| Title: | Various Methods for the Two Sample Problem |
|---|---|
| Description: | The routine twosample_test() in this package runs the two sample test using various test statistic. The p values are found via permutation or large sample theory. The routine twosample_power() allows the calculation of the power in various cases, and plot_power() draws the corresponding power graphs. The routine run.studies allows a user to quickly study the power of a new method and how it compares to some of the standard ones. |
| Authors: | Wolfgang Rolke [aut, cre] (ORCID: <https://orcid.org/0000-0002-3514-726X>) |
| Maintainer: | Wolfgang Rolke <[email protected]> |
| License: | GPL (>= 2) |
| Version: | 5.0.0 |
| Built: | 2026-10-06 12:31:33 UTC |
| Source: | https://github.com/cran/R2sample |
This function finds the p values of several tests based on large sample theory
asymptotic_pvalues(x, n, m)asymptotic_pvalues(x, n, m)
x |
a vector of test statistics |
n |
size of sample 1 |
m |
size of sample 2 |
A vector of p values.
This function creates the functions needed to run the various case studies. That means it generates two data sets the are equal with respect to three out of these four: mean, variance, skewness and kurtosis, and differ in the other. If which_diff=mixed, all are different.
case_studies( which, which_diff = "mean", data_type = "cont", n = 500, nbins = 50, funs_list, ReturnCaseNames = FALSE )case_studies( which, which_diff = "mean", data_type = "cont", n = 500, nbins = 50, funs_list, ReturnCaseNames = FALSE )
which |
name of the case study. |
which_diff |
="mean", name of parameter in which data sets differ. |
data_type |
="cont", is data continuous or discrete? |
n |
=500, sample sizes. |
nbins |
=50, number of bins for discrete data |
funs_list |
list of alternative functions |
ReturnCaseNames |
=FALSE, should list of case studies be returned? |
a function that generates data sets
This function runs the chi-square test for continuous or discrete data
chi_power( rxy, alpha = 0.05, B = 1000, xparam, yparam, nbins = c(50, 10), minexpcount = 5, typeTS )chi_power( rxy, alpha = 0.05, B = 1000, xparam, yparam, nbins = c(50, 10), minexpcount = 5, typeTS )
rxy |
a function to generate data |
alpha |
=0.05 type I error probability of test |
B |
=1000 number of simulation runs |
xparam |
vector of parameter values |
yparam |
vector of parameter values |
nbins |
=c(50, 10) number of desired bins |
minexpcount |
=5 smallest number of counts required in each bin |
typeTS |
type of problem, continuous/discrete, with/without weights |
A matrix of power values
function definitions for case studies
funs_listfuns_list
A list of functions
This function runs a test for continuous data
myTS_cont(x, y, TSextra)myTS_cont(x, y, TSextra)
x |
first data set |
y |
second data set |
TSextra |
list with extra info |
a number
This function runs a test for discrete data
myTS_disc(x, y, vals, TSextra)myTS_disc(x, y, vals, TSextra)
x |
counts for first data set |
y |
counts for second data set |
vals |
values of discrete data |
TSextra |
list with extra info |
a number
a local function needed for the vignette
myTS2(x, y, vals)myTS2(x, y, vals)
x |
An integer vector. |
y |
An integer vector. |
vals |
A numeric vector with the values of the discrete rv. |
A vector with test statistics
list of matrices with parameter values for case studies
paramparam
A list of matrices with numbers
This function draws the power graph, with curves sorted by the mean power and smoothed for easier reading.
plot_power(pwr, xname = " ", title = " ", Smooth = TRUE, span = 0.25)plot_power(pwr, xname = " ", title = " ", Smooth = TRUE, span = 0.25)
pwr |
a matrix of power values, usually from the twosample_power command |
xname |
Name of variable on x axis |
title |
(Optional) title of graph |
Smooth |
=TRUE lines are smoothed for easier reading |
span |
=0.25bandwidth of smoothing method |
plt, an object of class ggplot.
