The wine you taste will always have a different taste depending on what you
drink just before you taste.
You can take some drink like lemon and always the same taste and clean your
mouth with a lot of water between drinks and you have a better chance of
recognizing your wines.
2008/8/30 Devon McCormick <[EMAIL PROTECTED]>
> Members of the Forum -
>
> I had a blind-tasting last night where we sampled five different wines.
> After two rounds of tasting the wines in the same order, we had a round
> where we sampled them in a random, unknown order. Afterwards, we tried to
> guess which wines from the random order corresponded to their original
> numbering. On average, we were able to do this only once each.
>
> Not knowing how this shakes out by chance, I did the following to simulate
> comparing pairs of random permutations of five items to see how our results
> compared to random selection.
>
> ?~5 NB. 5-permutation
> 0 4 3 1 2
> $rs=. ?~2 1000$5 NB. 1000 pairs of 5-permutations
> 2 1000 5
> 0{=/rs NB. Look at the first comparison
> 1 0 0 0 0
> 0{"2 rs NB. and permutation pair.
> 1 0 4 3 2
> 1 3 2 0 4
> +/,=/rs NB. How many total matches?
> 992 NB. Average of 1.
>
> So, our ability to recognize the wines we'd just tasted twice is no better
> than random. It occurred to us that perhaps five is too many to distinguish
> and maybe we should taste only two at a time if we do this again.
>
> So, what would be the random match if we did this with only two wines?
>
> +/,=/?~2 1000$2
> 986
>
> Huh? It's the same: about one on average. Try this for other permutation
> lengths....
>
> +/,=/?~2 1000$3
> 992
> +/,=/?~2 1000$10
> 982
>
> Try larger sample size too.
>
> +/,=/?~2 10000$5
> 9886
> +/,=/?~2 10000$10
> 10185
> +/,=/?~2 10000$20
> 10058
> +/,=/?~2 10000$100
> 10049
>
> No matter what size the permutation, the average chance of a match is about
> one. This seems counter-intuitive to me. Am I doing something wrong in my J
> code or is this one of those well-known theorems of statistics about which
> I'm completely ignorant?
>
> You decide.
>
> Regards,
>
> Devon McCormick
> ^me^ at acm.
> org is my
> preferred e-mail
> ----------------------------------------------------------------------
> For information about J forums see http://www.jsoftware.com/forums.htm
>
--
Björn Helgason, Verkfræðingur
Fugl&Fiskur ehf,
Þerneyjarsundi 23, Hraunborgum
Po Box 127,801 Selfoss ,
t-póst: [EMAIL PROTECTED]
gsm: +3546985532
Landslags og skrúðgarðagerð, gröfuþjónusta
http://groups.google.com/group/J-Programming
Tæknikunnátta höndlar hið flókna, sköpunargáfa er meistari einfaldleikans
góður kennari getur stigið á tær án þess að glansinn fari af skónum
/|_ .-----------------------------------.
,' .\ / | Með léttri lund verður |
,--' _,' | Dagurinn í dag |
/ / | Enn betri en gærdagurinn |
( -. | `-----------------------------------'
| ) | (\_ _/)
(`-. '--.) (='.'=)
`. )----' (")_(")
----------------------------------------------------------------------
For information about J forums see http://www.jsoftware.com/forums.htm
