The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.
library(SBICgraph)
#>
#> Attaching package: 'SBICgraph'
#> The following object is masked from 'package:stats':
#>
#> simulate
library(network) # for visualization
#> network: Classes for Relational Data
#> Version 1.16.1 created on 2020-10-06.
#> copyright (c) 2005, Carter T. Butts, University of California-Irvine
#> Mark S. Handcock, University of California -- Los Angeles
#> David R. Hunter, Penn State University
#> Martina Morris, University of Washington
#> Skye Bender-deMoll, University of Washington
#> For citation information, type citation("network").
#> Type help("network-package") to get started.
# to reset par
<- function() {
resetPar dev.new()
<- par(no.readonly = TRUE)
op dev.off()
op }
The function comparison
allows for comparison between the true network and the estimated network from the SBIC method.
First we create a simulated data set using the embedded simulate
function within SBIC. The function simulate
generates a data frame, a real network adjacency matrix and a prior network adjacency matrix.
<- 200
p <- 100
m1 <- 30
m2 <- simulate(n=100, p=p, m1=m1, m2=m2)
d <- d$data
data<- d$realnetwork
real<- d$priornetwork priori
We can visualize the networks
<- network(priori)
prior_net <- network(real)
real_net par(mfrow = c(1,2))
plot(prior_net, main = "Prior network")
plot(real_net, main = "Real network")
par(resetPar())
We examine some features of both the prior network and the real network
sum(priori[lower.tri(priori)])
#> [1] 100
sum(priori[lower.tri(priori)])/(p*(p-1)/2)
#> [1] 0.005025126
sum(real[lower.tri(real)])
#> [1] 100
sum(real[lower.tri(real)])/(p*(p-1)/2)
#> [1] 0.005025126
Then we can fit SBIC using one function
<- exp(seq(-10,10, length=30))
lambda# calculating the error rate from the number of edges in the true graph and the number of discordant pairs
<- m2/m1
r1 <-m2/(p*(p-1)/2-m1)
r2 <- (r1+r2)/2
r <- sggm(data = data, lambda = lambda, M=priori, prob = r) model
Comparing the estimated network to the true and prior network. Our comparison function above calcualtes the Positive selection rate (PSR) and the False positive rate (FDR)
print("Comparing estimated model with the real network")
#> [1] "Comparing estimated model with the real network"
comparison(real = real, estimate = model$networkhat)
#> $PSR
#> [1] 0.4
#>
#> $FDR
#> [1] 0.4666667
print("Comparing the prior network with the real network")
#> [1] "Comparing the prior network with the real network"
comparison(real = real, estimate = priori)
#> $PSR
#> [1] 0.7
#>
#> $FDR
#> [1] 0.3
We can also compare visualizations
<- network(model$networkhat)
estimated_net par(mfrow = c(1,3))
plot(prior_net, main = "Prior Network")
plot(real_net, main = "Real Network")
plot(estimated_net, main = "Estimated Network")
par(resetPar())
The model object also stores all the candidate models generated.
length(model$candidate)
#> [1] 64
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.