This function estimates the power of test routines that calculate p value(s)
power_newtest(TS, f, xparam, yparam, TSextra, alpha = 0.05, B = 1000)power_newtest(TS, f, xparam, yparam, TSextra, alpha = 0.05, B = 1000)
TS |
routine to calculate test statistics. |
f |
routine that generates data. |
xparam |
values of first parameter under the alternative hypothesis. |
yparam |
values of second parameter under the alternative hypothesis. |
TSextra |
list passed to TS. |
alpha |
=0.05 type I error. |
B |
= 1000 number of simulation runs to estimate the power. |
A matrix of power values
the results of the included power studies
power_studypower_study
A list of matrices with powers
Find the power of two sample tests using Rcpp and parallel computing.
powerR( rxy, xparam, yparam, TS, typeTS, TSextra, alpha = 0.05, B = 1000, SuppressMessages, maxProcessor )powerR( rxy, xparam, yparam, TS, typeTS, TSextra, alpha = 0.05, B = 1000, SuppressMessages, maxProcessor )
rxy |
function to generate a list with data sets x, y and (optional) vals, weights |
xparam |
first argument passed to rxy |
yparam |
second argument passed to rxy |
TS |
test statistic |
typeTS |
which format has TS? |
TSextra |
list of items passed TS |
alpha |
=0.05, the level of the hypothesis test |
B |
= 1000 number of simulation runs |
SuppressMessages |
= FALSE print informative messages? |
maxProcessor |
maximum number of cores to use. If maxProcessor=1 no parallel computing is used. |
A numeric vector of power values.
data to draw a graph in vignette
pvaluecdfpvaluecdf
A matrix
Runs the shiny app associated with R2sample package
run_shiny()run_shiny()
No return value, called for side effect of opening a shiny app
This function runs the case studies included in the package and compares the power of a new test to those included.
run.studies( studies = 1:40, types = 1:5, data_type = "cont", TS, TSextra, With.p.value = FALSE, n = 500, alpha = 0.05, B = 1000, SuppressMessages = TRUE )run.studies( studies = 1:40, types = 1:5, data_type = "cont", TS, TSextra, With.p.value = FALSE, n = 500, alpha = 0.05, B = 1000, SuppressMessages = TRUE )
studies |
=1:40, either the names of the studies, or their numbers. If missing all the studies are run. |
types |
=1:5, either the types of studies, or their numbers. If missing all types are run. |
data_type |
="cont", continuous or discrete data |
TS |
routine to calculate test statistics. |
TSextra |
list passed to TS. |
With.p.value |
=FALSE does user supplied routine return p values? |
n |
= 500, desired sample size. |
alpha |
=0.05 type I error |
B |
= 1000 |
SuppressMessages |
= TRUE |
For details consult vignette("R2sample","R2sample")
A matrix of power values.
TSextra=list(nbins=5, statistic=FALSE) # Use 5 bins and calculate p values run.studies(1:2, 1:2, TS=myTS_cont, TSextra=TSextra, With.p.value=TRUE, B=100)TSextra=list(nbins=5, statistic=FALSE) # Use 5 bins and calculate p values run.studies(1:2, 1:2, TS=myTS_cont, TSextra=TSextra, With.p.value=TRUE, B=100)
This function does some rounding to nice numbers
signif_digits(x, d = 4)signif_digits(x, d = 4)
x |
a list of two vectors |
d |
=4 number of digits to round to |
A list with rounded vectors
test function
timecheck(dta, TS, typeTS, TSextra)timecheck(dta, TS, typeTS, TSextra)
dta |
data set |
TS |
test statistics |
typeTS |
format of TS |
TSextra |
additional info TS |
Mean computation time
Find the power of various two sample tests using Rcpp and parallel computing.
twosample_power( f, ..., TS, TSextra, With.p.value = FALSE, alpha = 0.05, B = 1000, nbins = c(50, 10), minexpcount = 5, UseLargeSample, samplingmethod = "Binomial", rnull, SuppressMessages = FALSE, maxProcessor )twosample_power( f, ..., TS, TSextra, With.p.value = FALSE, alpha = 0.05, B = 1000, nbins = c(50, 10), minexpcount = 5, UseLargeSample, samplingmethod = "Binomial", rnull, SuppressMessages = FALSE, maxProcessor )
f |
function to generate a list with data sets x, y and (optional) vals, weights |
... |
additional arguments passed to f, up to 2 |
TS |
routine to calculate test statistics for non-chi-square tests |
TSextra |
additional info passed to TS, if necessary |
With.p.value |
=FALSE does user supplied routine return p values? |
alpha |
=0.05, the level of the hypothesis test |
B |
=1000, number of simulation runs. |
nbins |
=c(50,10), number of bins for chi large and chi small. |
minexpcount |
=5 minimum required count for chi square tests |
UseLargeSample |
should p values be found via large sample theory if n,m>10000? |
samplingmethod |
="Binomial" or independence in discrete data case |
rnull |
a function that generates data from a model, possibly with parameter estimation. |
SuppressMessages |
= FALSE print informative messages? |
maxProcessor |
maximum number of cores to use. If maxProcessor=1 no parallel computing is used. |
For details consult vignette("R2sample","R2sample")
This routine runs a number of different two-sample tests for univariate data, either discrete or continuous. The user can also provide their own test method.
