Adjust significance threshold (alpha) according to FDR (Benjamini & Hochberg)` method in R











up vote
3
down vote

favorite












I'm aware about p.adjust function in R and it works well for my needs. However, now i'd like to correct significance threshold (alpha) instead of p-values themselves according to FDR (Benjamini & Hochberg) method.
For instance we have a ten of raw p-values:



0.0001,0.001,0.024,0.56,0.0077,0.55,0.0025,0.01,0.015,1


In case of Bonferroni it's very easy:



alpha_Bonferroni_corrected = 0.01/ number of tests (10 in our example)=0.001


But for FDR it will be a more tricky. Is there function in R for that?










share|improve this question


























    up vote
    3
    down vote

    favorite












    I'm aware about p.adjust function in R and it works well for my needs. However, now i'd like to correct significance threshold (alpha) instead of p-values themselves according to FDR (Benjamini & Hochberg) method.
    For instance we have a ten of raw p-values:



    0.0001,0.001,0.024,0.56,0.0077,0.55,0.0025,0.01,0.015,1


    In case of Bonferroni it's very easy:



    alpha_Bonferroni_corrected = 0.01/ number of tests (10 in our example)=0.001


    But for FDR it will be a more tricky. Is there function in R for that?










    share|improve this question
























      up vote
      3
      down vote

      favorite









      up vote
      3
      down vote

      favorite











      I'm aware about p.adjust function in R and it works well for my needs. However, now i'd like to correct significance threshold (alpha) instead of p-values themselves according to FDR (Benjamini & Hochberg) method.
      For instance we have a ten of raw p-values:



      0.0001,0.001,0.024,0.56,0.0077,0.55,0.0025,0.01,0.015,1


      In case of Bonferroni it's very easy:



      alpha_Bonferroni_corrected = 0.01/ number of tests (10 in our example)=0.001


      But for FDR it will be a more tricky. Is there function in R for that?










      share|improve this question













      I'm aware about p.adjust function in R and it works well for my needs. However, now i'd like to correct significance threshold (alpha) instead of p-values themselves according to FDR (Benjamini & Hochberg) method.
      For instance we have a ten of raw p-values:



      0.0001,0.001,0.024,0.56,0.0077,0.55,0.0025,0.01,0.015,1


      In case of Bonferroni it's very easy:



      alpha_Bonferroni_corrected = 0.01/ number of tests (10 in our example)=0.001


      But for FDR it will be a more tricky. Is there function in R for that?







      r






      share|improve this question













      share|improve this question











      share|improve this question




      share|improve this question










      asked Nov 10 at 22:17









      Denis

      7210




      7210
























          1 Answer
          1






          active

          oldest

          votes

















          up vote
          1
          down vote













          mutoss package seems to offer greater flexibility



           library(mutoss)
          alpha <- 0.01
          set.seed(1234)
          p <-c(runif(10, min=0, max=0.01), runif(10, min=0.9, max=1))
          result <- adaptiveBH(p, alpha)
          result





          share|improve this answer





















          • Thanks for your reply. Unfortunately i was not able to install mutoss. Error: package or namespace load failed for ‘mutoss’ in loadNamespace(j <- i[[1L]], c(lib.loc, .libPaths()), versionCheck = vI[[j]]): there is no package called ‘multtest’. I tried: install.packages('multtest') and got: package ‘multtest’ is not available (for R version 3.4.0)
            – Denis
            Nov 11 at 10:59








          • 1




            Try this if (!requireNamespace("BiocManager", quietly = TRUE)) install.packages("BiocManager") BiocManager::install("multtest", version = "3.8"). bioconductor.org/packages/release/bioc/html/multtest.html
            – paoloeusebi
            Nov 11 at 11:38












          • Now i got it, thanks! But there is no ``FDR` corrected alpha in the result although. While it's probably to some extent easy to find the corrected alpha from the adaptiveBH R function output in comparison to p.adjust indeed. In the mentioned above your example adjusted alpha=(1/20)*0.01, but in case of multiple significant p-values it would not be clear.
            – Denis
            Nov 11 at 16:48











          Your Answer






          StackExchange.ifUsing("editor", function () {
          StackExchange.using("externalEditor", function () {
          StackExchange.using("snippets", function () {
          StackExchange.snippets.init();
          });
          });
          }, "code-snippets");

          StackExchange.ready(function() {
          var channelOptions = {
          tags: "".split(" "),
          id: "1"
          };
          initTagRenderer("".split(" "), "".split(" "), channelOptions);

