similar to: Confidence intervals of log transformed data

Hi I have a general statistics question on calculating confidence interval of log transformed data. I log transformed both x and y, regressed the transformed y on transformed x: lm(log(y)~log(x)), and I get the following relationship: log(y) = alpha + beta * log(x) with se as the standard error of residuals My question is how do I calculate the confidence interval in the original scale of x

I've got a vector of data (hours to drive from a to b) y. After a qqplot I know, that they don't fit the normal probability. I would like to transform these data with the boxcox transformation (MASS), that they fit the model. When I try ybx<-boxcox(y~1,0) qqnorm(ybx) the plot is different from library (TeachingDemos) ybct<-bct(y,0) // qqnorm(ybct) How can I transform

Dear all: I'm trying to fit the optimal Box-Cox transformation related to nls (see the code below) for the demand of money data in Green (3th Edition) but in the last step R gives the next error message. Error en `[.data.frame`(eval(object$data), , as.character(formula(object)[[2]])[2]) : undefined columns selected. ?Any idea to solve the problem? Thanks in advance,

Dear experts, I tried to learn about Box-Cox-transformation but found the following thing: When I had to add a constant to make all values of the original variable positive, I found that the lambda estimates (box.cox.powers-function) differed dramatically depending on the specific constant chosen. In addition, the correlation between the transformed variable and the original were not 1 (as I

Hello R users & R friends, I just want to ask you if density() can produce a confidence interval, indicating how "certain" the density() line follows the true frequency distribution based on the sample you feed into density(). I've heard of loess.predict(loess(y ~ x), se=TRUE) which gives you a SE estimate of the smoothed scatterplot - but density() kernel smoothing is not the

Hello, I would like to calculate the 95% confidence intervals for the estimates of a linear model and I just wanted to check that I am doing it correct. Is it just: Estimate + 1.95996*Std.Error to Estimate - 1.95996*Std.Error or is there another approach that doesn't assume a normal distrbution? Thanks. Apologies for my naiivity Dan --

Hi R People: If I have a fitted values from a model, how do I plot the (1-alpha)100% confidence intervals along with the fitted values, please? Also, if the intervals are "shaded" gray, that would be nice too, please? I check confint, but that doesn't seem to do what I want. Thanks in advance, Sincerely, Erin -- Erin Hodgess Associate Professor Department of Computer and

Hi folks! I run the following code to get a CI for a Poisson with lambda=12.73 library(MASS) set.seed(125) x <- rpois(100,12.73) lambda_hat<-fitdistr(x, dpois, list(lambda=12))$estimate #Confidence Intervals - Normal Approx. alpha<-c(.05,.025,.01) for(n in 1:length(alpha)) { LowerCI<-mean(x)-(qnorm(1-alpha[n]/2, mean = 0, sd = 1)*sqrt(var(x)/length(x)))

I'm using the lme function in nmle to estimate the variance components of a fully nested two-level model: Y_ijk = mu + a_i + b_j(i) + e_k(j(i)) lme computes estimates of the variances for a, b, and e, call them v_a, v_b, and v_e, and I can use the intervals function to get confidence intervals. My understanding is that these intervals are probably not that robust plus I need intervals on the

Hi, I can't seem to find a function in R that will reverse a BoxCox transformation. Can somebody help me locate one please? Thanks in advance. Best wishes, Des [[alternative HTML version deleted]]

Hi, Here is the situation, I hope somebody can help me. Our Email server running ubuntu 8.04.1 and dovecot 1.0.10 rebooted, and when it came back up the dovecot config had changed. Prior to the reboot, users stored their emails and folders in /var/mail/~username. Then the config became /var/mail/username for the main Inbox and /home/~username/mail for Folders. Now, none of the folders

Help page for boxcox function in MASS library says that the transformation is y^lambda, which is different from the Y' = log(Y) if lambda = 0 , Y' = ((Y ^ lambda) - 1)/lambda otherwise I'm used to. Is this just a help page typo ? Thanks. ---------------------------------------------------------------- This message was sent using IMP, the Internet Messaging Program.

Dear R-users, I am using R version 1.8.0-1 under Suse 8.2. I need to use the boxcox command because I want to apply a Cox-Box transformation to a vector of rainfall values. Within the libraries, the MASS library is present, but I don't know whether this means that is automatically installed or not. The command doesn't work. What do I have to do in order to make it working? Is just a

I have a rather basic background in statistics, and am looking for assistance in solving what I expect is a common type of problem. I have measurements of physical processes, and mathematical models of those processes that I want to feed the measurements into. A simple case is using measurements of electric power entering and leaving a power conversion device, sampled at regular intervals, and

Hi all! I'm getting a model fit from glm() (a binary logistic regression fit, but I don't think that's important) for a formula that contains powers of the explanatory variable up to fourth. So the fit looks something like this (typing into mail; the actual fit code is complicated because it involves step-down and so forth): x_sq <- x * x x_cb <- x * x * x x_qt <- x * x * x

Hi, Hope this does not sound too ignorant . I am trying to detrend and transform variables to achieve normality and stationarity (for time series use, namely spectral analysis). I am using the boxcox transformations. As my dataset contains zeros, I found I need to add a constant to it in order to run "boxcox". I have ran tests adding several types of constants, from .0001

I'm trying to write a small function (below) to compute Box & Cox transformations of x for arbitrary values of lambda. I'd like to specify a range of values for lamba (min,max,step) and am having trouble getting the for loop to work. Suggestions? Any pointers to resources for learning to write functions in R for neophyte programmers? Thanks. --Dale boxcox <-

Hello all, I have to run a 2 Sample Confidence Interval on some data; the command for such intervals is "confint(...)", but in the help documentation it says that you need a "fitted model object" in order to run this command. What does that mean? The data is very small, it's: x=c(8,12,10,14,2,0,0) y=c(-6,0,1,2,-3,-4,2) and I want to be able to run a Confidence

Hello, I wonder if anyone has a function for calculating confidence intervals for ratios. I have mortality rates calculated for several groups from sample data -- but these can be treated as ratios?). I am entertaining the idea of bootstrapping them. Any help would be greatly appreciated. TIA, Marwan ---------------------------------------------------------------------------- ------------

Thanks John. ?boxcox says: ************************* Arguments object a formula or fitted model object. Currently only lm and aov objects are handled. ************************* I read that as saying that boxcox(lm(z+1 ~ 1),...) should run without error. But it didn't. And perhaps here's why: BoxCoxLambda <- function(z){ b <- MASS:::boxcox.lm(lm(z+1 ~ 1), lambda = seq(-5, 5,