| Type: | Package |
| Title: | Functions for Conditional Hypergeometric Distributions |
| Version: | 0.3.1 |
| Author: | William Nickols |
| Maintainer: | William Nickols <willnickols@college.harvard.edu> |
| Description: | An implementation of the probability mass function, cumulative density function, quantile function, random number generator, maximum likelihood estimator, and p-value generator from a conditional hypergeometric distribution: the distribution of how many items are in the overlap of all samples when samples of arbitrary size are each taken without replacement from populations of arbitrary size. |
| License: | MIT + file LICENSE |
| Encoding: | UTF-8 |
| RoxygenNote: | 7.1.1 |
| Suggests: | knitr, rmarkdown |
| VignetteBuilder: | knitr |
| NeedsCompilation: | no |
| Packaged: | 2021-08-12 10:23:01 UTC; willn |
| Repository: | CRAN |
| Date/Publication: | 2021-08-13 09:20:05 UTC |
Probability mass function for conditional hypergeometric distributions
Description
Calculates the PMF of a conditional hypergeometric distribution: the distribution of how many items are in the overlap of all samples when samples of arbitrary size are each taken without replacement from populations of arbitrary size.
Usage
dchyper(k, s, n, m, verbose = T)
Arguments
k |
an integer or vector of integers representing the overlap size |
s |
an integer representing the size of the intersecting population |
n |
a vector of integers representing the sizes of each non-intersecting population |
m |
a vector of integers representing the sample sizes |
verbose |
T/F should intermediate messages be printed? |
Value
The probability of sampling k of the same items in all samples
Examples
dchyper(c(3,5), 10, c(12,13,14), c(7,8,9))
Maximum likelihood estimator for sample size in conditional hypergeometric distributions
Description
Calculates the MLE of a sample size in a conditional hypergeometric distribution: the distribution of how many items are in the overlap of all samples when samples of arbitrary size are each taken without replacement from populations of arbitrary size.
Usage
mleM(population, k, s, n, m, verbose = T)
Arguments
population |
the index of the unknown sample size |
k |
the observed overlaps |
s |
an integer representing the size of the intersecting population |
n |
a vector of integers representing the sizes of each non-intersecting population |
m |
a vector of integers representing the sample sizes where the value of the unknown sample size should be any integer as a placeholder |
verbose |
T/F should intermediate messages be printed? |
Value
The maximum likelihood estimator of the unknown sample size
Examples
mleM(1, c(0,0,1,1,0,2,0), 8, c(12,13,14), c(0,8,9))
Maximum likelihood estimator for a unique population size in conditional hypergeometric distributions
Description
Calculates the MLE of a unique population size in a conditional hypergeometric distribution: the distribution of how many items are in the overlap of all samples when samples of arbitrary size are each taken without replacement from populations of arbitrary size.
Usage
mleN(population, k, s, n, m, verbose = T)
Arguments
population |
the index of the unique population to estimate |
k |
the observed overlaps |
s |
an integer representing the size of the intersecting population |
n |
a vector of integers representing the sizes of each non-intersecting population where the value of the unknown population size should be any integer as a placeholder |
m |
a vector of integers representing the sample sizes |
verbose |
T/F should intermediate messages be printed? |
Value
The maximum likelihood estimator of the unknown unique population size
Examples
mleN(1, c(0,0,1,1,0,2,0), 8, c(0,13,14), c(7,8,9))
Maximum likelihood estimator for overlap size in conditional hypergeometric distributions
Description
Calculates the MLE of the overlap size in a conditional hypergeometric distribution: the distribution of how many items are in the overlap of all samples when samples of arbitrary size are each taken without replacement from populations of arbitrary size.
Usage
mleS(k, n, m, verbose = T)
Arguments
k |
the observed overlaps |
n |
a vector of integers representing the sizes of each non-intersecting population |
m |
a vector of integers representing the sample sizes |
verbose |
T/F should intermediate messages be printed? |
Value
The maximum likelihood estimator of the intersecting population size
Examples
mleS(c(0,0,1,1,0,2,0), c(12,13,14), c(7,8,9))
Cumulative density function for conditional hypergeometric distributions
Description
Calculates the CDF of a conditional hypergeometric distribution: the distribution of how many items are in the overlap of all samples when samples of arbitrary size are each taken without replacement from populations of arbitrary size.
Usage
pchyper(k, s, n, m, verbose = T)
Arguments
k |
an integer or vector of integers representing the overlap size |
s |
an integer representing the size of the intersecting population |
n |
a vector of integers representing the sizes of each non-intersecting population |
m |
a vector of integers representing the sample sizes |
verbose |
T/F should intermediate messages be printed? |
Value
The probability of sampling k or less of the same items in all samples
Examples
pchyper(c(3,5), 10, c(12,13,14), c(7,8,9))
P-values from a conditional hypergeometric distribution
Description
Calculates p-values from a conditional hypergeometric distribution: the distribution of how many items are in the overlap of all samples when samples of arbitrary size are each taken without replacement from populations of arbitrary size.
Usage
pvalchyper(k, s, n, m, tail = "upper", verbose = T)
Arguments
k |
an integer or vector of integers representing the overlap size |
s |
an integer representing the size of the intersecting population |
n |
a vector of integers representing the sizes of each non-intersecting population |
m |
a vector of integers representing the sample sizes |
tail |
whether the p-value should be from the upper or lower tail (options: "upper", "lower") |
verbose |
T/F should intermediate messages be printed? |
Value
The probability of getting the k or more (or less if tail="lower") overlaps by chance from the conditional hypergeometric distribution specified by the parameters
Examples
pvalchyper(c(1,2), 8, c(12,13,14), c(7,8,9), "upper")
Quantile function for conditional hypergeometric distributions
Description
Calculates the quantile function of a conditional hypergeometric distribution: the distribution of how many items are in the overlap of all samples when samples of arbitrary size are each taken without replacement from populations of arbitrary size.
Usage
qchyper(p, s, n, m, verbose = T)
Arguments
p |
the desired quantile or quantiles |
s |
an integer representing the size of the intersecting population |
n |
a vector of integers representing the sizes of each non-intersecting population |
m |
a vector of integers representing the sample sizes |
verbose |
T/F should intermediate messages be printed? |
Value
The minimum integer (or integers for a vector input) such that the input probability is less than or equal to the probability of sampling that many of the same items in all samples.
Examples
qchyper(c(0,0.9,1), 10, c(12,13,14), c(7,8,9))
Random number generator for conditional hypergeometric distributions
Description
Generates random numbers from a conditional hypergeometric distribution: the distribution of how many items are in the overlap of all samples when samples of arbitrary size are each taken without replacement from populations of arbitrary size.
Usage
rchyper(size, s, n, m, verbose = T)
Arguments
size |
the number of random numbers to generate |
s |
an integer representing the size of the intersecting population |
n |
a vector of integers representing the sizes of each non-intersecting population |
m |
a vector of integers representing the sample sizes |
verbose |
T/F should intermediate messages be printed? |
Value
A vector of random numbers generated from the PMF of the conditional hypergeometric distribution specified by the parameters
Examples
rchyper(100, 10, c(12,13,14), c(7,8,9))