thinCounts(x, prob=NULL, target.size=min(colSums(x)))
x
, the expected proportion of the events to keep.NCOL{x}
, the desired total column counts.
Must be not greater than column sum of x
. Ignored if prob
is not NULL
.x
, with thinned counts.prob
is not NULL
, then this function calls rbinom
with size=x
and prob=prob
to generate the new counts.
This is classic binomial thinning.
The new column sums are random, with expected values determined by prob
.
If prob
is NULL
, then this function does multinomial thinning of the counts to achieve specified column totals.
The default behavior is to thin the columns to have the same column sum, equal to the smallest column sum of x
.
If the elements of x
are Poisson, then binomial thinning produces new Poisson random variables with expected values reduced by factor prob
.
If the elements of each column of x
are multinomial, then multinomial thinning produces a new multinomial observation with a reduced sum.x <- rpois(10,lambda=10)
thinCounts(x,prob=0.5)
Run the code above in your browser using DataLab