(by Andrew Gelman)
I just received the following (unsolicited) email:
Please take two minutes to tell us how you work with public relations professionals and how your practice journalism in today’s social media environment and we’ll enter you to win a new iPad 2™. The lucky winner will be selected on Wednesday, March 23.
We’re reaching out to more than 500,000 working journalists around the world to learn more about their relationships with public relations professionals. At ***.com, we are here to connect you, the members of our working journalist database with the press releases and resources that you need to write your stories.
Please go to the brief 15 – question survey now . . .
This survey is your forum to tell us what’s working for you. Tell us what needs to be changed. We want to hear from you. To say “thank you” for participating, we are going to place your email address into a drawing for the new iPad 2™.
Ummm . . . 500,000 journalists and one i-Pad 2 (I refuse to type TM here), which, according to ebay, seems to be selling for about $650. That would be an expected value of $650/500000 = 0.13 cents. Not 13 cents. 13/100 of a cent. If the survey takes 15 minutes, that comes to . . . a half cent an hour! I don’t even know if Mechanical Turk people will work for a half cent an hour.
But, hey, maybe the response rate is only 1 in a 1000, in which case it’s worth $1.30, which comes to a respectable $5/hour (assuming you want an I-Pad 2, that is). On the other hand, what could be the possible use of a survey with a 0.1% response rate???
Either the prize drawing is a ripoff or the survey is a joke. Or both.
If I didn’t know better, I’d think that these people aren’t interested in our opinions at all . . .
P.S. This is relevant to the Statistics Forum because it is an example of how the statistical idea of survey sampling, used so effectively by George Gallup and so many others, can also be used as a pseudo-scientific cover story for just about anything.
It’s also a fine example for your teaching, to demonstrate the idea of an expected value.