similar to: FW: FDR analyses: minimum number of features

Dear List, We are planning a genotyping study to be analyzed using false discovery rates (FDRs) (See Storey and Tibshirani PNAS 2003; 100:9440-5). I am interested in learning if there is any consensus as to how many features (ie. how many P values) need to be studied before reasonably reliable FDRs can be derived. Does anyone know of a citation where this is discussed? Bill Dupont William D.

I am posting this to both R and BioC communities because I believe there is a lot of confusion on this topic in both communities (having searched the mail archives of both) and I am hoping that someone will have information that can be shared with both communities. I have seen countless questions on the BioC list regarding limma (Bioconductor) and its calculation of FDR. Some of them involved

I am posting this to both R and BioC communities because I believe there is a lot of confusion on this topic in both communities (having searched the mail archives of both) and I am hoping that someone will have information that can be shared with both communities. I have seen countless questions on the BioC list regarding limma (Bioconductor) and its calculation of FDR. Some of them involved

Hello, I've a question about the fdr method in p.adjust: What is the threshold of the FDR, and is it possible to change this threshold? As I understand the FDR (please correct) it adjusts the p-values so that for less than N% (say the cutoff is 25%) of the alternative hypothesis the Null is in fact true. thanks a lot for help, +regards, Arne

Dear friends - a couple of papers in PNAS (lastly:framework for making better predictions by directly estimating variables' predictivity, Lo et al PNAS 2016; 113:14277-14282) have focused interest on mapping complex traits to multiple loci spread all over the genome. I have been around on the relevant taskview(s) I hope but fail to see that the backward haplotype transmission association

Dear R users, I am wondering about the following results: > p.adjust(c(0.05,0.05,0.05),"fdr") [1] 0.05 0.05 0.05 > p.adjust(c(0.05,0.04,0.03),"fdr") [1] 0.05 0.05 0.05 Why does p.adjust(..., "fdr") not adjust p-values, if they are constant? Does somebody have an explanation or can point to a reference? Thanks in advance, Will

Hello, Also, I’ve noticed that FDR mode doesn’t flush to a log unless programmatically configured to do so unlike basic mode, which flushes by default. Would it be possible to add this feature as well? Thanks, Henry -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://lists.llvm.org/pipermail/llvm-dev/attachments/20180611/295c3dba/attachment.html>

Hello, I am not sure about the p.adjust( , fdr). How do these adjusted p-values get? I have read papers of BH method. For independent case, we compare the ordered p-values with the alfa*i/m, where m is the number of tests. But I have checked that result based on the adjusted p-values is different with that by using the independent case method. Then how do the result of p.adjust( , fdr) come? And

Mark, there is a fdr website link via Yoav Benjamini's homepage which is: http://www.math.tau.ac.il/%7Eroee/index.htm On it you can download an S-Plus function (under the downloads link) which calculates the false discovery rate threshold alpha level using stepup, stepdown, dependence methods etc. Some changes are required to the plotting code when porting it to R. I removed the

Hello all, I am doing SAM and the median of positive genes in the permutated sets is = false positives, and the "parent set" gives true positives. FDR = FP/TP * 100. My FDR comes to greater than 100. Is that possible? Please help! Thanks, -D. [[alternative HTML version deleted]]

Hi all, In Tibshirani's PNAS paper about nearest shrunken centroid analysis of microarrays (PNAS vol 99:6567), they used cross validation to choose the amount of shrinkage used in the model, and then test the performance of the model with the cross-validated shrinkage in separate independent testing set. If I don't have the luxury of having independent testing set, can I just use the

Dear list, I have performed several tests for the hypergeometric distribution using phyper() for some gene annotation categories as follows >phyper(26,830,31042,337, lower.tail=F) >phyper(16,387,31042,337, lower.tail=F) . . . I am only running some selected categories but I would like to correct this value for multiple testing since I have 3121 possible tests according to 3121

Full_Name: Kevin Coombes Version: 2.4.0 OS: Windows XP Submission from: (NULL) (143.111.22.24) I'm running R 2.4.0 on a Windows XP machine, with only the default packages loaded. Running Sweave or Stangle on the following Rnw file: -------------- % bug.Rnw \begin{document} Demonstrate an Sweave/Stangle bug. <<info>>= sessionInfo() @ <<getFDR>>= x <- 1 @

Hi llvm-dev, I've recently been working on improving the profiling mode for XRay in compiler-rt [0] and am ramping up efforts to do the same for flight-data recorder mode. The changes are generally in the direction of reducing the overheads (measured through benchmarks in the test-suite) and addressing some feature requests/bugs. In the interest of addressing these changes in a timely

You asked the same question on the Bioconductor mailing list back in August. At that time, you suggested yourself a solution for how the adjusted p-values should be interpreted. I answered your query and told you that your interpretation was correct. So I'm not sure what more can be said, except that you should read the article Wright (1992), which is cited in the help entry for p.adjust(),

Dear All, In Storey's estimator of the proportion of true nulls, the estimator depends on the tuning parameter lamda. Suppose now that an estimator of this proportion has been obtained by the qvalue package, what is the lamda that corresponds to the estimate? How to get this lamda? Thanks, -Chee [[alternative HTML version deleted]]

Hola a todos, Tengo un pequeño problemilla... Tengo unas 9000 variables que he contrastado con 1 en concreto con el test de wilcoxon. He calculado el p-valor, y queria corregirlo con el permutation-based FDR. He encontrado una funcion con R comp.fdr()que hace esta corrección, pero te pide que le pongas las variables con las observaciones y te hace el test (según he entendido). Yo solo quiero

I am using Efron's local fdr procedure. But, I want to change the null from N(0,1) to N(0, 0.002). I can access the function but I have no idea what to change. In other words, I want nulltype to be N(0,0.002) instead of N(0,1) in his function. Anyone has any ideas. This is his code for the local fdr: function (zz, bre = 120, df = 7, pct = 0, pct0 = 1/4, nulltype = 1, type = 0, plot = 1,

Hi, I have tried some time trying to figure out how to use pamr to plot multiclass Estimated probabilities for the training data and test data? Specifically, how to recreate the PAMR publication on PNAS with Tibshrani et al. The publication is as attached. The plot I want to do is Figure 5. I have downloaded the pamr package and the function which gives similar plot is pamr.plotcvprob

Hello, I am initializing FDR mode and finalizing/flushing the buffers manually. XRay does not log calls from the main thread unless there is a function call after __xray_log_finalize(). This behavior is abnormal since one would expect the trace file to contain all function calls made up to the point when __xray_log_finalize() is called. To demonstrate this behavior, I have taken the test case