Hi Guys, I am having a real hard time trying to figure out for microarry. Here is my code One-Sample t-Test dim(data.sub) [1] 10000 140 ##there are 10000 probesets and 140 columns hist(data.sub) ## Histogram. Identify if the probesets are normal distributed q<-rnorm(10000) ##generate 10000 random, normal distributed values qqplot(data.sub,q)) ##Show the plot of the probeset qqline(data.sub,q) ##Show the line going through the plot t.test(data.sub,mu=0) ## One Sample t-test: identify any significant in the probeset When i plot and use histogram, it is showing a nice normal distribution. What i want to do is to use classical paired or one-sample test for each row (10000 rows) what is the best way to do this? thanks, kei -- View this message in context: http://www.nabble.com/paired-or-one-sample-t-Test-tp15824910p15824910.html Sent from the R help mailing list archive at Nabble.com.
Hi Keizer, Look at *"Computing Thousands of Test Statistics Simultaneously in R" *by Holger Schwender and Tina Müller in http://stat-computing.org/newsletter/v181.pdf HTH Jorge On Tue, Mar 4, 2008 at 6:05 AM, Keizer_71 <christophe.lo@gmail.com> wrote:> > Hi Guys, > > I am having a real hard time trying to figure out for microarry. > > Here is my code > > One-Sample t-Test > > dim(data.sub) > [1] 10000 140 ##there are 10000 probesets and 140 columns > > hist(data.sub) ## Histogram. Identify if the probesets are normal > distributed > q<-rnorm(10000) ##generate 10000 random, normal distributed values > qqplot(data.sub,q)) ##Show the plot of the probeset > qqline(data.sub,q) ##Show the line going through the plot > t.test(data.sub,mu=0) ## One Sample t-test: identify any significant in > the > probeset > > When i plot and use histogram, it is showing a nice normal distribution. > > What i want to do is to use classical paired or one-sample test for each > row > (10000 rows) > > what is the best way to do this? > > thanks, > kei > -- > View this message in context: > http://www.nabble.com/paired-or-one-sample-t-Test-tp15824910p15824910.html > Sent from the R help mailing list archive at Nabble.com. > > ______________________________________________ > R-help@r-project.org mailing list > https://stat.ethz.ch/mailman/listinfo/r-help > PLEASE do read the posting guide > http://www.R-project.org/posting-guide.html > and provide commented, minimal, self-contained, reproducible code. >[[alternative HTML version deleted]]
Keizer_71 wrote:> > Hi Guys, > > I am having a real hard time trying to figure out for microarry. > > Here is my code > > One-Sample t-Test > > dim(data.sub) > [1] 10000 140 ##there are 10000 probesets and 140 columns > > Example of the table in excel > > sample_drug sample_control sample_drug > sample_control........etc > 1 .567 .321 .674 > .311 > > hist(data.sub) ## Histogram. Identify if the probesets are normal > distributed > q<-rnorm(10000) ##generate 10000 random, normal distributed values > qqplot(data.sub,q)) ##Show the plot of the probeset > qqline(data.sub,q) ##Show the line going through the plot > t.test(data.sub,mu=0) ## One Sample t-test: identify any significant in > the probeset > > When i plot and use histogram, it is showing a nice normal distribution. > > What i want to do is to use classical paired test for each row > > what is the best way to do this? > > thanks, > kei >-- View this message in context: http://www.nabble.com/paired-or-one-sample-t-Test-tp15824910p15830343.html Sent from the R help mailing list archive at Nabble.com.