A numeric vector of power values.
# Power of standard normal vs. normal with mean mu. f1=function(mu) list(x=rnorm(25), y=rnorm(25, mu)) #Power of uniform discrete distribution vs. with different probabilities. twosample_power(f1, mu=c(0,2), B=100, maxProcessor = 1) f2=function(n, p) list(x=table(sample(1:5, size=1000, replace=TRUE)), y=table(sample(1:5, size=n, replace=TRUE, prob=c(1, 1, 1, 1, p))), vals=1:5) twosample_power(f2, n=c(1000, 2000), p=c(1, 1.5), B=100, maxProcessor = 1) # Compare power of a new test with those in package: myTS=function(x,y) {z=c(mean(x)-mean(y),sd(x)-sd(y));names(z)=c("M","S");z} cbind(twosample_power(f1, mu=c(0,2), TS=myTS,B=100, maxProcessor = 1), twosample_power(f1, mu=c(0,2), B=100, maxProcessor = 1)) # Power estimation if routine returns a p value, using two parameters for # the alternative f3=function(mu, n) list(x=rnorm(25), y=rnorm(n, mu)) myTS2=function(x, y) {out=ks.test(x,y)$p.value; names(out)="KSp"; out} twosample_power(f3, c(0,1), c(25, 30), TS=myTS2, With.p.value = TRUE, B=100)# Power of standard normal vs. normal with mean mu. f1=function(mu) list(x=rnorm(25), y=rnorm(25, mu)) #Power of uniform discrete distribution vs. with different probabilities. twosample_power(f1, mu=c(0,2), B=100, maxProcessor = 1) f2=function(n, p) list(x=table(sample(1:5, size=1000, replace=TRUE)), y=table(sample(1:5, size=n, replace=TRUE, prob=c(1, 1, 1, 1, p))), vals=1:5) twosample_power(f2, n=c(1000, 2000), p=c(1, 1.5), B=100, maxProcessor = 1) # Compare power of a new test with those in package: myTS=function(x,y) {z=c(mean(x)-mean(y),sd(x)-sd(y));names(z)=c("M","S");z} cbind(twosample_power(f1, mu=c(0,2), TS=myTS,B=100, maxProcessor = 1), twosample_power(f1, mu=c(0,2), B=100, maxProcessor = 1)) # Power estimation if routine returns a p value, using two parameters for # the alternative f3=function(mu, n) list(x=rnorm(25), y=rnorm(n, mu)) myTS2=function(x, y) {out=ks.test(x,y)$p.value; names(out)="KSp"; out} twosample_power(f3, c(0,1), c(25, 30), TS=myTS2, With.p.value = TRUE, B=100)
This function runs a number of two sample tests using Rcpp and parallel computing.
twosample_test( x, y, vals = NA, TS, TSextra, wx = rep(1, length(x)), wy = rep(1, length(y)), B = 5000, nbins = c(50, 10), minexpcount = 5, maxProcessor, UseLargeSample, samplingmethod = "Binomial", rnull, SuppressMessages = FALSE, doMethods = "all" )twosample_test( x, y, vals = NA, TS, TSextra, wx = rep(1, length(x)), wy = rep(1, length(y)), B = 5000, nbins = c(50, 10), minexpcount = 5, maxProcessor, UseLargeSample, samplingmethod = "Binomial", rnull, SuppressMessages = FALSE, doMethods = "all" )
x |
a vector of numbers if data is continuous or of counts if data is discrete or a list with the data |
y |
a vector of numbers if data is continuous or of counts if data is discrete. |
vals |
=NA, a vector of numbers, the values of a discrete random variable. NA if data is continuous data. |
TS |
routine to calculate test statistics for non-chi-square tests |
TSextra |
additional info passed to TS, if necessary |
wx |
A numeric vector of weights of x. |
wy |
A numeric vector of weights of y. |
B |
=5000, number of simulation runs for permutation test |
nbins |
=c(50,10), number of bins for chi square tests. |
minexpcount |
=5, minimum required expected counts for chi-square tests. |
maxProcessor |
maximum number of cores to use. If missing (the default) no parallel processing is used. |
UseLargeSample |
should p values be found via large sample theory if n,m>10000? |
samplingmethod |
="Binomial" or "independence" for discrete data |
rnull |
a function that generates data from a model, possibly with parameter estimation. |
SuppressMessages |
= FALSE print informative messages? |
doMethods |
="all" a vector of codes for the methods to include. If "all", all methods are used. |
For details consult vignette("R2sample","R2sample")
A list of two numeric vectors, the test statistics and the p values.