          StackExchange.using("externalEditor", function() {
          // Have to fire editor after snippets, if snippets enabled
          if (StackExchange.settings.snippets.snippetsEnabled) {
          StackExchange.using("snippets", function() {
          createEditor();
          });
          }
          else {
          createEditor();
          }
          });

          function createEditor() {
          StackExchange.prepareEditor({
          heartbeatType: 'answer',
          convertImagesToLinks: true,
          noModals: true,
          showLowRepImageUploadWarning: true,
          reputationToPostImages: 10,
          bindNavPrevention: true,
          postfix: "",
          imageUploader: {
          brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
          contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
          allowUrls: true
          },
          onDemand: true,
          discardSelector: ".discard-answer"
          ,immediatelyShowMarkdownHelp:true
          });


          }
          });














           

          draft saved


          draft discarded


















          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53243979%2fadjust-significance-threshold-alpha-according-to-fdr-benjamini-hochberg-m%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown

























          1 Answer
          1






          active

          oldest

          votes








          1 Answer
          1






          active

          oldest

          votes









          active

          oldest

          votes






          active

          oldest

          votes








          up vote
          1
          down vote













          mutoss package seems to offer greater flexibility



           library(mutoss)
          alpha <- 0.01
          set.seed(1234)
          p <-c(runif(10, min=0, max=0.01), runif(10, min=0.9, max=1))
          result <- adaptiveBH(p, alpha)
          result





          share|improve this answer





















          • Thanks for your reply. Unfortunately i was not able to install mutoss. Error: package or namespace load failed for ‘mutoss’ in loadNamespace(j <- i[[1L]], c(lib.loc, .libPaths()), versionCheck = vI[[j]]): there is no package called ‘multtest’. I tried: install.packages('multtest') and got: package ‘multtest’ is not available (for R version 3.4.0)
            – Denis
            Nov 11 at 10:59








          • 1




            Try this if (!requireNamespace("BiocManager", quietly = TRUE)) install.packages("BiocManager") BiocManager::install("multtest", version = "3.8"). bioconductor.org/packages/release/bioc/html/multtest.html
            – paoloeusebi
            Nov 11 at 11:38












          • Now i got it, thanks! But there is no ``FDR` corrected alpha in the result although. While it's probably to some extent easy to find the corrected alpha from the adaptiveBH R function output in comparison to p.adjust indeed. In the mentioned above your example adjusted alpha=(1/20)*0.01, but in case of multiple significant p-values it would not be clear.
            – Denis
            Nov 11 at 16:48















          up vote
          1
          down vote













          mutoss package seems to offer greater flexibility



           library(mutoss)
          alpha <- 0.01
          set.seed(1234)
          p <-c(runif(10, min=0, max=0.01), runif(10, min=0.9, max=1))
          result <- adaptiveBH(p, alpha)
          result





          share|improve this answer





















          • Thanks for your reply. Unfortunately i was not able to install mutoss. Error: package or namespace load failed for ‘mutoss’ in loadNamespace(j <- i[[1L]], c(lib.loc, .libPaths()), versionCheck = vI[[j]]): there is no package called ‘multtest’. I tried: install.packages('multtest') and got: package ‘multtest’ is not available (for R version 3.4.0)
            – Denis
            Nov 11 at 10:59








          • 1




            Try this if (!requireNamespace("BiocManager", quietly = TRUE)) install.packages("BiocManager") BiocManager::install("multtest", version = "3.8"). bioconductor.org/packages/release/bioc/html/multtest.html
            – paoloeusebi
            Nov 11 at 11:38












          • Now i got it, thanks! But there is no ``FDR` corrected alpha in the result although. While it's probably to some extent easy to find the corrected alpha from the adaptiveBH R function output in comparison to p.adjust indeed. In the mentioned above your example adjusted alpha=(1/20)*0.01, but in case of multiple significant p-values it would not be clear.
            – Denis
            Nov 11 at 16:48













          up vote
          1
          down vote










          up vote
          1
          down vote









          mutoss package seems to offer greater flexibility



           library(mutoss)
          alpha <- 0.01
          set.seed(1234)
          p <-c(runif(10, min=0, max=0.01), runif(10, min=0.9, max=1))
          result <- adaptiveBH(p, alpha)
          result





          share|improve this answer












          mutoss package seems to offer greater flexibility



           library(mutoss)
          alpha <- 0.01
          set.seed(1234)
          p <-c(runif(10, min=0, max=0.01), runif(10, min=0.9, max=1))
          result <- adaptiveBH(p, alpha)
          result






          share|improve this answer












          share|improve this answer



          share|improve this answer










          answered Nov 11 at 9:06









          paoloeusebi

          528211




          528211












          • Thanks for your reply. Unfortunately i was not able to install mutoss. Error: package or namespace load failed for ‘mutoss’ in loadNamespace(j <- i[[1L]], c(lib.loc, .libPaths()), versionCheck = vI[[j]]): there is no package called ‘multtest’. I tried: install.packages('multtest') and got: package ‘multtest’ is not available (for R version 3.4.0)
            – Denis
            Nov 11 at 10:59








