SimOnenu.mix {SharedHT2} | R Documentation |
SimOnenu.mix
generates a single simulated micro-array expression
experiment under the Wishart/mixed Inverse Wishart model. This can be used
to generate a variety of example datasets which violate the assumptions
of the Wishart/Inverse Wishart model. See the documentation for
Simnu.mix
for more details (type ?Simnu.mix).
SimOnenu.mix(nu = NULL, Lambda = NULL, theta = NULL, f1f2 = c(1/4, 1/2), nreps, Ngenes, effect.size)
nu |
The shape parameter for the Inverse Wishart distribution with equal averaged-over-genes group variance. |
Lambda |
The rate parameter matrix, of dimension d by d
where d is the number of experimental groups. |
theta |
Alternatively to specifying nu and Lambda
above, the user can directly specify the model parameters from which
nu and Lambda are computed. Type ?EBfit for more details. |
nreps |
Number of replicates per group. |
Ngenes |
Number of rows (or genes) in the dataset (micro-array experiment) |
effect.size |
A vector of length Ngenes giving the effect size.
Rows with population mean zero (not differentially expressed) are set to zero
while rows with non-zero population mean (differentially expressed) are set to
some non-zero value. For a feeling of corresponding power in the naive F test
of all means identically zero see the documetation on find.ncp by typing
?find.ncp. |
f1f2 |
A vector of length 2 containing strictly increasing values between
0 and 1. These are additional parameters specifying the mixing proportion for
the discrete two component mixture and the proportion of the fractional part
of nu/(2*d+2) specifying the amount by which one of the two shape
parameters should exceed 1. The other shape parameter is derived so that
the averaged-over-genes group variances are equal to their values under the
corresponding Wishart/Inverse Wishart model. |
A dataframe having Ngenes
rows and nreps * d
columns where d
is implicit in the dimension of Lambda, (see above). See the documentation for
SimAffyDat
for more details.
Grant Izmirlian izmirlian@nih.gov
EB.Anova
, EBfit
, SimAffyDat
,
TopGenes
, Simnu.mix
nu <- 9.107182 Lambda <- matrix(c(0.12789434, 0.08468535, 0.08468535, 0.12390469), 2, 2) Ngenes <- 12625 nreps <- 3 nTP <- 100 MyDat <- SimOnenu.mix(nu=nu, Lambda=Lambda, Ngenes=Ngenes, nreps=nreps, effect.size=c(rep(7.5/nreps^{0.5}, nTP), rep(0, Ngenes-nTP))) # notice the names given to the columns by default: names(MyDat) # Now try out 'EB.Anova' on your dataset fit.MyDat <- EB.Anova(data=MyDat, labels= "log2.grp" %,% (1:2), H0="zero.means") # View the sorted genelist TopGenes(fit.MyDat, FDR=0.05, allsig=TRUE)