`library(alpha-correction-bh)`

This package provides functions for calculating alpha corrections for
a list of p-values according to the *Benjamini-Hochberg* alpha
correction.

Reference: Benjamini, Y., & Hochberg, Y. (1995). Controlling the false discovery rate: a practical and powerful approach to multiple testing. Journal of the Royal Statistical Society: series B (Methodological), 57(1), 289-300.

For a sorted list containing *m* p-values indexed from
*1* to *m*, the alpha for each p-value *p* is
computed as:

` alpha(i) = (p_value(i)/m)Q`

where:

*i*is the index of the p-value in list*l*(1 to m),*p_value(i)*is the p_value at index i, and- Q is the false discovery rate, which is 0.05 by default.

Install the package using dev-tools directly from github or from cran.

`devtools::install_github('pcla-code/alpha.correction.bh')`

This library uses *knitr* to render tables.

Import the package:

`library(alpha-correction-bh)`

`library(knitr)`

And call the get_alphas_bh function, passing your p_values and, optionally, Q:

`get_alphas_bh(p_values, Q)`

Use this function to calculate corrected values for a list of p-values and a given false discovery rate Q.

If you do not provide Q, a default value of 0.05 will be used.

You can customize the output of the function using the following two options:

`output`

- valid values are:*print*- print the data frame to the console only*data_frame*- return the data frame only*both*- print the data frame to the console and return it. This is the default behavior.

`include_is_significant_column`

- valid values are:*TRUE*- The*is significant?*column is included. This is the default behavior.*FALSE*- The*is significant?*column is not included.

`get_alphas_bh(list(0.08,0.01,0.039))`

Output:

p-value | alpha | is significant? |
---|---|---|

0.08 | 0.05 | NO |

0.01 | 0.017 | YES |

0.039 | 0.033 | NO |

`get_alphas_bh(list(0.08,0.01,0.039), .07)`

Output:

p-value | alpha | is significant? |
---|---|---|

0.08 | 0.07 | NO |

0.01 | 0.023 | YES |

0.039 | 0.047 | YES |

To read the documentation of the function, execute the following in R:

`?get_alphas_bh`

You can also read the vignette here.