Breakdown of median "IQ" by "LessWrongUse":
136.0000 "I lurk, but never registered an account"
140.0000 "I've registered an account, but never posted"
139.5000 "I've posted a comment, but never a top-level post"
138.0000 "I've posted in Discussion, but not Main"
138.0000 "I've posted in Main"
Breakdown of median "SATscoresoutof1600" by "LessWrongUse":
1490.0000 "I lurk, but never registered an account"
1515.0000 "I've registered an account, but never posted"
1505.0000 "I've posted a comment, but never a top-level post"
1515.0000 "I've posted in Discussion, but not Main"
1530.0000 "I've posted in Main"
Breakdown of median "SATscoresoutof2400" by "LessWrongUse":
2245.0000 "I lurk, but never registered an account"
2250.0000 "I've registered an account, but never posted"
2240.0000 "I've posted a comment, but never a top-level post"
2260.0000 "I've posted in Discussion, but not Main"
2180.0000 "I've posted in Main"
Breakdown of median "KarmaScore" by "Sequences":
0.0000 "Never even knew they existed until this moment"
0.0000 "Know they existed, but never looked at them"
0.0000 "Some, but less than 25%"
0.0000 "About 25% of the Sequences"
4.0000 "About 50% of the Sequences"
59.0000 "About 75% of the Sequences"
100.0000 "Nearly all of the Sequences"
Breakdown of median "TimeinCommunity" by "LessWrongUse":
12.0000 "I lurk, but never registered an account"
19.0000 "I've registered an account, but never posted"
24.0000 "I've posted a comment, but never a top-level post"
24.0000 "I've posted in Discussion, but not Main"
55.0000 "I've posted in Main"
Breakdown of median "AutismScore" by "LessWrongUse":
24.0000 "I lurk, but never registered an account"
26.0000 "I've registered an account, but never posted"
23.0000 "I've posted a comment, but never a top-level post"
24.0000 "I've posted in Discussion, but not Main"
22.0000 "I've posted in Main"
Breakdown of median "KarmaScore" by "Profession":
0.0000 "Other "social science""
0.0000 "Biology"
0.0000 "Statistics"
0.0000 "Art"
3.0000 "Computers (practical: IT, programming, etc.)"
7.0000 "Business"
10.0000 "Finance / Economics"
65.0000 "Computers (AI)"
10.0000 "Philosophy"
0.0000 "Computers (other academic, computer science)"
0.0000 "Engineering"
0.0000 "Other"
18.0000 "Mathematics"
0.0000 "Medicine"
10.0000 "Neuroscience"
0.0000 "Law"
6.5000 "Physics"
10.0000 "Other "hard science""
43.0000 "Psychology"
Breakdown of median "KarmaScore" by "Degree":
0.0000 "Bachelor's"
8.0000 "Master's"
0.0000 "None"
5.0000 "High school"
0.0000 "2 year degree"
0.0000 "MD/JD/other professional degree"
80.5000 "Other"
100.0000 "Ph D."
Of 1063 survey takers, 981 reported a karma score, and 466 reported that it was zero (Yvain instructed users to put in zero if they didn’t have an account). I’m actually surprised there weren’t more zeros.
Of 1063 survey takers, 981 reported a karma score, and 466 reported that it was zero (Yvain instructed users to put in zero if they didn’t have an account). I’m actually surprised there weren’t more zeros.
Which is why you do exploratory data analysis, and look at your distributions first.
Me, I’m surprised that people who don’t post bothered to take a long survey. You have to have an account to post, right? Do you have access to the system data, so that you could compare the distribution of karma scores for registered users versus the poll results?
Next suggestion—I’d probably make separate analyses based on LessWrongUse—never posted and never registered as one class , posted and more (interactive users) as another. And substitute rank(karmascore) over the whole population for karmascore.
I would think that all the karma score break downs by category would be better by median than mean, as the top scorers would really skew the data.
Of 1063 survey takers, 981 reported a karma score, and 466 reported that it was zero (Yvain instructed users to put in zero if they didn’t have an account). I’m actually surprised there weren’t more zeros.
Which is why you do exploratory data analysis, and look at your distributions first.
Me, I’m surprised that people who don’t post bothered to take a long survey. You have to have an account to post, right? Do you have access to the system data, so that you could compare the distribution of karma scores for registered users versus the poll results?
Next suggestion—I’d probably make separate analyses based on LessWrongUse—never posted and never registered as one class , posted and more (interactive users) as another. And substitute rank(karmascore) over the whole population for karmascore.