Hi Bioconductor Developers and Users, I've a question regard dmpFinder method in Minfi package 1.8.9, in particular for shrinkVar argument. I usually calculate dmp both set shrinkVar=TRUE both set shrinkVar=FALSE with the following method calls: 1) dmpOne <- dmpFinder(myMvalue.byMyGenomicRatioSet, pheno=myPhenoData$Sample_Group, type="categorical", shrinkVar=TRUE) 2) dmpTwo <- dmpFinder(myMvalue.byMyGenomicRatioSet, pheno=myPhenoData$Sample_Group, type="categorical") and I've a variable number of significance estimates (qval < 0.05) on the two result objects. In a dataset of 44 samples I've 207020 significance estimates on dmpOne and 207382 on dmpTwo. In a dataset of 13 samples I've 67 significance estimates on dmpOne and 19 significance estimates on dmpTwo. Now in a dataset of 9 samples I've 21 significance estimates on dmpOne and 3102 on dmpTwo. So I was wondering which of the two result objects should I choose? The one with the greatest number of significance estimates? In the manual shrinkVar=TRUE is recommended when sample sizes are small (<10), but sample sizes refers to the number of samples? It is also recommended but not "required". Thanks in advance, Giovanni Laboratory of Preclinical and Translational Research IRCCS - CROB Oncology Referral Center of Basilicata Rionero in Vulture - Italy ***** sessionInfo ***** R version 3.0.1 (2013-05-16) Platform: x86_64-unknown-linux-gnu (64-bit) locale: [1] LC_CTYPE=en_GB.UTF-8 LC_NUMERIC=C LC_TIME=en_GB.UTF-8 [4] LC_COLLATE=en_GB.UTF-8 LC_MONETARY=en_GB.UTF-8 LC_MESSAGES=en_GB.UTF-8 [7] LC_PAPER=C LC_NAME=C LC_ADDRESS=C [10] LC_TELEPHONE=C LC_MEASUREMENT=en_GB.UTF-8 LC_IDENTIFICATION=C attached base packages: [1] parallel stats graphics grDevices utils datasets methods base other attached packages: [1] IMA_3.1.2 [2] dplR_1.5.9 [3] preprocessCore_1.24.0 [4] bioDist_1.34.0 [5] KernSmooth_2.23-12 [6] MASS_7.3-31 [7] limma_3.18.13 [8] WriteXLS_3.5.0 [9] doParallel_1.0.8 [10] lumi_2.14.2 [11] IlluminaHumanMethylation450kanno.ilmn12.hg19_0.2.1 [12] IlluminaHumanMethylation450kmanifest_0.4.0 [13] minfi_1.8.9 [14] bumphunter_1.2.0 [15] locfit_1.5-9.1 [16] iterators_1.0.7 [17] foreach_1.4.2 [18] Biostrings_2.30.1 [19] GenomicRanges_1.14.4 [20] XVector_0.2.0 [21] IRanges_1.20.7 [22] reshape_0.8.5 [23] lattice_0.20-29 [24] Biobase_2.22.0 [25] BiocGenerics_0.8.0 [26] BiocInstaller_1.12.1 loaded via a namespace (and not attached): [1] affy_1.40.0 affyio_1.30.0 annotate_1.40.1 AnnotationDbi_1.24.0 [5] base64_1.1 beanplot_1.1 biomaRt_2.18.0 bitops_1.0-6 [9] BSgenome_1.30.0 codetools_0.2-8 colorspace_1.2-4 DBI_0.2-7 [13] digest_0.6.4 doRNG_1.6 genefilter_1.44.0 GenomicFeatures_1.14.5 [17] gmp_0.5-11 grid_3.0.1 illuminaio_0.4.0 itertools_0.1-3 [21] Matrix_1.1-3 matrixStats_0.8.14 mclust_4.3 methylumi_2.8.0 [25] mgcv_1.7-29 multtest_2.18.0 nleqslv_2.1.1 nlme_3.1-117 [29] nor1mix_1.1-4 pkgmaker_0.20 plyr_1.8.1 RColorBrewer_1.0-5 [33] Rcpp_0.11.1 RCurl_1.95-4.1 registry_0.2 R.methodsS3_1.6.1 [37] rngtools_1.2.4 Rsamtools_1.14.3 RSQLite_0.11.4 rtracklayer_1.22.7 [41] siggenes_1.36.0 splines_3.0.1 stats4_3.0.1 stringr_0.6.2 [45] survival_2.37-7 tools_3.0.1 XML_3.98-1.1 xtable_1.7-3 [49] zlibbioc_1.8.0 ***** End sessionInfo ***** [[alternative HTML version deleted]]