RobertNiles.com
About Robert
Reporting Help
Finding Data on the Internet
Questions for Candidates
Stats Lessons
Mean
Median
Percent
Per capita
Standard Deviation
Margin of Error
Data Analysis
Sample Sizes
Stats Tests
Help Board
Bookstore


A Mathematician Reads the Newspaper

Read about reporters who blew it when trying to write about stats. A mathematician leads you through the tricks, citing contemporary examples.
More information
-->

Home > Statistics Every Writer Should Know > The Stats Board > Discusssion

Examples of bad use of stats in the news?
Message posted by Robert Niles (via 64.175.184.131) on July 27, 2001 at 5:42 PM (ET)

Hi,

I'm putting together another talk for a group of reporters and am looking for some fresh examples of journalists mangling stats or stats research in news stories.

Please e-mail me your favorite examples (with publication name and date, please), or just respond here.

Thanks!


READERS RESPOND:
(In chronological order. Most recent at the bottom.)

Re: Examples of bad use of stats in the news?
Message posted by JG (via 128.8.22.99) on July 30, 2001 at 12:07 PM (ET)

See the following web site: http://www.modbee.com/reports/levy/stories/20010721_01.html . They refer to an unscientic poll - whatever that means - and seem to be very confused about random sampling, populations, etc.


Re: Examples of bad use of stats in the news?
Message posted by Sara House (via 198.248.68.192) on September 10, 2001 at 7:32 PM (ET)

I remember an example of messed up statistics in my Stats I book. Of course, this is more a basic math mistake. In 1999, USA Today published two pie graphs about people ignoring commercials. One was for men and the other, for women. If you pay close attention, the pie graph about women adds up to 101 percent. I don't know if this is a USA Today mistake, or a mistake from NFO Research for Ogilvy Public Relations Worldwide (the source of the information). The title of this graph was "Ignoring Commercials?" and if appeared in the USA SNAPSHOTS section. I'm not sure of the exact date.


Re: Examples of bad use of stats in the news?
Message posted by Tomi (via 154.32.143.51) on September 21, 2001 at 2:54 AM (ET)

Your pie chart is not really a bad use of statistics. It's just the result of accumulating rounding errors.

The percentages on the pie chart will have been rounded to the nearest whole number to make things easier for readers. In the process, more have been rounded up than have been rounded down, yielding the "error" in total percentage.

Example:
Consider the numbers 8, 11, 12, 14, 15. Work them out as percentages of the total (60) and round to the nearest whole number. Adding them together, you don't get 100%.



Your $5 contribution helps cover part the $500 annual cost of keeping this site online.

Niles Online Sites:RobertNiles.comTheme Park InsiderViolinist.com

RobertNiles.com™, the site, content and services 咀opyright 1996-2002, Robert Niles.
All rights reserved. Questions? Comments? Read my Privacy Policy, or E-mail me!