similar to: Fwd: Re: Fitting exponential curve to data points

Hi folks, I've looked through the list archives and online resources, but I haven't really found an answer to this -- it's pretty basic, but I'm (very much) not a statistician, and I just want to check that my solution is statistically sound. Basically, I have a data file containing two columns of data, call it data.tsv: year count 1999 3 2000 5 2001 9 2002 30 2003 62 2004 154

I'm trying to find an R package that will smooth a line with the "polynomial approximation with exponential kernel" or "PAEK" algorithm that is used in ESRI's ArcGIS software. I have a copy of the original paper that provides the algorithm, but I'm not confident in how to code it. The algorithm will smooth a polyline's vertices at a user specified distance

Hi there, I'm quite new to R (and statistics), and I like it (both)! But I'm a bit lost in all these packages, so could someone please give me a hint whether there exists a package for fitting exponential curves (of the type t --> \sum_i a_i \exp( - b_i t)) on a noisy signal? In fact monoexponential decay + polynomial growth is what I'd like to try. Thanks in advance,

Dear useRs, I have the following plot: pos <- c(27/44, 11/32, 8/40, 4/42, 3/40, 4/40, 2/40) tmin <- c(15.8, 12.6, 10.5, 2.4, 5.2, 8.5, 7.9) plot(tmin, pos) I would like to fit an exponential curve to it. How could I be able to do this? Thanks in advance, Rafael. ____________________________________________________________________________________ [[elided Yahoo spam]]

I'm trying to use nls() to fit an exponential decay with an unknown offset in the time (independent variable). (Perhaps this is inherently very difficult?). > decay.pl <- nls (amp ~ expn(b0,b1,tau,t0,t), data = decay, + start = c(b0=1, b1=7.5, tau=3.5, t0=0.1), trace=T) Error in nlsModel(formula, mf, start) : singular gradient matrix at initial parameter estimates

Dear list, I have been checking my package ('analogue') using R2.13-0-alpha (details of exact svn version appended below) and the R CMD check procedure is generating an error rebuilding a vignette in the package, which raises a NOTE in the check. The log printed to screen during check shows: .... * checking re-building of vignettes ... NOTE Error in re-building vignettes: ... Error in

I finally got (mostly) what I wanted. In an attempt to figure out how to get nls to deal with a non-differentiable function, I had (stupidly) 'simplified' the problem until it became singular. Can I do something to make optim() less sensitive to my initial guess? For this example, I get a lousy solution if I make the initial guess for t0 = min(t) = 0.05. Thanks again, -- Robert Merithew

I am learning glm function, but how do you fit data using exponential distribution with glm? In the help file, under "Family Objects for Models", no ready made option seems available for the distribution as well as for other distributions satisfying GLM requirements not listed there.

Hi all, I am attempting to fit, and test the goodness of fit of, a mixed exponential distribution to my dataset which consists of 15minute rainfall intensity data. FYI, the dataset spanning approx.2 years and 7 rainfall stations consists of some three hundred thousand 15min data records, of which some 30 thousand are non-zero rainfall amounts. Could anyone please tell me how i could do

Hi, I would like to fit some experimental points by a exponential function. I ignore the parameters of this exponential and what I would like is to ask R to calculate the best fitting curve an the associated parameters (as the linear model function (lm) does for linear models). Is it possible ? Do anyone have an idea about how to do that ? Thanks by advance Jessica Gervais [[alternative

Dear R-users I have some datasets, all left-censoring, and I would like to fit distributions to (weibull,exponential, etc..). I read one solution using the function survreg in the survival package. i.e survreg(Surv(...)~1, dist="weibull") but it returns only the scale parameter. Does anyone know how to successfully fit the exponential, weibull etc... distributions to left-censoring

Dear R helpers   I am working on the credit risk default data and am referring to "An introduction to Credit Risk Modelling" by Christian Bluhm. The literature affirms that 'the default frequencies grow exponentially with decreasing credit worthiness'.   I have a data of rating wise default frequencies. The idea is to fit exponentail of the type Y = a * exp( b*X ) where Y is

Dear All, I have two questions regarding distribution fitting. I have several datasets, all left-truncated at x=1, that I am attempting to fit distributions to (lognormal, weibull and exponential). I had been using fitdistr in the MASS package as follows: fitdistr<-(x,"weibull") However, this does not take into consideration the truncation at x=1. I read another posting in this

Dear mailing list, I have following array: X2 Y2 [1,] 422.7900 6.0 [2,] 469.8007 10.5 [3,] 483.9428 11.0 [4,] 532.4917 25.5 [5,] 596.1942 33.5 [6,] 630.8496 40.5 [7,] 733.2996 45.0 [8,] 946.4779 32.0 [9,] 996.8068 35.5 [10,] 1074.3310 23.0 I do afterwards the following: plot.new() plot.window(xlim=c(min(X1)-50,max(X1)+50),

Hello, I have what should be an easy question. I'm a new r user and making the transition from menus to the command line so as to do batch processing of tons of data. One of my data streams needs to be detrended. It's a vector of numbers that follows a negative exponential decay. I need to fit a curve to it and use the residuals as an object. The data looks something like this: foo.dat

I was looking for suggestions as to how to smooth a timeseries and, having accomplished that, how to find the fitted curve values for intermediate points. ? I've tried numerous examples of possible approaches in R that I've found on the web, but when applied to my simple data, R returns an error message in numerous cases. ? The main problem seems to be that I have monthly data, starting

Suppose you have a vector of data in x and response values in y. How do you plot together both the points (x,y) and the curve that results from the fitted model, if the model is not y ~ x, but a higher order polynomial, e.g. y~poly(x,2)? (In other words, abline doesn't work for this case.) Thanks, --Paul -- Paul Lynch Aquilent, Inc. National Library of Medicine (Contractor)

I have a data set of 6 or so ordered pairs, and I've been able to graph them and have decided to use a high-order polynomial regression. I've used the following piece of code: regression <- function(x,y) { x <- c(insert_numbers_here) y <- c(insert_other_numbers_here) fit <- lm(y ~ x + I(x^2) + I(x^3) + I(x^4) + I(x^5) + I(x^6) + I(x^7) + I(x^8) + I(x^9))

Any one know is there any package or function to generate bivariate exponential distribution? I gusee there should be three parameters, two rate parameters and one correlation parameter. I just did not find any function available on R. Any suggestion is appreciated. -- View this message in context:

Is the matrix exponential available in some package? The cannonical reference is "Nineteen dubious ways to take the exponential of a matrix". (Love that title) Terry T.