similar to: Hypothesis testing after optim

Dear R users, I am running a maximum likelihood model with optim. I chose the simulated annealing method (method="SANN"). SANN is not performing bad, but I guess it would be much more effecive if I could set the `parscale' parameter. The help sais: `parscale' A vector of scaling values for the parameters. Optimization is performed on `par/parscale' and these

I'd like to be able to test linear hypotheses after setting up and running a model using optim or perhaps nlm. One hypothesis I need to test are that the average of several coefficients is less than zero, so I don't believe I can use the likelihood ratio test. I can't seem to find a provision anywhere for testing linear combinations of coefficients after max. likelihood. Cheers

Dear r-help, I would like to use the 'ppm' function of the 'spatstat' package to fit a Strauss inhibition model. I understand that I can specify a parametric model for the "background" trend, but how would I specify a trend which is estimated using a Kernel density smoother? In particular, I would like to use the 'kde' function of the 'ks' package to

Dear R-packages list members, Last month, Peter Muhlberger posted a message to the r-help list that suggested, among other things, a desire for a more convenient method of performing Wald tests for statistical models fit in R. Thanks largely to Achim Zeleis's help, the linear.hypothesis function in the car package has been reworked so that (1) it is applicable to any model object that

Dear R-packages list members, Last month, Peter Muhlberger posted a message to the r-help list that suggested, among other things, a desire for a more convenient method of performing Wald tests for statistical models fit in R. Thanks largely to Achim Zeleis's help, the linear.hypothesis function in the car package has been reworked so that (1) it is applicable to any model object that

On Wed, 4 Jan 2006, Peter Muhlberger wrote: One comment in advance: please use a more meaningful subject. I would have missed this mail if a colleague hadn't pointed me to it. > I'm someone who from time to time comes to R to do applied stats for social > science research. [snip] > I would also prefer not to have to work through a > couple books on R or S+ to learn how to

Hi, All, I am a beginner for R. Now I have installed R 2.5.1 in Window environment. After I run a program such as "gam" I would like to display a plot for the object. The following is an example. When I did this, only the last plot was presented on my screen. How can I get a plot before the last plot? I mean if the object has several plots how can I get those? "gam.object <-

I'm trying to use the source command to run commands from a file. For instance: source("do.R"), where do.R is a file in the same directory in which I am running R. The contents of do.R are: ls() print("hello") sum(y1) mean(y1) After source("do.R"), all I see is: > source("do.R") [1] "hello" I'm using the X11 version of R for

Is there a likelihod function for the Weibull distribution in 'R'? I found the following reference: http://www.weibull.com/LifeDataWeb/weibull_log_likelihood_functions_and_their_partials.htm But I had a hard time understanding the parameters required Particularly 'number of groups of times-to-failure data points", "number of groups of suspension data points", and

A newbie question: I'm trying to decide whether to run a maximum likelihood estimation in R or Stata and am wondering if the R mle routine is reasonably robust. I'm fairly certain that, with this data, in Stata I would get a lot of complaints about non-concave functions and unproductive steps attempted, but would eventually have a successful ML estimate. I believe that, with the

Hi, does anyone out there have a recommendation for multilevel / random effects and longitudinal analysis? My dream book would be something that's both accessible to a non-statistician but rigorous (because I seem to be slowly turning into a statistician) and ideally would use R. Peter

I'm used to statistical languages, such as Stata, in which it's trivial to pass a list of variables to a function & have that function modify those variables in the existing dataset rather than create copies of the variables or having to replace the entire dataset to change a few variables. In R, I suppose I could paste together the right instructions in a function and then execute

Apologies if this has been posted about recently, but I haven't been on this listserve for a while. I ran into a problem trying to compile Hmisc (required package for rms) and have found a solution that I'd like to share. The compile fails with the message: /usr/bin/ld: cannot find -lquadmath libquadmath exists on my Debian Squeeze system (up-to-date, recently installed): ldconfig -p

Hi, I'm using R 1001 for Windows NT and the sm library. I'm trying to create plots for my data set like Bowman and Azzalini have in Figure 1.8 (p. 9) of their book for my data (i.e. a contour plot for each group in my data set and its all plotted on 1 plot). The problem I'm having is that R is not drawing closed contour lines for each group. Sometimes it does; other times it

Dear R experts, I am in transition to the R system from other statistical systems I was using (SPSS, Statistica, etc.). I have used R for a few months on my Windows PC, but now I would like to install R on a Linux box with SuSE 8.1. I downloaded the RPM for SuSE 8.1 from the CRAN mirror. But when I run the INSTALL script using the midnight commander it gives the following error message: #

Alternatively, just type debug(optim) before using it, then step through it by hitting enter repeatedly... When you're done, do undebug(optim). Andy > From: Spencer Graves > > Have you looked at the code for "optim"? If you > execute "optim", it > will list the code. You can copy that into a script file and walk > through it line by line to

Hi list, I have a group of data. It looks like they follow a exponential distribution. In R, how can I esimate lamda, that is the rate in pexp, of the distribution and can I use Kolmogorov-Smirnov for hypothesis testing in such a situation? I have read the "8.2 Examing the distribution of a set of data" of "An Introduction to R" but I did not find any clues on this issue.

Dear R-users, Some hours ago I successfully installed R 1.7.1 on my Linux computer (SuSE 8.1). Now I am trying to get my scripts work which I have written for R/Windows. * While with Windows I was able to use the vowels with the accents present in the Hungarian language: > d$crude.inc<-d$esetsz?m/d$?vk?zepi.l?leksz?m*1000000 > the same line leads to an error on Linux: >

Full_Name: peter muhlberger Version: 2.7.1 OS: Ubuntu x86_64 dual core Submission from: (NULL) (70.238.206.13) I've spent half a day generating .dta files using write.dta only to have them crash my copy of Stata. I eventually discovered that removing a string variable with a maximum observed length of 280 characters allows Stata to read the file without problems. A Stata limit is that the

I''m working in a complex web app that could have 1000+ users within the next year. It must be run on Windows 2003. Current db is SqlServer 2000. Company is deciding between Rails and ASP 2.0. I''d like to get some feedback on which would be the best to develop in. ( I prefer Rails :) 1. Will Rails be stable in that environment? Will it work with IIS? 2. Is it better for