The Number Don't Lie -- Or Do They?

Campaign Desk — March 29, 2010 06:00 AM

Out on a Limb

The problems with that ‘wingnuts’ poll

By Greg Marx

In the course of surfing the Web last week, you may have come across some polling data showing that large numbers of Republicans believe some pretty scary things about the president. The figures, provided by Harris Interactive, seem to have been first reported by Daily Beast contributor John Avlon in an item posted at midnight Tuesday. The story, titled “Scary New GOP Poll,” cited details including:

45 percent of Republicans (25 percent overall) agree with the Birthers in their belief that Obama was “not born in the United States and so is not eligible to be president”

38 percent of Republicans (20 percent overall) say that Obama is “doing many of the things that Hitler did”

Scariest of all, 24 percent of Republicans (14 percent overall) say that Obama “may be the Antichrist.”

Ok, maybe that last line is not meant to be taken seriously, but still, pretty crazy, right? And Avlon wrote that “the full results of the poll… are even more frightening.” But those results wouldn’t be available until Wednesday, meaning there was no way for readers to see them—and, more importantly, no way for skeptics to examine the poll’s methodology—as the early numbers filtered through the media.

But soon enough, the results did come out, and they were promptly and persuasively skewered by, among others, Gary Langer, the polling director for ABC News.

NO CLASS TONIGHT 3/22

Students,

I will not be on campus tonight and must cancel class. Please watch you email and the class blog page for additional info, including lecture notes and responses to the midterm.

Errol

WABC Up Close, Sunday March 14, 2010

The Attorney General Bows Out of the Investigation of Paterson

Reporter's Roundtable, Friday March 12

Paterson's Poll Numbers

SPRING BREAK

Rangel Steps Down as Chairman of Ways & Means

Margin of Error

Margin of Error deserves better than the throw-away line it gets in the bottom of stories about polling data. Writers who don't understand margin of error, and its importance in interpreting scientific research, can easily embarrass themselves and their news organizations.


Check out the following story that moved in the summer of 1996 on a major news wire

WASHINGTON (Reuter) - President Clinton, hit by bad publicity recently over FBI files and a derogatory book, has slipped against Bob Dole in a new poll released Monday but still maintains a 15 percentage point lead.


The CNN/USA Today/Gallup poll taken June 27-30 of 818 registered voters showed Clinton would beat his Republican challenger if the election were held now, 54 to 39 percent, with seven percent undecided. The poll had a margin of error of plus or minus four percentage points.


A similar poll June 18-19 had Clinton 57 to 38 percent over Dole.

Unfortunately for the readers of this story, it is wrong. There is no reasonable statistical basis for claiming that Clinton's lead over Dole has slipped.

Why? The margin of error. In this case, the CNN et al. poll had a four percent margin of error. That means that if you asked a question from this poll 100 times, 95 of those times the percentage of people giving a particular answer would be within 4 points of the percentage who gave that same answer in this poll. [emphasis added]

Study Questions

BE SURE TO REVIEW LECTURE NOTES ON THE COURTS, POSTED AT http://liujournalism.blogspot.com/2010/03/lecture-4-covering-courts.html


The highest state court in New York is
a) The Supreme Court
b) The Court of Appeals
c) The Court of Claims
d) The Appellate Division


The second-highest court in New York State is
a) The Court of Claims
b) The Court of Appeals
c) The Appellate Division
d) The People's Court


What's the difference between a criminal case and a civil case?
a) Criminal cases are always heard in criminal court
b) Civil cases are usually disputes that do not involve jail or prison sentences
c) Civil cases are always heard in the Court of Claims
d) There is no jury in a civil case.

Which of the following is a criminal case?
a) Gore v. Bush
b) Kramer v. Kramer
c) The People v. Larry Flynt
d) Apple v. IBM

When covering a civil trial, the first document a reporter should try to locate is
a) The complaint
b) The indictment
c) The subpoena
d) The verdict

How many people live in New York City?
a) 7 million
b) 8 million
c) 14 million
d) 50 million


How many people live in the United States?
a) 100 million
b) 250 million
c) 300 million
d) 500 million

Statistics

From RobertNiles.com, an excellent source of information for reporters on the use and misuse of statistics:

When talking about averages -- for example, average income or average wages -- be sure you understand the difference between the Mean and the Median.

Percent changes are useful to help people understand changes in a value over time. Again, figuring this one requires nothing more than third-grade math.

Simply subtract the old value from the new value, then divide by the old value. Multiply the result by 100 and slap a % sign on it. That's your percent change.

Let's say Springfield had 50 murders last year, as did Capital City. So there's no difference in crime between these cities, right? Maybe, maybe not. Let's go back and look at the number of murders in those towns in previous years, so we can determine a percent change.

Five years ago, Capital City had 42 murders while Springfield had just 29.
Subtract the old value from the new one for each city and then divide by the old values. That will show you that, over a five year period, Capital City had a 19 percent increase in murders, while Springfield's increase was more than 72 percent.

That's your lead.

Or is it? There's something else to consider when computing percent change. Take a look at per capita to find out.