-----Mensaje original----- De: r-help-boun...@r-project.org [mailto:r-help-boun...@r-project.org] En nombre de Julia Cains Enviado el: lunes, 19 de abril de 2010 9:22 Para: r-help@r-project.org Asunto: [R] Truncated Normal Distribution and Truncated Pareto distribution
Dear R helpers, I have a bimodal dataset dealing with loss amounts. I have divided this dataset into two with the bounds for the first dataset i.e. dataset-A being 5,000$ to 100,000$ and the dataset-B deals with the losses exceeding 100,000$ i.e. dataset-B is left truncated. I need to fit truncated normal disribution to dataset - I having lower bound of 5000 and upper bound of 100,000. While I need to fit truncated Pareto for the lossess exceeding 100,000$. Is there any package in R which will guide me to fit these two distrubitions also giving KS (Kolmogorov Smirnov) test and Anderson Darling test results. Please guide Julia ----------- See library(MASS) ?fitdistr You can define your customized truncated density as a function in the parameter densfun of fitdistr. See also http://www.mail-archive.com/r-h...@stat.math.ethz.ch/msg34540.html http://www.mail-archive.com/r-h...@stat.math.ethz.ch/msg34548.html HTH ____________________________________________________________________________________ Dr. Rubén Roa-Ureta AZTI - Tecnalia / Marine Research Unit Txatxarramendi Ugartea z/g 48395 Sukarrieta (Bizkaia) SPAIN ************************************************ Only a man of Worth sees Worth in other men ************************************************ [[alternative HTML version deleted]] ______________________________________________ R-help@r-project.org 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. ______________________________________________ R-help@r-project.org 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.
