search for: logarithms

Hello, in scilab /Matlab there are functions that can create linear sequences (like R's seq()) as well as logarithmic sequences. Is there a logarithmic aequivalent of seq()? Or maybe this would be an idea for newer R-releases, maybe a type-option with "linear" and "logarithmic" as parameters....?! Ciao, Oliver

Hello I want to calculate natural logarithm of sum of combinations as follow: (R code) { com_sum=choose(2000000,482)*choose(1000000,118)+choose(2000000,483)*choose(1000000,117)+...+choose(2000000,i)*choose(1000000,600-i)+...+choose(2000000,600)*choose(1000000,0) #calculate the sum result=log(com_sum) #calculate the log of the sum } But

Hi, In order to use the mle2-function, one has to define the likelihood function itself. As we know, the likelihood function is a sum of the logarithm of probability density functions (pdf). I have implemented myself the pdfs that I am using. My problem is, that the pdfs values are negative and I cann't take the logarithm of them in the log-likelihood function. So how can one take the

Hi, I have some questions for the wireframe function of the lattice package. My dataset's "x-data" are sampled logarithmically and as such I would like to have a semilogarithmic 3D plot when plotting a time series. Does anyone know how to change the example in http://addictedtor.free.fr/graphiques/sources/source_40.R such that x or y would be logarithmically scaled? Also, I would

Dear Researches, sorry for the easy and common question. I am trying to justify the idea of RandomForest don't require a transformations (e.g. logarithmic) of variables, comparing this non parametrics method with e.g. the linear regressions. In leteruature to study my phenomena i need to apply a logarithmic trasformation to describe my model, but i found RF don't required this approach.

Hello! Thank you for answering! What I am trying to do is to plot my raw values (biomass of different species) on a logaritmic y-axis with the base of e. When I type "log="y"", the axis transforms into a logaritmic axis with the base of 10. Best regards, Elisabeth > Dear Elisabeth, > > I'm not sure if I have understood your question -- are you trying > to

Dear R-help, Here's a simple example of nonlinear curve fitting where nls seems to get the answer wrong on a very simple exponential fit (my R version 2.7.2). Look at this code below for a very basic curve fit using nls to fit to (a) a logarithmic and (b) an exponential curve. I did the fits using self-start functions and I compared the results with a more simple fit using a straight lm()

How can perform logarithmic binning in the scatterplot? I could only take the log of the variables and plot them, but I am sure that is not the way. I have a very huge data, and would want to plot those high density scatterplots and code then with different colors for the bins/density. -- View this message in context:

I'm using the {lattice} "levelplot" function to make a (more or less) 2-d histogram, and for the most part it's working fine with my data. However, I can't get the color key to do what I need. I can give it labels and custom cutoffs, but my cutoff lines (and hence my labels) aren't evenly spaced, instead they're more-or-less logarithmic, starting at

Dear all I am trying to make a graphic with the "vioplot" package. I use the following code: library(vioplot) x1 <- GSMrxDL x2 <- WIFI x3 <- UMT vioplot(x1, x2, x3, ylim=c(0, 10), names=c("GSMrxDL", "WIFI", "UMT"), col="gold") title("NIS Strahlung", xlab="Sender", ylab="V/m") Now I want to scale the y-axis

Hi, In continuation of the discussion of melange comments,about negative value returned in matcher due to logarithm of probabilities. *I**f we make K suitably large, we could clamp each log(K.Pi) to be >= 0, and this change will only affect really low probability terms (those with Pi < 1/K, so you can adjust K to suit):* *W' = sum(i=1,...,n, max(log(K.Pi), 0))* Did you mean for low

This should be simple but I am struggling. I like to easily switch in xyplot between a linear or logarithmic y-axis by setting a logical flag logY to False or True. This switch changes the scales argument of xyplot. I found out that the original two-dimentional data (Conc vs Time in my case) are converted to log10(Conc) if log=TRUE in scales, but it appears that functions like panel.curve need to

Greetings all, So, I''ve finally found a place to play around with the Ajax.PeriodicalUpdater. In looking at the API, I''m liking the decay option -- not necessarily for my current purpose, but just to keep in mind -- and I have a question: can the decay be a function which returns an integer? Basically, why I''m looking for is a logarithmic decay (where the system

Hi there, I guess this must be a standard issue, but I'm starting to go crazy with it. I simply want a plot with the x axis being logarithmic, having labels 1, 10, 100..., and ten unlabelled ticks between each of them - just as they introduce logarithmic axis at school. I've played around a bit with log="x", xlog=T (where exactly is the difference here?), xaxp, and xaxt

Hi, I am quite new to R and I have two questions regarding ROCR. 1. I have tried to understand how to extract area-under-curve value by looking at the ROCR document and googling. Still I am not sure if I am doing the right thing. Here is my code, is "auc1" the auc value? " pred1 <- prediction(resp1,label1) perf1 <- performance(pred1,"tpr","fpr") plot(

Hi! I'm using a large panel data, and now I have faced some difficulties with my analysis. The predictors are not normally distributed and there are quite many outliers (some of them are influential though). I have tried to change the logarythm, but i'm not sure, how to do that. I want also draw a plot picture in which logarythms of predictors x and y are changed. How could I do that?

Hi everyone, I am new in R, just used it for 2 weeks and I have a basic question. I have data, for example table$attrib that I would like to plot its cumulative distribution in logarithmic scale. How do I do that? After browsing internet, I tested this command: > plot.ecdf(1:100, log ="y", table$attrib) I got a plot, but I am not really sure what 1:100 and log="y"did to

> My question is not about statistics but more obviously about an R command. > I would like to plot an histogram with a logarithmic scale. I have > searched through R documentation and have read about the "log" option. > What matters is that it does not work with the hist() function. I'm > working with R version 1.2.3 . Maybe the problem has been solved in R 1.3 > .

Dear R-helpers! Using logarithmic axes sometimes results in an odd labelling. In some cases, only half of the axes do have labels. Hmmmm. I've played around with par(lab=c(5,5,7)) but that didn't help. An example: ---- begin example ---- x <- c(0.12, 0.3, 0.53, 1.1, 1.8, 2.6, 4.5) y <- c(0.012, 0.021, 0.032, 0.055, 0.1, 0.2, 0.35) plot(x, y, log="xy",

Hi, I am searching for a possibility to display a logarithimic y-axis in a histogram. With plot that's easy (e.g. plot(1:10, log="y") but for histograms this does not work the same way: I tried hist(rnorm(1000), freq=FALSE, seq(-4, 4, .5), ylim=c(0.001, 0.5), log="y") Which gives the expected histogram but also warnings for my log="y" command