R2sample::twosample_test(rnorm(1000), rt(1000, 4), B=1000) myTS=function(x,y) {z=c(mean(x)-mean(y),sd(x)-sd(y));names(z)=c("M","S");z} R2sample::twosample_test(rnorm(1000), rt(1000, 4), TS=myTS, B=1000) vals=1:5 x=table(sample(vals, size=100, replace=TRUE)) y=table(sample(vals, size=100, replace=TRUE, prob=c(1,1,3,1,1))) R2sample::twosample_test(x, y, vals)R2sample::twosample_test(rnorm(1000), rt(1000, 4), B=1000) myTS=function(x,y) {z=c(mean(x)-mean(y),sd(x)-sd(y));names(z)=c("M","S");z} R2sample::twosample_test(rnorm(1000), rt(1000, 4), TS=myTS, B=1000) vals=1:5 x=table(sample(vals, size=100, replace=TRUE)) y=table(sample(vals, size=100, replace=TRUE, prob=c(1,1,3,1,1))) R2sample::twosample_test(x, y, vals)
This function runs a number of two sample tests using Rcpp and parallel computing and then finds the correct p value for the combined tests.
twosample_test_adjusted_pvalue( x, y, vals = NA, TS, TSextra, wx = rep(1, length(x)), wy = rep(1, length(y)), B = c(5000, 1000), nbins = c(50, 10), minexpcount = 5, samplingmethod = "independence", rnull, SuppressMessages = FALSE, doMethods )twosample_test_adjusted_pvalue( x, y, vals = NA, TS, TSextra, wx = rep(1, length(x)), wy = rep(1, length(y)), B = c(5000, 1000), nbins = c(50, 10), minexpcount = 5, samplingmethod = "independence", rnull, SuppressMessages = FALSE, doMethods )
x |
a vector of numbers if data is continuous or of counts if data is discrete, or a list with the data. |
y |
a vector of numbers if data is continuous or of counts if data is discrete. |
vals |
=NA, a vector of numbers, the values of a discrete random variable. NA if data is continuous data. |
TS |
routine to calculate test statistics for non-chi-square tests |
TSextra |
additional info passed to TS, if necessary |
wx |
A numeric vector of weights of x. |
wy |
A numeric vector of weights of y. |
B |
=c(5000, 1000), number of simulation runs for permutation test |
nbins |
=c(50,10), number of bins for chi square tests. |
minexpcount |
= 5, minimum required expected counts for chi-square tests |
samplingmethod |
="independence" or "Binomial" for discrete data |
rnull |
routine for parametric bootstrap |
SuppressMessages |
= FALSE print informative messages? |
doMethods |
="all" a vector of codes for the methods to include. If "all", all methods are used. |
For details consult vignette("R2sample","R2sample")
A list of two numeric vectors, the test statistics and the p values.
x=rnorm(100) y=rt(200, 4) R2sample::twosample_test_adjusted_pvalue(x, y, B=c(500, 500)) vals=1:5 x=table(c(1:5, sample(1:5, size=100, replace=TRUE)))-1 y=table(c(1:5, sample(1:5, size=100, replace=TRUE, prob=c(1,1,3,1,1))))-1 R2sample::twosample_test_adjusted_pvalue(x, y, vals, B=c(500, 500))x=rnorm(100) y=rt(200, 4) R2sample::twosample_test_adjusted_pvalue(x, y, B=c(500, 500)) vals=1:5 x=table(c(1:5, sample(1:5, size=100, replace=TRUE)))-1 y=table(c(1:5, sample(1:5, size=100, replace=TRUE, prob=c(1,1,3,1,1))))-1 R2sample::twosample_test_adjusted_pvalue(x, y, vals, B=c(500, 500))