Title: | Multiple Testing Procedures of Cox (2011) and Wong and Cox (2007) |
---|---|
Description: | Performs the multiple testing procedures of Cox (2011) <doi:10.5170/CERN-2011-006> and Wong and Cox (2007) <doi:10.1080/02664760701240014>. |
Authors: | Christiana Kartsonaki |
Maintainer: | Christiana Kartsonaki <[email protected]> |
License: | GPL-2 |
Version: | 1.2 |
Built: | 2025-02-16 04:30:28 UTC |
Source: | https://github.com/cran/ManyTests |
Performs the multiple testing procedures of Cox (2011) and Wong and Cox (2007).
Package: | ManyTests |
Type: | Package |
Version: | 1.1 |
Date: | 2016-10-30 |
License: | GPL-2 |
Christiana Kartsonaki
Maintainer: Christiana Kartsonaki <[email protected]>
Cox, D. R. (2011). Discovery: a statistical perspective. Phystat Conference CERN. <doi:10.5170/CERN-2011-006>
Cox, D. R. and Wong, M. Y. (2004). A simple procedure for the selection of significant effects. Journal of the Royal Statistical Society B 66 (2), 395–400. <doi:10.1111/j.1369-7412.2004.05695.x>
Wong, M. Y. and Cox, D. R. (2007). On the screening of large numbers of significance tests. Journal of Applied Statistics 34 (7), 779–783. <doi:10.1080/02664760701240014>
t_0
Calculates the FDR which corresponds to a given cut-off t_0
according to the procedure of Wong and Cox (2007).
FDR(test_statistics, t_0)
FDR(test_statistics, t_0)
test_statistics |
A vector of values of test statistics. |
t_0 |
A cut-off value. |
The FDR which corresponds to a given cut-off t_0
.
Christiana Kartsonaki
Cox, D. R. and Wong, M. Y. (2004). A simple procedure for the selection of significant effects. Journal of the Royal Statistical Society B 66 (2), 395–400. <doi:10.1111/j.1369-7412.2004.05695.x>
Wong, M. Y. and Cox, D. R. (2007). On the screening of large numbers of significance tests. Journal of Applied Statistics 34 (7), 779–783. <doi:10.1080/02664760701240014>
x <- c(rnorm(100, 2, 2), rnorm(50, 0, 2)) FDR(x, t_0(x))
x <- c(rnorm(100, 2, 2), rnorm(50, 0, 2)) FDR(x, t_0(x))
Calculates the effective slope of the plot at large values and tests the deviation of the largest value from that line (Cox, 2011).
local_slope(p, k)
local_slope(p, k)
p |
Vector of p-values. |
k |
Number of 'top' |
local_slope |
The estimated local slope of the plot at large values. |
test_statistic |
The value of the test statistic. |
Fvalue |
The upper 5% value of the F distribution with |
pvalue |
The p-value of the test. |
Christiana Kartsonaki
Cox, D. R. (2011). Discovery: a statistical perspective. Phystat Conference CERN. <doi:10.5170/CERN-2011-006>
# generate a vector of p values p <- runif(100, 0, 1) local_slope(p, 10)
# generate a vector of p values p <- runif(100, 0, 1) local_slope(p, 10)
Calculates the expected values of the Renyi decomposition.
ordered_values(n)
ordered_values(n)
n |
Number of values. |
A vector of length n
.
Christiana Kartsonaki
Cox, D. R. (2011). Discovery: a statistical perspective. Phystat Conference CERN. <doi:10.5170/CERN-2011-006>
ordered_values(10)
ordered_values(10)
Plots -log(p)
against the expected values of the Renyi decomposition (Cox, 2011).
plot_pvalues(p)
plot_pvalues(p)
p |
A vector of p-values. |
Christiana Kartsonaki
Cox, D. R. (2011). Discovery: a statistical perspective. Phystat Conference CERN. <doi:10.5170/CERN-2011-006>
# generate a vector of p-values p <- runif(100, 0, 1) plot_pvalues(p)
# generate a vector of p-values p <- runif(100, 0, 1) plot_pvalues(p)
Calculates the cut-off level corresponding to unit Bayes factor according to the procedure of Wong and Cox (2007).
t_0(test_statistics)
t_0(test_statistics)
test_statistics |
A vector of values of test statistics. |
Cut-off level corresponding to unit Bayes factor.
Christiana Kartsonaki
Cox, D. R. and Wong, M. Y. (2004). A simple procedure for the selection of significant effects. Journal of the Royal Statistical Society B 66 (2), 395–400. <doi:10.1111/j.1369-7412.2004.05695.x>
Wong, M. Y. and Cox, D. R. (2007). On the screening of large numbers of significance tests. Journal of Applied Statistics 34 (7), 779–783. <doi:10.1080/02664760701240014>
x <- c(rnorm(100, 2, 2), rnorm(50, 0, 2)) t_0(x)
x <- c(rnorm(100, 2, 2), rnorm(50, 0, 2)) t_0(x)