search for: logmean

Mich besch?ftig folgende Fragestellung. Ich kenne die Verteilung (lognormal) zus?tzlich weiss ich das 99%, das 90% und das 1% Quantil. Gibt es in R eine M?glichkeit die Lognormalverteilung zu finden, das heisst den korrespondierenden logmean und logsd? Vielen Dank f?r ihre Hilfe Gruss Yvonne

...the help of Berend, the cov matrix was converted to log-return from an arithmetic return as follows:   logreturn <- function(am,asigma) {   M <- 1/(1+am)   S <- log( diag(M) %*% asigma %*% diag(M) + 1)   mu <- log(1+am) - diag(S)/2   list(mean=mu, vcov=S) } z <- logreturn(mu, sigma) logmean <-z$mean cov <-z$vcov   following I used : i <-matrix(rlnorm.rplus(5000,logmean,cov),ncol=5),  which will give me results much different from my starting point of mu.   To try to better explain my goal here: I also happened to know the medians and SDs of this multivariate structure, and th...

...name. Various packages have functions which do that same sort of thing (log(exp(x)+exp(y)) and log(exp(x)-exp(y)) without unnecessary floating point errors). They have names like matrixStats::logSumExp(lx, na.rm=FALSE, ...) (the ... is ignored by the function) sna::logSub(x,y), logSum(x), logMean(x) BTYD::addLogs(loga, logb) and subLogs(loga, logb) Googling for logSumExp (the Python name) indicates that many know this as "LSE" (the "Log-Sum-Exp trick"). I've seen several instances in R-help recently where user code could be made more accurate if these were avail...