          • 1




            Try this if (!requireNamespace("BiocManager", quietly = TRUE)) install.packages("BiocManager") BiocManager::install("multtest", version = "3.8"). bioconductor.org/packages/release/bioc/html/multtest.html
            – paoloeusebi
            Nov 11 at 11:38












          • Now i got it, thanks! But there is no ``FDR` corrected alpha in the result although. While it's probably to some extent easy to find the corrected alpha from the adaptiveBH R function output in comparison to p.adjust indeed. In the mentioned above your example adjusted alpha=(1/20)*0.01, but in case of multiple significant p-values it would not be clear.
            – Denis
            Nov 11 at 16:48


















          • Thanks for your reply. Unfortunately i was not able to install mutoss. Error: package or namespace load failed for ‘mutoss’ in loadNamespace(j <- i[[1L]], c(lib.loc, .libPaths()), versionCheck = vI[[j]]): there is no package called ‘multtest’. I tried: install.packages('multtest') and got: package ‘multtest’ is not available (for R version 3.4.0)
            – Denis
            Nov 11 at 10:59








          • 1




            Try this if (!requireNamespace("BiocManager", quietly = TRUE)) install.packages("BiocManager") BiocManager::install("multtest", version = "3.8"). bioconductor.org/packages/release/bioc/html/multtest.html
            – paoloeusebi
            Nov 11 at 11:38












          • Now i got it, thanks! But there is no ``FDR` corrected alpha in the result although. While it's probably to some extent easy to find the corrected alpha from the adaptiveBH R function output in comparison to p.adjust indeed. In the mentioned above your example adjusted alpha=(1/20)*0.01, but in case of multiple significant p-values it would not be clear.
            – Denis
            Nov 11 at 16:48
















          Thanks for your reply. Unfortunately i was not able to install mutoss. Error: package or namespace load failed for ‘mutoss’ in loadNamespace(j <- i[[1L]], c(lib.loc, .libPaths()), versionCheck = vI[[j]]): there is no package called ‘multtest’. I tried: install.packages('multtest') and got: package ‘multtest’ is not available (for R version 3.4.0)
          – Denis
          Nov 11 at 10:59






          Thanks for your reply. Unfortunately i was not able to install mutoss. Error: package or namespace load failed for ‘mutoss’ in loadNamespace(j <- i[[1L]], c(lib.loc, .libPaths()), versionCheck = vI[[j]]): there is no package called ‘multtest’. I tried: install.packages('multtest') and got: package ‘multtest’ is not available (for R version 3.4.0)
          – Denis
          Nov 11 at 10:59






          1




          1




          Try this if (!requireNamespace("BiocManager", quietly = TRUE)) install.packages("BiocManager") BiocManager::install("multtest", version = "3.8"). bioconductor.org/packages/release/bioc/html/multtest.html
          – paoloeusebi
          Nov 11 at 11:38






          Try this if (!requireNamespace("BiocManager", quietly = TRUE)) install.packages("BiocManager") BiocManager::install("multtest", version = "3.8"). bioconductor.org/packages/release/bioc/html/multtest.html
          – paoloeusebi
          Nov 11 at 11:38














          Now i got it, thanks! But there is no ``FDR` corrected alpha in the result although. While it's probably to some extent easy to find the corrected alpha from the adaptiveBH R function output in comparison to p.adjust indeed. In the mentioned above your example adjusted alpha=(1/20)*0.01, but in case of multiple significant p-values it would not be clear.
          – Denis
          Nov 11 at 16:48




          Now i got it, thanks! But there is no ``FDR` corrected alpha in the result although. While it's probably to some extent easy to find the corrected alpha from the adaptiveBH R function output in comparison to p.adjust indeed. In the mentioned above your example adjusted alpha=(1/20)*0.01, but in case of multiple significant p-values it would not be clear.
          – Denis
          Nov 11 at 16:48


















           

          draft saved


          draft discarded



















































           


          draft saved


          draft discarded














          StackExchange.ready(
          function () {
          StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53243979%2fadjust-significance-threshold-alpha-according-to-fdr-benjamini-hochberg-m%23new-answer', 'question_page');
          }
          );

          Post as a guest















          Required, but never shown





















































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown

































          Required, but never shown














          Required, but never shown












          Required, but never shown







          Required, but never shown







          Popular posts from this blog

          Full-time equivalent

          さくらももこ

          13 indicted, 8 arrested in Calif. drug cartel investigation