On May 16, 2012, at 12:37 , Andras Farkas wrote: > Dear R Expert > > allow me to ask a quick qestion: I have a mean value of 6 and a SD of 3 > describing my distribution. I would like to "convert" this distribution into > a log normal distribution that would best describe it when resimulated using > log normal distribution. Currently I am using another software to estimate > the respective mean and SD on the log scale and the results are: 1.6667 and > SD 0.47071. Then, to best reproduce my original distribution in R, I use the > following commands: > > c <- rlnorm(5000,1.6667,0.47071) > d <- exp(c) > mean(c) > sd(c) > > and the results for mean and SD are 5.92 and 2.94 (original 6 and 3), > respectively, which I am reasonably happy with. I would like to grow > independent of the another software I use, but am unable to figure out how to > generate the values of 1.6667 and 0.47071 using R. could someone please help > me with this question?
Perhaps this was what you were looking for: > d <- log(c) > mean(d) [1] 1.675003 > sd(d) [1] 0.4656469 Taking exp() of a log-normal rarely makes much sense. More commonly, you take log() to get a normal distribution. -- Peter Dalgaard, Professor, Center for Statistics, Copenhagen Business School Solbjerg Plads 3, 2000 Frederiksberg, Denmark Phone: (+45)38153501 Email: [email protected] Priv: [email protected] ______________________________________________ [email protected] 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.
