similar to: geoR/likfit: variance explained by model

We want to compute a pseudo R-squared for a model whose parameter estimation was based on maximum likelihood (function likfit, package geoR). I tried to compute the R2 proposed by Maddala (1983) which compare the maximized likelihood for the model without any predictor and the maximized likelihood for the model with all predictors. I got a really low value (0,01%). Did I miss something? Are

Hi I'm using geoR package to perform linear spatial interpolation(OK). The function likfit() fails to compute REML. The error meassage is : Error in solve.default(v$varcov, xmat); How I can find out that likfit() is failed to process and retrieving the error message ? Thank you so much for your help.

I am having difficulty getting the trend.spatial function in geoR to work properly. After creating a trend.spatial object with a covariate, I try to add the command into my likfit() function as follows: trend1.trend.spatial <- trend.spatial("1st", trend1.geodata) trend1.spatial.EC0.1.reml <- likfit(spatial.geodata, trend1.trend.spatial, ini.cov.pars = spatial.EC0.1.eyefit,

ComRades: I am geeting the error message Error in ldots[[which(MET)]] : attempt to select less than one element when I try to fit the geostatistical model with the likfit() function of geoR. I have tried with old data for which likfit() successfully maximised the likelihood in previous versions of geoR, and yet the current version fails. I have tried in Windows Vista and Windows XP (I haven't

Mzabalazo Ngwenya wrote: > Hi everyone ! > > I'm am trying to fit a kriging model to a set of data. When I just run > the "likfit" command I can obtain the results. However when I try to > pass additional arguements to the optimization function "optim" I get > errors. That is I want to obtain the hessian matrix so matrix > (hessian=TRUE). >

Hi everyone !   I'm am trying to fit a kriging model to a set of data. When I just run the "likfit" command I can obtain the results. However when I try to pass additional arguements to the optimization function "optim" I get errors. That is I want to obtain the hessian matrix so matrix (hessian=TRUE).   Heres a little example( 1-D). Can anyone shed some light?  Where am I

> -----Original Message----- > From: r-help-bounces at stat.math.ethz.ch [SMTP:r-help-bounces at stat.math.ethz.ch] On Behalf Of ernesto > Sent: Friday, January 13, 2006 9:25 AM > To: Mailing List R > Subject: [R] help with gepRglm::likfit.glsm > > Hi, > > I'm exploring likfit.glsm and I need some help. I have to say that I'm > not an MCMC expert ... >

Hi I am struggling to fit a non-linear trend using the likfit function in geoR. Specifically I want a sigmoidal function, something like SSfpl in the nls package to fit the trend. But it seems trend.spatial in geoR only works with lm or glm type models. Any ideas how I can specify the model to calculate the kriging parameters using REML, including the parameters of a sigmoidal trend function

Greetings comRades: Has anyone worked out a procedure to calculate the estimated covariance between the beta and lambda estimates in the likelihood-based geostatistical model implemented in package geoR? If so, please help me out by letting me know. Do I have reasons to expect that this covariance term would be big or perhaps more happily, that it could be discarded without much effect?

Dear Aaron, I am really a tool user and not a tool maker (actually an ecologist doing some biostatistics)... so, I take the liberty of sending a copy of this e-mail to the r-help list where capable computer persons and true statisticians may provide more relevant information and also to Paulo Ribeiro and Peter Diggle, the authors of geoR.. I really feel that your huge matrix cannot be

Hi, Im using geoR and I'm trying to do some predictions, based on an external trend. I'm having some problems specifying my model.control, specifically how do I define my model, and also the source of the covariate data at the prediction locations? I am assuming that the covariate data at the prediction locations should be imported to a geodata object along with the prediction location

Hi cross posting from sig geo , because I really need help! I'm using geoR for some spatial linear models and I'm getting surprisingly optimistic values from the spatial models relative to the non-spatial, even when the models appear to be performing about equally (by AIC comparison) For example This model relating encounter rates of lizards to a soil substrate parameter gives >

Hello, I am attempting to get the standard deviation in multiple distance bins in my spatial data. It appears as though the 'variog' command in the geoR package will do the trick, as one of the outputs from 'variog' is 'variog$sd', which, according to the manual, is the "standard deviation of the values in each bin". However, when I run this command, the

Hi all, I am trying to model (continuous) spatial variation in a response variable as a function of one or more of several explanatory variables. I am principally interested in obtaining some measure of the relative "importance" of the explanatory variables. I have found several R libraries that are tailored to this sort of problem (geoR, geoRglm, gstat, etc.); however, as near

Hello, I used glsm.mcmc and likfit.glsm to create model. Now I want to predict at different locations, but I can't get glsm.krige to work. I keep getting the error that trend.d and trend.l must have similar specifications. I have tried numerous ways to include the covariates in the glsm.krige model, and I keep getting the same error message. The bolded part is the part that doesn't work.

Mac OS 10.3.5, R 2.0.0 latest version of geoR I have an incomplete 5 x 20 spatial array of samples (60 out of 100 possible locations) for which I would like to calculate directional variograms using variog4(). Unfortunately, I can't get it to return all 4 directions. It returns variograms for 45, 90, and 135 degrees, omitting 0 degrees (pi/4, pi/2, 3pi/4, omitting 0). If I specify 0

I'm using R for Mac OSX version 1.14 (2129) and the geoR package version 1.6-5 (the current version in the R repository). I'm running R in OS 10.4.6 on a Mac G4 iBook (933MHz, 640 MB DDR SDRAM). I searched the R archive and did not find a posting on this issue. I want to use the variog and variog4 functions of geoR to characterize the pattern of spatial autocorrelation of tree

Dear R users: I want to model mosquito count data based on landcover attributes and meteorological variables using a Poisson GLSM in the geoRglm package. I have monthly mosquito counts over more than 20 years with repeated observations from individual trap sites over time. I have used as.geodata() to successfully read my dataset into the geodata format utilized by geoR and geoRglm,

Hi All, I'm trying to use the geoRglm package to run a poisson spatial glm on a dataset with several covariates. When I run without covariates I have no problems. control1.data.geo <- mcmc.control(S.scale=0.2, thin = 1) model1.data.geo <- list(cov.pars = c(1,1), beta=c(1), family="poisson") test1.model1 <- glsm.mcmc(data.geo, model=model1.data.geo,

Hi, I want to automatically fit variograms to a large number of different sample data sets, and call the funtion "likfit" (in package geoR) from within a for-loop. "likfit" does again call "optim". After ssuccessfully fitting variograms to some of the data sets, the procedure crashes and I get the error message: Error in optim(par = ini, fn = negloglik.GRF,