search for: rocdemo

The name conflicts in Epi and ROC packages (2 'ROC' functions are the problem) cause the following code to work once, but not twice: library(MASS); data(cats); x = cats[,2] y = ifelse(cats[,1]=='F',0,1) library(Epi); ROC(x,y,grid=0)$AUC library(ROC); AUC(rocdemo.sca(y, x, dxrule.sca)) What is the standard way of resolving name conflicts? Ask maintainers to resolve it or rename the younger function, use namespaces somehow, or something else? My machine is WinXP, R-2.2.0, ROC and Epi packages are the latest versions. Jarek Tuszynski [[alternative HT...

I am doing a simulation with a relatively large data set (20,000 observations) for which I want to calculate the area under the Receiver Operator Curve (AUC) for many parameter combinations. I am using the ROC library and the following commands to generate each AUC: rocobj=rocdemo.sca(truth = ymis, data = model$fitted.values, rule = dxrule.sca) #generation of observed ROC object aucobj=AUC(rocobj) #pulling out just the observed AUC - trapezoidal not integrated but they are pretty slow. Does anyone know of a faster way to get the AUC? Thanks, Nina [[alternati...

...t.window(xlim, ylim, log, asp, ...) : need finite xlim values" --- > set.seed(123) > state <- c(0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 1, 1, + 1, 1, 1) > markers <- c(1, 2, 1, 1, 2, 3, 3, 4, 2, 1, 1, 3, 2, 3, 2, 4, + 5, 2, 3, 4) + runif(20, -1, 1) > roc1 <- rocdemo.sca(truth = state, data = markers, rule = dxrule.sca, seqlen = 5) > plot(roc1) Error in plot.window(xlim, ylim, log, asp, ...) : need finite xlim values In addition: Warning messages: 1: no finite arguments to min; returning Inf 2: no finite arguments to max; returning -Inf 3: no finite...

...)) auc[1,i] = colAUC(x, y, alg="ROC") auc[2,i] = colAUC(x, y, alg="Wilcox") auc[3,i] = wilcox.test(x1, x2, exact=0)$statistic / (n1*n2) auc[4,i] = (sum(r[1:n1]) - n1*(n1+1)/2) / (n1*n2) auc[5,i] = roc.area(y, x)$A.tilda auc[6,i] = AUC(rocdemo.sca(y, x, dxrule.sca)) auc[7,i] = performance(prediction( x, y),"auc")@y.values[[1]] auc[8,i] = ROC(x,y,grid=0)$AUC # get AUC by 'ROC' auc[9,i] = auROC(y, x) # get AUC by 'auROC' pval[1,i] = wilcox.test(x1, x2, exact=0)$p.value pval[2,i] = wilcox.test(...

Question on graphs: The default case for drawing a graph in R, is where a little space is left on the x and y axis before the first tick i.e. even if I say xlim=c(0,1) -- there will be some space between the edge of the x-axis and where 0 is placed. If I want 0 on the edge, how do I do it in R? Area under the curve: I have a 45 degree line and a curve above or below it. Is there a way in R