SI
SI
discoversearch

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor.  We ask that you disable ad blocking while on Silicon Investor in the best interests of our community.  If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.
Politics : GOPwinger Lies/Distortions/Omissions/Perversions of Truth -- Ignore unavailable to you. Want to Upgrade?

To: Kevin Rose who wrote (164896)3/22/2010 1:53:37 PM
From: Bill1 Recommendation  Read Replies (2) | Respond to of 173976
 
You can't take a random selection of 1300 out of a (possibly non-representative) 25,000 and have the results be valid.

Well obviously if the 25,000 is not representative, the results will not be statistically significant. Duh.
But you can certainly take a random sample of 1,300 our of a representative population and get valid results. Stats 101.



To: Kevin Rose who wrote (164896)3/22/2010 2:10:59 PM
From: HPilot  Read Replies (1) | Respond to of 173976
 
Actually a sample of 1,300 out of 25,000 should give some vary valid stats. The main problem is that it is based on only those that turned in the survey. But then all polls have that problem, I have turned down pollsters a couple of times.


HomeMailHotSubjectMarksPeopleMarksKeepersSettings
Terms Of UseContact UsCopyright/IP PolicyPrivacy PolicyAbout UsFAQAdvertise on SI
© 2025 Knight Sac Media.  Data provided by Twelve Data, Alpha Vantage, and CityFALCON News