A previous incarnation of the test just asked what your IQ was. We got both people who had taken official tests responding, and people who were just estimating their IQ. The second group is really noisy, and made it difficult to meaningfully talk about the IQ of LWers.
I suggested the current question as a way to get high-quality information out of survey-takers, but I also wanted a question where people estimated their IQ (maybe as two questions, for the lower and upper bound of a 50% CI) so that we could still get the low-quality information.
Respondents with high IQ seem more likely to have taken official tests, though; doesn’t this overestimate LW’s mean?
Any self-report will overestimate LW’s mean, even if there is no disproportionality among test-takers. I’ve taken this into account with various assumed population means in the analysis of previous surveys, but there’s fudging involved (if the average IQ of responders is 130, is it really sensible to expect non-responders have an average IQ of 100?).
A previous incarnation of the test just asked what your IQ was. We got both people who had taken official tests responding, and people who were just estimating their IQ. The second group is really noisy, and made it difficult to meaningfully talk about the IQ of LWers.
I suggested the current question as a way to get high-quality information out of survey-takers, but I also wanted a question where people estimated their IQ (maybe as two questions, for the lower and upper bound of a 50% CI) so that we could still get the low-quality information.
I consider giqtest.com also professional/scientific, despite being taken online.
(I understand the general aversion towards online tests, and don’t mind the current wording.)
Respondents with high IQ seem more likely to have taken official tests, though; doesn’t this overestimate LW’s mean?
Any self-report will overestimate LW’s mean, even if there is no disproportionality among test-takers. I’ve taken this into account with various assumed population means in the analysis of previous surveys, but there’s fudging involved (if the average IQ of responders is 130, is it really sensible to expect non-responders have an average IQ of 100?).