hypotesting: Univariate hypothesis testing

hypotestingR Documentation

Univariate hypothesis testing

Description

Univariate hypothesis testing

Usage

hypotesting(
  x,
  test.c = c("ttest", "limma", "wilcoxon", "anova", "kruskal", "pearson", "spearman",
    "limma2ways", "limma2waysInter", "anova2ways", "anova2waysInter")[2],
  factor_names.vc,
  factor_levels.ls = list(factor1Vc = "default", factor2Vc = "default"),
  adjust.c = c("holm", "hochberg", "hommel", "bonferroni", "BH", "BY", "fdr",
    "none")[5],
  adjust_thresh.n = 0.05,
  signif_maxprint.i = NA,
  title.c = NA,
  display_signif.l = FALSE,
  prefix.c = "",
  figure.c = c("none", "interactive", "interactive_plotly", "myfile.pdf")[2],
  report.c = c("none", "interactive", "myfile.txt")[2]
)

## S4 method for signature 'MultiAssayExperiment'
hypotesting(
  x,
  test.c = c("ttest", "limma", "wilcoxon", "anova", "kruskal", "pearson", "spearman",
    "limma2ways", "limma2waysInter", "anova2ways", "anova2waysInter")[2],
  factor_names.vc,
  factor_levels.ls = list(factor1.vc = "default", factor2.vc = "default"),
  adjust.c = c("holm", "hochberg", "hommel", "bonferroni", "BH", "BY", "fdr",
    "none")[5],
  adjust_thresh.n = 0.05,
  signif_maxprint.i = NA,
  title.c = NA,
  display_signif.l = FALSE,
  prefix.c = "",
  figure.c = c("none", "interactive", "interactive_plotly", "myfile.pdf")[2],
  report.c = c("none", "interactive", "myfile.txt")[2]
)

## S4 method for signature 'SummarizedExperiment'
hypotesting(
  x,
  test.c = c("ttest", "limma", "wilcoxon", "anova", "kruskal", "pearson", "spearman",
    "limma2ways", "limma2waysInter", "anova2ways", "anova2waysInter")[2],
  factor_names.vc,
  factor_levels.ls = list(factor1.vc = "default", factor2.vc = "default"),
  adjust.c = c("holm", "hochberg", "hommel", "bonferroni", "BH", "BY", "fdr",
    "none")[5],
  adjust_thresh.n = 0.05,
  signif_maxprint.i = NA,
  title.c = NA,
  display_signif.l = FALSE,
  prefix.c = "",
  figure.c = c("none", "interactive", "interactive_plotly", "myfile.pdf")[2],
  report.c = c("none", "interactive", "myfile.txt")[2]
)

## S4 method for signature 'MultiDataSet'
hypotesting(
  x,
  test.c = c("ttest", "limma", "wilcoxon", "anova", "kruskal", "pearson", "spearman",
    "limma2ways", "limma2waysInter", "anova2ways", "anova2waysInter")[2],
  factor_names.vc,
  factor_levels.ls = list(factor1.vc = "default", factor2.vc = "default"),
  adjust.c = c("holm", "hochberg", "hommel", "bonferroni", "BH", "BY", "fdr",
    "none")[5],
  adjust_thresh.n = 0.05,
  signif_maxprint.i = NA,
  title.c = NA,
  display_signif.l = FALSE,
  prefix.c = "",
  figure.c = c("none", "interactive", "interactive_plotly", "myfile.pdf")[2],
  report.c = c("none", "interactive", "myfile.txt")[2]
)

## S4 method for signature 'ExpressionSet'
hypotesting(
  x,
  test.c = c("ttest", "limma", "wilcoxon", "anova", "kruskal", "pearson", "spearman",
    "limma2ways", "limma2waysInter", "anova2ways", "anova2waysInter")[2],
  factor_names.vc,
  factor_levels.ls = list(factor1.vc = "default", factor2.vc = "default"),
  adjust.c = c("holm", "hochberg", "hommel", "bonferroni", "BH", "BY", "fdr",
    "none")[5],
  adjust_thresh.n = 0.05,
  signif_maxprint.i = NA,
  title.c = NA,
  display_signif.l = FALSE,
  prefix.c = "",
  figure.c = c("none", "interactive", "interactive_plotly", "myfile.pdf")[2],
  report.c = c("none", "interactive", "myfile.txt")[2]
)

Arguments

x

An S4 object of class SummarizedExperiment or MultiAssayExperiment

test.c

Character: One of the 9 available hypothesis tests can be selected (either 'ttest', 'limma', 'wilcoxon', 'anova', 'kruskal', 'pearson', 'spearman', 'limma2ways', 'limma2waysInter', 'anova2ways', 'anova2waysInter')

factor_names.vc

(Vector of) character(s): Factor(s) of interest (up to two), i.e. name(s) of a column from the pData(x)

factor_levels.ls

List: for each factor of interest (up to two), the levels of the factor can be specified (i.e. re-ordered) by including a character vector with those levels in the list; by default (no specification), the two vectors are set to "default".

adjust.c

Character: Name of the method for correction of multiple testing (the p.adjust function is used)

adjust_thresh.n

Numeric: Threshold for (corrected) p-values

signif_maxprint.i

Interger: Maximum number of significant feature to display on the screen (by default, 'NA', all significant features are displayed)

title.c

Character: Title of the graphics

display_signif.l

Character: In case of two sample tests (or correlation test), should individual boxplots (or scatterplots) of significant features be shown?

prefix.c

Character: prefix to be added to the supplementary columns from the variableMetadata to prevent overwriting of pre-existing columns with identical names [default: ""]

figure.c

Character: File name with '.pdf' extension for the figure (for venn diagrams, e.g. in the 'anova2ways' test, the extension will be internally changed to '.tiff' for compatibility with the VennDiagram package); if 'interactive' (default), figures will be displayed interactively; if 'none', no figure will be generated

report.c

Character: File name with '.txt' extension for the printed results (call to sink()'); if 'interactive' (default), messages will be printed on the screen; if 'none', no verbose will be generated

Value

SummarizedExperiment or MultiAssayExperiment including the difference in means/medians or correlations and the adjusted p-values in feature metadata

Examples

sacurine.se <- reading(system.file("extdata/W4M00001_Sacurine-statistics", package = "phenomis"))
sacurine.se <- correcting(sacurine.se, figure.c = 'none')
sacurine.se <- sacurine.se[, colData(sacurine.se)[, "sampleType"] != "pool"]
sacurine.se <- transforming(sacurine.se)
sacurine.se <- sacurine.se[, colnames(sacurine.se) != "HU_neg_096_b2"]
# Student's T test
sacurine.se <- hypotesting(sacurine.se, "ttest", "gender")
# Pearson correlation test
sacurine.se <- hypotesting(sacurine.se, "pearson", "age")
# ANOVA
colData(sacurine.se)[, "ageGroup"] <- vapply(colData(sacurine.se)[, "age"],
                                                 function(x) {
                                                   if (x < 35) {
                                                     return("thirty")
                                                   } else if (x < 50) {
                                                     return("fourty")
                                                   } else {
                                                     return("fifty")}},
                                                 FUN.VALUE = character(1))
sacurine.se <- hypotesting(sacurine.se, "anova", "ageGroup")
prometis.mset <- reading(system.file("extdata/prometis", package="phenomis"))
prometis.mset <- hypotesting(prometis.mset, "limma", "gene")

SciDoPhenIA/phenomis documentation built on June 9, 2022, 11:54 p.m.