InvestorsHub Logo
Boards
News
Market Data
Markets
Discover
Discover
Subscribe Login/Register
S&P 500
5,482.18
(
0.93%
)
US TECH 100
19,436.80
(
1.40%
)
Dow Jones
38,773.39
(
0.48%
)
Brent Oil
83.86
(
2.11%
)
Bitcoin
67,070.00
(
0.65%
)
Post# of 252227
Next 10
Reply Private New
Public Reply Private Reply New Post
Keep Last Read
Replies (2) Keep Next 10 Report Keyboard Shortcuts
Replies (2) Next 10 Prev Next

DewDiligence

Send PM Follow Ignore
Followers 833
Posts 119855
Boards Moderated 17
Alias Born 09/05/2002

DewDiligence

Member Level

Re: iandy post# 174408

Tuesday, 02/18/2014 4:06:18 PM

Tuesday, February 18, 2014 4:06:18 PM

Post# of 252227

PRAN—First off you use Bonferroni corrections for multiple pairwise comparisons...

Given the huge number of secondary endpoints*, a bona fide use of Bonferroni corrections would have made the statsig p-value threshold for any given endpoint vanishingly small and nothing would have come out as "statsig."

*There were 672 shots on goal according to @JohnTuckerPhD on Twitter; I’ve cut this number to 336 insofar as it would not be impressive to show a “statsig” effect on some metric at the low dose but not the high dose.

“The efficient-market hypothesis may be
the foremost piece of B.S. ever promulgated
in any area of human knowledge!”

Public Reply Private Reply New Post
Keep Last Read
Replies (2) Keep Last Read Next 10 Report Keyboard Shortcuts
Replies (2) Next 10 Prev Next

Join the InvestorsHub Community

Register for free to join our community of investors and share your ideas. You will also get access to streaming quotes, interactive charts, trades, portfolio, live options flow and more tools.

Sign Up