Female managers in India elicit 5% higher worker performance than males, but of course earn 15% less. http://www.gsb.stanford.edu/gsb-cmis/gsb-cmis-get-alfresco-doc/407186/notcase …pic.twitter.com/E1s9ub4Ul6
You can add location information to your Tweets, such as your city or precise location, from the web and via third-party applications. You always have the option to delete your Tweet location history. Learn more
I'd say N=199 & J=8, with putatively exogenous variation at manager level & data on employees. But u have a point.
I think that objection is adequately dealt with in the paper; 8 isn't the correct count of sample size
# i in j is large but irrelevant. Also, is a sample of 31 really "representative?" Of what?
Some final (?) thoughts on this after talking to Nathaniel:http://pastebin.com/LvrhNpJq
proved is a strong word! I think the last paragraph is overstated; no reason to think fiddling
I agree wording may be misleading, and the concerns of your paragraphs 2 and 3 are worthwhile
but I don't see any of this indicating that their CI was calculated incorrectly
Maybe I will just make a blog post out of this :(
multilevel modeling and generalizability are both thorny af
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.