Statisticians

[lathany]

"To call in the statistician after the experiment is done may be no more than asking him to perform a post-mortem examination: he may be able to say what the experiment died of." - Ronald Fisher.

I heard this quote today at a swan-song lunchtime presentation of one of our department. It made me think of a dear friend who is dealing with the results from a survey that her colleague messed up.

Comments

[dr-bob.livejournal.com]

Makes me think of a colleague who was writing up a year or two's work, when one of his co-authors noticed that he'd written a key DNA sequence backwards, rendering the data meaningless.

[bateleur.livejournal.com]

Ouuuuuuch. I feel his pain.

[sumbitch.livejournal.com]

I didn't even tell you the punchline, which I discovered weeks after... because it was set up stupidly stupidly, every time people who shared an IP address submitted a survey it overwrote any other survey from that address. I feel so badly for the poor souls who poured their heart out in the open-ended response section (and some of them did).

*shakes head*

[lathany.livejournal.com]

*winces*

I hope he's been permanently removed from anything resembling a survey set-up.