# "Harris Poll confusing to Americans," reports Harris Poll **URL:** \ **Category:** Miscellaneous and Personal Stuff I Must Share\ **Created:** [April 1, 2008, 11:08pm UTC](https://boards.straightdope.com/t/harris-poll-confusing-to-americans-reports-harris-poll/443597 "2008-04-01T23:08:27Z")\ **Posts on this page:** 7\ **Page:** 1
**Author:** ![Really\_Not\_All\_That\_Bright](https://avatars.discourse-cdn.com/v4/letter/r/e8c25b/32.png) [@Really\_Not\_All\_That\_Bright](https://boards.straightdope.com/u/Really_Not_All_That_Bright)\ **Post date:** [April 1, 2008, 11:08pm UTC](https://boards.straightdope.com/t/harris-poll-confusing-to-americans-reports-harris-poll/443597/1 "2008-04-01T23:08:27Z")
While looking for some important stuff on the Harris Poll website (okay, incidence of sexual encounters with garden furniture), I couldn’t help but notice this absolute gem of a poll results title: [“Margin of Error”, When Used by Pollsters, Is Widely Misunderstood and Confuses Most People](http://www.harrisinteractive.com/harris_poll/index.asp?PID=832) Yeah, I thought it was a link to an Onion story too. > [@](#): > > Many media and pollsters, when releasing new poll results, include statements such as “the margin of error for this survey is +/- 3 percent”. A new Harris Poll was developed to measure the public’s understanding, or misunderstanding, of the phrase “margin of error” when used to describe opinion polls. It found that these words are misunderstood by most people. Arguably they confuse more people than they enlighten, and they suggest a level of accuracy that no statistician could justify. > [@](#): > > This number is actually a purely theoretical calculation of what the likely maximum error (at a 95% confidence level) would be if the survey had used a pure probability sample with a response rate of 100% and there were no other possible sources of error. In other news, **Really Not All That Bright** also reportedly confused by terms like “margin of error”. Despite having taken Scope and Methods of Political Science _twice_. ---
**Author:** ![gotpasswords](https://avatars.discourse-cdn.com/v4/letter/g/c57346/32.png) [@gotpasswords](https://boards.straightdope.com/u/gotpasswords)\ **Post date:** [April 1, 2008, 11:26pm UTC](https://boards.straightdope.com/t/harris-poll-confusing-to-americans-reports-harris-poll/443597/2 "2008-04-01T23:26:04Z")
It’s just like the old joke of the statistician asking the client “What would you \*like \* the survey results to be?” and having a means to mash the data around to fit. ---
**Author:** ![pinkfreud](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/pinkfreud/32/17603_2.png) [@pinkfreud](https://boards.straightdope.com/u/pinkfreud)\ **Post date:** [April 1, 2008, 11:30pm UTC](https://boards.straightdope.com/t/harris-poll-confusing-to-americans-reports-harris-poll/443597/3 "2008-04-01T23:30:33Z")
For several years I was an aptitude testing specialist with a government agency. When we issued test scores, the scores were reported twice: the achieved score and the score plus the standard error of measurement. More than once, people called me to ask whether these acknowledged “errors” invalidated the test scores. ---
**Author:** ![CalMeacham](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/calmeacham/32/35_2.png) [@CalMeacham](https://boards.straightdope.com/u/CalMeacham)\ **Post date:** [April 2, 2008, 12:33am UTC](https://boards.straightdope.com/t/harris-poll-confusing-to-americans-reports-harris-poll/443597/4 "2008-04-02T00:33:10Z")
Wait, I’m confused… What do people THINK that +/- 3% means? ---
**Author:** ![MadPansy64](https://avatars.discourse-cdn.com/v4/letter/m/dc4da7/32.png) [@MadPansy64](https://boards.straightdope.com/u/MadPansy64)\ **Post date:** [April 2, 2008, 12:49am UTC](https://boards.straightdope.com/t/harris-poll-confusing-to-americans-reports-harris-poll/443597/5 "2008-04-02T00:49:59Z")
[QUOTE=CalMeacham] Wait, I’m confused… What do people THINK that +/- 3% means? [/QUOTE] Plus divided by minus times three percent? ---
**Author:** ![sinjin](https://avatars.discourse-cdn.com/v4/letter/s/ebca7d/32.png) [@sinjin](https://boards.straightdope.com/u/sinjin)\ **Post date:** [April 2, 2008, 1:44am UTC](https://boards.straightdope.com/t/harris-poll-confusing-to-americans-reports-harris-poll/443597/6 "2008-04-02T01:44:33Z")
[QUOTE=gotpasswords] It’s just like the old joke of the statistician asking the client “What would you \*like \* the survey results to be?” and having a means to mash the data around to fit. [/QUOTE] Plot the curve _then_ derive the data. 🆒 ---
**Author:** ![Really\_Not\_All\_That\_Bright](https://avatars.discourse-cdn.com/v4/letter/r/e8c25b/32.png) [@Really\_Not\_All\_That\_Bright](https://boards.straightdope.com/u/Really_Not_All_That_Bright)\ **Post date:** [April 2, 2008, 2:31am UTC](https://boards.straightdope.com/t/harris-poll-confusing-to-americans-reports-harris-poll/443597/7 "2008-04-02T02:31:00Z")
[QUOTE=CalMeacham] Wait, I’m confused… What do people THINK that +/- 3% means? [/QUOTE] I’m pretty sure they understand that means the survey is accurate to a range of six per cent. I think the point is they don’t understand _why_.