In survey & focus group research, there are formal steps to exclude the professional subjects. Too corrupting & untrustworthy.
-
-
Replying to @zeynep @jeffbigham
Any chance you have a link to formal ways of excluding professional survey takers?
2 replies 0 retweets 1 like -
I ask b/c I've thought about this a lot and I haven't found a good way to get past pro survey takers online
1 reply 0 retweets 0 likes -
while still getting participants and not paying $80k a survey to do so
5 replies 0 retweets 0 likes -
Replying to @syardi @jeffbigham
I'll look but it's absolutely standard. Professional subjects must be eliminated, and subjects that talk to each other.
1 reply 0 retweets 0 likes -
It's okay maybe if you're doing image labeling, if they are workers. Not if they are taking surveys on opinions etc.
3 replies 0 retweets 1 like -
I understand the alternatives are expensive, I do. But... It's incredible that this is accepted.
1 reply 0 retweets 0 likes -
Replying to @zeynep @jeffbigham
interesting, what have you done that works? Pay 10s of 1000s per study?
1 reply 0 retweets 0 likes -
Replying to @syardi @jeffbigham
Yep. I have used undergrads only for "college youth social media". Rest is national existing sample OR I recruit with $$
1 reply 0 retweets 0 likes -
And it is very expensive; I am now going around begging money for one more year on a project cause so expensive. :-(
1 reply 0 retweets 2 likes
I understand the pressures. I just got tenure myself. But when I look at a study in which turkers are crucial.. Well.
-
-
Maybe a turker panel could turn out to be fine? But as a category, it is structurally suspect. And how do you know? sigh
1 reply 0 retweets 1 like -
Panels (you mean longitudinal?) don't have the same biases. If you got people doing a single study, it's ok to pay them.
1 reply 0 retweets 0 likes - Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.