[R] comparing real set vs sampled sets

PQuery pierre.khoueiry at embl.de
Wed Jul 31 10:15:38 CEST 2013


Dear R helper,

I have a statistic question. 
I have a vector of 500 values for which I need to assess the statistical
significance of occurrence

real.dist <- realValues

For that, I sampled from my data large data pool 1000 other vectors of 500
values each.

I then run ks.test with my real vec vs each of the sampled vectors.

ks.res<-unlist(lapply(l.sampled,function(x){
  ks <- ks.test(real.dist, x$dist)
  as.numeric(ks[["statistic"]])
}))

I now have 1000 "D" values with their corresponding p.values. How can I have
a general p.value saying that
my real data differs from the sampled one, and thus significant ?

Any suggestion ?
Many thanks,




--
View this message in context: http://r.789695.n4.nabble.com/comparing-real-set-vs-sampled-sets-tp4672709.html
Sent from the R help mailing list archive at Nabble.com.



More information about the R-help mailing list