In trying to prove that the Bush administration is throttling research into global warming, the Union of Concerned Scientists rolled out some breathtakingly bad science.

The group unveiled a supposedly scientific survey of more than 1,600 federal climate scientists as evidence that the administration was engaged in "wide-ranging political interference in research related to global warming."

"The new evidence shows that political interference in climate science is no longer a series of isolated incidents but a system-wide epidemic," Dr. Francesca Grifo, director of the UCS Scientific Integrity Program, said in a statement. "Tailoring scientific fact for political purposes has become a problem across many federal science agencies."

Grifo obviously doesn't appreciate the irony when he trots out a poll that is so flawed that it is manifest evidence of exaggeration, incompetence or dishonesty on his group's part.

You don't have to be a social scientist to understand that the survey was deceptive, for example, when it lumped into the same category scientists who said they actually experienced the alleged tampering and scientists who simply "perceived" that it happened to someone else. For example, the group's press release said "Forty-three percent of respondents reported they had perceived or personally experienced changes or edits during review of their work that changed the meaning of their scientific findings." But turn to the study's appendix, and you'll find that only 15 percent of the respondents said that they had actually experienced such interference.

Other examples abound: 43 percent perceived or experienced "fear of retaliation for openly expressing concerns about climate change outside my agency." Actually, only 14 percent personally harbored such a fear; the other 29 percent apparently thought they saw it in others. Notice, the question didn't ask how many actually experienced retaliation, instead of just fearing it.

When the survey finally got around to asking how many scientists actually received "requests by officials for scientists to provide incomplete, inaccurate, or misleading information to the public," only 12 scientists (4 percent of respondents) did. Let's see, 12 out of the 1,630 scientists who received the survey amounts an underwhelming 0.7 percent. Hardly the kind of statistic that supports the claim of a "wide-spread epidemic" of interference.

Explaining the problem in more detail was the Statistical Assessment Service (STATS), a non-partisan a watchdog at George Mason University that tries to correct misinformation in the media springing from bad science, politics or ignorance.

STATS said that by lumping together scientists who actually experienced interference with those who only perceived it, the survey "creates a statistical phenomenon that artificially inflates the impression of a hostile work environment. Consider an agency that contains 10 scientists. One tells the other nine that he has encountered interference. When they are surveyed, all ten report that they have 'perceived in others and/or personally experienced' interference. So one act of interference is counted as ten acts that are 'perceived' or 'experienced'; ten percent of the scientists have been interfered with, but 100 percent report 'perceiving in others and' or personally' experiencing interference. If the agency contains 100 scientists, the interference experienced by one becomes 'perceived' interference by the other 99, and so forth."

The survey's "most obvious problem" STATS said, was the low response rate of 17 percent. "This means we don't know the views and experiences of the other 83 percent...Any professional survey researcher...will tell you that a 17 percent response rate is inadequate to draw conclusions about the group being surveyed, in the absence of other information demonstrating that the sample is representative." STATS quotes Harris Poll chairman Humphrey Taylor as saying a small response rate is more damaging than a small sample, noting that many peer-reviewed academic journals will not accept papers relying on samples smaller than 50 percent.

The survey also may be infected with a "selection bias," meaning that "the scientists who took the time and effort to fill out and return the questionnaire might be precisely those most upset about perceived interference."

STATS also refers to "a great deal of social science evidence" that such perceptions often are wrong. "The tendency to believe that others will be influenced by forces to which we ourselves are immune (e.g., by misleading advertising or partisan rhetoric) is so common that sociologists have a name for it—the 'third person effect.'"

"Finally," STATS said, "the researchers assume that all these responses refer to officials' efforts to alter certain kinds of findings about global warming. But that is not specified in the questionnaire." For example, a scientist could find a change in working conditions without it having anything to do with global warming.

The original research was bad enough, but the reporting of it was horrendous. No telling where NBC's Andrea Mitchell got the figure that "nearly half [the scientists] were pressured to eliminate the words' climate change' or 'global warming,' but it clearly wasn't from the survey, which said no such thing. Not to be outdone in the patently wrong department, the New York Times reported that 60 percent of the scientists "personally experienced" interference. ABC's Jake Tapper said, "scientists say their work on global warming has been watered down and twisted by the White House..." even though such hyperbole is not a conclusion warranted by the survey.

Naturally, editorial writers, egged on by faulty science and faulty reporting, raised the usual alarms, such as the Minneapolis Star Tribune's "Bush's blatant abuse of climate scientists."

One explanation for such appalling journalism is the industry's willingness to be spoon-fed by the likes of Rep. Henry Waxman, D-Calif., who gladly sanctified the bad science by giving it a platform on his Committee on Oversight and Government Reform. "It appears there may have been an orchestrated campaign to mislead the public about climate change," Waxman said.

And if anything makes Bush look bad, some in the media will show up. Like NBC's Brian Williams, for example, who intoned on his nightly newscast: "The question in Washington was this: did the Bush administration...try to cook the books on the topic of global warming?"

Of course, scientists ought not be pressured or made to change their research to suit a political or ideological agenda. I wouldn't be surprised if someone, somewhere down the line tried, but I also don't buy the whining by some scientists about how delays in the "release of websites, press releases, reports, or other science-based materials" demonstrated some sort of conspiracy to shut them up. What do they think, that they're not working in a government bureaucracy?

I'm not surprised, but I can't excuse, how the Union of Concerned Scientists, the inexhaustibly liberal and self-appointed guardians of scientific purity, can try to corrupt science for its own ends. But I never can get over how so many of my media colleagues allow themselves to be so easily manipulated by junk science.