countering Scientific Elitism
How can someone combat a scientific system that favors the few, the powerful, the elite? First, when confronted with policies based on the "scientific consensus," point out that "consensus" is not a valid scientific argument. It reintroduces bias into science and has always been used when the underlying evidence is weak. Urge a return to science based on experiments and observations.
Second, remember the atheistic bias of elite scientists and maintain a healthy skepticism of their opinions--particularly on broad social policies and medical ethics. In some instances the same people who decide what is data are the ones who gather the data, analyze the data, and then interpret the results into policy. For this reason, people need a healthy distrust of the experts. Back in 1982, even Gould warned:
People need to realize that scientists are human beings like everybody else and that their pronouncements may arise from their social prejudices, as any of our pronouncements might. The public should avoid being snowed by the scientist's line: "Don't think about this for yourself, because it's all too complicated."16

Third, support those groups that maintain independent oversight and review. The Institute for Creation Research is one such group. It receives no governmental, educational, or industrial funding--but ICR continues to expose the scientific weaknesses of naturalistic science.
Withhold Important Facts
Incomplete Report
What is left out here is the fact that there were three less
matches than the previous year. In division 1, average
attendance was 25,000 per match.

Result: attendance had actually gone UP!!
The Daily Telegraph (London, UK) made a lot of the decline
In football attendance in the 1970’s. Below is a chart which
was in their publication headlined: “Gates Down.”
Keep Doing Studies Until Results are to Your Liking
Definition of Terms
Statistical Claim:"Today, electric power is available to more than three quarters of U.S. farms..."
Danger in Prediction
"In the space of one hundred and seventy-six years the Lower Mississippi has shortened itself two hundred and forty-two miles. That is an average of a trifle over one mile and a third per year.
Therefore, any calm person, who is not blind or idiotic, can see that ... seven hundred and forty-two years from now the Lower Mississippi will be only a mile and three-quarters long, and Cairo and New Orleans will have joined their streets together, and be plodding comfortably along under a single mayor and a mutual board of aldermen." (Mark Twain)
What error was made here?
What error was made here?
Full transcript