(I apologize in advance for the profanity-laden rant. But this stuff makes me nuts.)
More from the department of making shit up:
In one of those moments when the NYT decided to provide free advertising to the Heritage Foundation, it prominently features the following from one of our favourite right-wing thinktanks:
Studies Rebut Earlier Report on Pledges of Virginity
By LAWRENCE K. ALTMAN
Challenging earlier findings, two studies from the Heritage Foundation reported yesterday that young people who took virginity pledges had lower rates of acquiring sexually transmitted diseases and engaged in fewer risky sexual behaviors.
The new findings were based on the same national survey used by earlier studies and conducted by the Department of Health and Human Services. But the authors of the new study used different methods of statistical analysis from those in an earlier one that was widely publicized, making direct comparisons difficult.
Independent experts called the new findings provocative, but criticized the Heritage team’s analysis as flawed and lacking the statistical evidence to back its conclusions. The new findings have not been submitted to a journal for publication, an author said. The independent experts who reviewed the study said the findings were unlikely to be published in their present form.
Okay. Say this with me now. Manipulating the data to make it look like the truth is still considered LYING. (And I still believe that bearing false witness is a big no-no. But what do I know? I’m an unethical atheist.)
Now that certain people have decided that science can be interpreted any damn way you please, and thus, there is TOO scientific proof for Intelligent Design, apparently, you can take a survey and change the data just a little tiny bit and get whole different results. Who’d a thunk?
So, even though the original study was published in a vetted journal, and this one is not going to be published in a journal, doesn’t make this one any less legitimate, right?
Those studies that came out of Texas that showed higher rates of pregnancy among the kids who’d taken abstinence-only education courses must have been bullshit, no?
The team needs to do “a lot of work” on its paper, said David Landry, a senior research associate at the Alan Guttmacher Institute in New York. He said in an interview that it was “a glaring error” to use the result of a statistical test at a 0.10 level of significance when journals generally use a lower and more rigorous level of 0.05.
.10 or .05, what’s the big diff? Sheesh.
I figure there’s going to be lots of explaining to do soon. See, if these kids are not having sex, how are they going to explain those pregnancies? Hmmm. There is a Biblical precedent for such an explanation, but I think that was a one-time occurrence.
I’m deeply distressed that the Times ran with this story. Is there an obligation to report every piece of right-wing propaganda as if it has scientific merit? Where will this bullshit end?
Cross-posted at Stregoneria
I don’t think they really care. About the truth I mean… the point is to get the lie out there into circulation, because the lie will last (you watch, this will be cited on all sorts of right wing sites, and in debates).
NYTimes… eh. All the media is on the run. What they seemed to have learned from their Jayson Blair debacle (and the other guy, who was calling in stories from places he never was), and Judith Miller and so on is seemingly not to be more accurate … but to give more credence and space to the right.
I am not a statistician enough to delve into the math but a .10 (10%) statistical correlation is meaningless. Only the Heritage Foundation of Bogus Research would think it worth publishing.
More and more I’m beginning to see why conservatives are not present in academia. They lack fundamental grounding in research methodology and skills.
I do math, not stats, so take this for what it’s worth. But I don’t think they’re talking about a correlation of .1, but rather a p-value of .1. The p-value is the probability that the difference in results was due to chance rather than different sex ed curricula. The standard p-value most journals expect is .05 or lower. So yes, .1 isn’t acceptable as a p-value, but not as egregiously awful as a correlation of .1 would be.
I agree if the .1 is a p-value the error is less, but only less, laughable. Any reputable journal would have tossed it back with some rather nasty comments from the reviewers.
However, I did make an unwarranted assumption; My bad.
It’s been 30 years (Holy Moley!) since I worked with statistics. My interests are Mathematical Logic, Diophantine equations, Applied & Formal Logic, Chaos, and that there stuff where statistics isn’t all that productive.
What math do you do?
I did my Ph.D. in analytic number theory, but since I work at a liberal arts college, I’ve been (very) slowly working my way towards understanding the computational end of the field, because it’s easier to get students ready to understand the ideas and interact with research problems. Last sabbatical I hung out with people who work with elliptic curve cryptography, and the undergraduate research projects I’ve supervised lately have been about factorization algorithms and primality testing.
I do occasionally have to teach the stats-for-people-who-hate-math course, but when I’m not immersed in it, my command of it fades.
What I find interesting is this. They are not going to submit the results of their data analysis to a journal–they just issue it as a press release and watch as it gets picked up by news agencies. Even if their hypothesis is bogus, as was said above by Nanette, it’s now out there in the ether: “Didn’t I read somewhere that it turns out that abstinence programs do work? Oh yeah, I read it in the Times.” The Heritage Foundation has done exactly what it set out to do. It doesn’t need to do anything else.
The Right Wing makes shit up… News at eleven.
Seriously, they’ve been doing this for years. In fact, one of the first things Bush did after he took office was put the scientific arms of the government under political control. Studies that contradicted the party line were either suppressed or “edited”. I seem to remember that a few scientists got fired and smeared for pointing out bogus science involved in Bush’s Alaskan Wildlife Refuge drilling plans.
Yes. And the gov’t sites have been stripped of vital health information that might contradict the blessed abstinence program. For a while, the whole “abortion causes breast cancer” bogus crap was up there, too. People like Bjorn Lomborg are the right wing science darlings (even though Lomborg is not a scientist) while it the r.w. continues to insist that global warming is not real.
The thing is, they don’t have to prove anything. They just have to keep contradicting scientific data with their own made-up data. To the average person, how are you supposed to know what’s real and what’s not real?
There I go banging my head on my keyboard again. These people are absolutely with out values or ethics of any kind. The ends justify any and all means to get there. Frankly, if we don’t get these asshats out of there pretty soon, I’m looking for another planet.
shirl don’t leave the planet, we will miss you dearly. Damn reichwingers, are getting as bad as the Nazi’s in the 30’s, just grabbing shit out the air and making it true. The core principle that reichwingers live by is get the lie out there, the bigger the lie, the more action is taken to make sure that even if you know that it is a lie, you will accept it, if it is promoted long and hard enough. LIE is the reichwings bread and butter and the bigger the lie, the better the butter.