Register for an account


Enter your name and email address below.

Your email address is used to log in and will not be shared or sold. Read our privacy policy.


Website access code

Enter your access code into the form field below.

If you are a Zinio, Nook, Kindle, Apple, or Google Play subscriber, you can enter your website access code to gain subscriber access. Your website access code is located in the upper right corner of the Table of Contents page of your digital edition.

The Sciences

The "Unrepresentative Sample" Canard

The IntersectionBy Chris MooneyJanuary 31, 2007 6:20 PM


Sign up for our email newsletter for the latest science news

Iain Murray is repeating the lame argument made by Darrell Issa at the Waxman hearing yesterday:

The UCS mailed out over 1600 survey forms to climate scientists and based their assertions of political interference on the 297 that got returned. That's a response rate of just 19 percent. OMB guidelines clearly state that a response rate of less than 80 percent requires an investigation of potential biases and an even closer investigation for a response rate lower than 70 percent. A response rate of lower than twenty percent is clearly vulnerable to the charge of a self-selecting sample, perhaps those with an axe to grind against their bosses, the politically motivated, and so on. In short, it proivides all sorts of legitimate reasons to dismiss the survey as utterly unrepresentative.

I will say it again: The UCS found over 100 government climate scientists claiming political interference with their work or the dissemination of that work. It is beyond perverse to attack this finding on the grounds that it isn't "representative"--that's not the point. Suppose the UCS had never even called this a "survey" at all but just announced numbers of scientists reporting political interference. They would still have documented a very disturbing phenomenon. Or alternatively, imagine that the survey was representative after all, but only 10 percent of scientists reported political interference. That would still be a serious problem. These considerations show that the "unrepresentative sample" argument, although perhaps the best the right can do, is utterly vacuous.

    3 Free Articles Left

    Want it all? Get unlimited access when you subscribe.


    Already a subscriber? Register or Log In

    Want unlimited access?

    Subscribe today and save 70%


    Already a subscriber? Register or Log In