[Tutor] FYI: An Introduction to Interactive Programming in Python

Prasad, Ramit ramit.prasad at jpmorgan.com
Tue Apr 9 22:58:49 CEST 2013


Alan Gauld wrote:
> 
> On 09/04/13 13:47, Steven D'Aprano wrote:
> 
> >> Since when did 30 become a representative sample size?
> >
> > If they are randomly selected, 30 is likely plenty for a representative
> > sample size. In surveys, a sample size of 30 gives you a margin of error
> > of about 15%, which isn't too bad.
> 
> Hmm, if I'd gone to my manager (and especially the finance director)
> with a project proposal based on assumptions with a 15% margin they'd
> have thrown me out. And if I told them I'd developed 5 key assumptions
> based on that same proposal I'd probably have been fired! I'd be looking
> for something like 300+ samples for a project like this to claim that my
> 5 key principles were valid. And its not like there is a shortage of
> computer scientists to ask (although admittedly harder to find ones with
> no formal computer training)!

Well, 15% error margin is from statistics and provable, but the layman
usually hears "30 people" and thinks "that's far too small". I certainly
did it too. :) 

Error margins are one of those surprising things like the Birthday 
Problem (at least to me). Seems like it should not be true but it is.
http://en.wikipedia.org/wiki/Birthday_problem

Honestly, with surveys the method of the survey itself makes a 
difference. This includes things like question wording, question
order, and even survey format (free form, multiple choice, etc).

Much like scientific studies, I am more interested in *how* it
was done than in some summarized (frequently sensationalized)
"findings". In my opinion, a flawed methodology is more 
frequently a problem than a small sample size. 

> 
> > 1) it is likely to be a biased selection
> 
> My suspicion is they just asked around their local department!
> But maybe I'm just overly suspicious... 

Overly suspicious or concerned based on experience? :)


~Ramit


This email is confidential and subject to important disclaimers and
conditions including on offers for the purchase or sale of
securities, accuracy and completeness of information, viruses,
confidentiality, legal privilege, and legal entity disclaimers,
available at http://www.jpmorgan.com/pages/disclosures/email.  


More information about the Tutor mailing list