![]() These can be done together with the mt.() function. We might want to compute the numerators and denominators of the test statistics. They definitely correspond to genes whose expression levels differ between the ALL and AML groups They could correspond to genes whose expression levels differ between the ALL and AML groupsī. Question 1 (Multiple Choice) What can we say about those points on the plot that look like outliers?Ī. Plt = ggplot(ame(teststat), aes(sample = teststat)) + stat_qq() + theme_bw() The default test is the two-sample Welch t-test. This can be done with the mt.teststat function. Let's compute two-sample t-statistics that compares the gene expressions for each gene in the ALL and AML cases. The mt.teststat and mt. functions provide a convenient way to compute test statistics for each row of a data frame, e.g., two-sample Welch t-statistics, Wilcoxon statistics, F-statistics, paired t-statistics, and block F-statistics. There are also gene identifiers and tumor class labels (0 for ALL, 1 for AML). Note that each column is a sample, and golub is the expression level for gene j in tumor mRNA sample i. We'll illustrate some of the functionality of multtest with gene expression data from the leukemia ALL/AML study of Golub et al. Make sure you answer them on the OHMS page. The questions on the OHMS page are in the middle of this webpage marked as Question X. We will follow the manuals found on the Bioconductor site. This lab is about doing multiple testing in R, using the package multtest. Achieving two significant results is much more demanding, not least because of the Bonferroni correction: having both treatments turn up significant 80% of the time would require 3000 subjects.Lab 8: Multiple testing in R Lab 8: Multiple testing in R The results of this simulation are graphed below: with 800 or so subjects equally allocated between the three treatments, this experiment is about 80% likely to recover at least one significant result. Points(possible.ns, power.fullranking, col="blue") Points(possible.ns, power.bothtreatments, col="red") Plot(possible.ns, power.atleastone, ylim=c(0,1)) ![]() This operation can be done with an analytically derived formula, but this simulation will provide the basis for more complicated designs. ![]() We then vary the total number of subjects to see how power will vary with sample size. We have to make assumptions about the size of the treatment effect and the standard deviation of the outcome variable. The standard design randomly assigns subjects to either treatment or control with probability 0.5. Please check out EGAP’s 10 Things You Need To Know About Statistical Power for some intuition and guidance when using this code. This page gives code in R for some basic and some more complicated power analyses. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |