[R] Sampling
Peter Dalgaard
p.dalgaard at biostat.ku.dk
Wed Feb 6 20:43:41 CET 2008
Tim Hesterberg wrote:
>> values <- sapply(1:1000, function(i) sample(1:3, size=2, prob = c(.5, .25, .25)))
>> table(values)
>>
> values
> 1 2 3
> 834 574 592
>
> The selection probabilities are not proportional to the specified
> probabilities.
>
> In contrast, in S-PLUS:
>
>> values <- sapply(1:1000, function(i) sample(1:3, size=2, prob = c(.5, .25, .25)))
>> table(values)
>>
> 1 2 3
> 1000 501 499
>
>
But is that the right thing? If you can use prob=c(.6, .2, .2) and get
1200 - 400 - 400, then I'm not going to play poker with you....
The interpretation in R is that you are dealing with "fat cards", i.e.
card 1 is twice as thick as the other two, so there is 50% chance of
getting the _first_ card as a 1 and additionally, (.25+.25)*2/3 to get
the 2nd card as a 1 for a total of .8333. And since the two cards are
different the expected number of occurrences of card 1 in 1000 samples
is 833. What is the interpretation in S-PLUS?
--
O__ ---- Peter Dalgaard Øster Farimagsgade 5, Entr.B
c/ /'_ --- Dept. of Biostatistics PO Box 2099, 1014 Cph. K
(*) \(*) -- University of Copenhagen Denmark Ph: (+45) 35327918
~~~~~~~~~~ - (p.dalgaard at biostat.ku.dk) FAX: (+45) 35327907
More information about the R-help
mailing list