search for: submodels

Here's a more general question following up on the specific question I asked earlier: Can anybody recommend an R command other than mle.aic() (from the wle package) that will give back a ranked list of submodels? It seems like a pretty basic piece of functionality, but the closest I've been able to find is stepAIC(), which as far as I can tell only gives back the best submodel, not a ranking of all submodels. Thanks in advance, Alexandra

...d to experiment with the small-sample correction AICc, I dug around in the code for the functions glm.fit stepAIC dropterm.glm addterm.glm extractAIC.glm and came across something I just don't understand. stepAIC() passes dropterm.glm() a model object. dropterm.glm() then fits a number of submodels, computing for each some measure DeltaFit of the relative change in goodness of fit. It then returns to stepAIC() with some indication of which submodel is best. addterm.glm behaves similarly. The problem is, both functions use the submodel deviances to compute the DeltaFits, not the submodel AICs,...

...'ve only just started using AIC for model comparison and after a bunch of different keyword searches I've failed to find a page laying out what the differences are between the AIC scores assigned by AIC() and mle.aic() using default settings. I started by using mle.aic() to find the best submodels, but then I wanted to also be able to make comparisons with a couple of submodels that were nowhere near the top, so I started calculating AIC values using AIC(). What I found was that not only the scores, but also the ranking of the models was different. I'm not sure if this has to do with t...

...> customRF$fit <- function(x, y, wts, param, lev, last, weights, > classProbs, ...) { > > > > randomForest(x, y, maxnodes = param$maxnodes, ntree=param$ntree, ...) > > > > } > > > > customRF$predict <- function(modelFit, newdata, preProc = NULL, > submodels = NULL) > > > > predict(modelFit, newdata) > > > > customRF$prob <- function(modelFit, newdata, preProc = NULL, submodels = > NULL) > > > > predict(modelFit, newdata, type = "prob") > > > > customRF$sort <- function(x) x[order(x[,...

I would like to try a likelihood ratio test in place of waldtest. Ideally I'd like to provide two glm models, the second a submodel of the first, in the style of lrt (http://www.pik-potsdam.de/~hrust/tools/farismahelp/lrt.html). [lrt takes farimsa objects] Does anyone know of such a likelihood ratio test? Chris Elsaesser, PhD Principal Scientist, Machine Learning SPADAC Inc. 7921

...RF$grid <- function(x, y, len = NULL, search = "grid") {} customRF$fit <- function(x, y, wts, param, lev, last, weights, classProbs, ...) { ?randomForest(x, y, maxnodes = param$maxnodes, ntree=param$ntree, ...) } customRF$predict <- function(modelFit, newdata, preProc = NULL, submodels = NULL) predict(modelFit, newdata) customRF$prob <- function(modelFit, newdata, preProc = NULL, submodels = NULL) ? predict(modelFit, newdata, type = "prob") customRF$sort <- function(x) x[order(x[,1]),] customRF$levels <- function(x) x$classes ? # Set grid search parameter...

...nova(mod)) does not provide the expected results. Moreover, the results of "anova" do not depend on the contrasts, since setting options(contrasts=c("contr.treeatment", "contr.poly")) leads to the same result. I manage to obtain the desired results by creating the submodels without the corresponding columns, and by comparing them with "anova" , for example : xsub = mod$x[,-c(2)] submod = lm(Y ~ xsub-1) print(anova(submod,mod)) So my questions are : 1) is there a direct way to perform the anova I want ? 2) what does "anova" really test, and why...

...function called jointModelBayes(), which accepts as main arguments a linear mixed effects object fit returned by function lme() of package nlme, and a Cox model object fit returned by function coxph() of package survival. * jointModelBayes() allows for joint models with relative risk survival submodels with Weibull or B-spline approximated baseline hazard functions (controlled by argument 'survMod'). * In addition, argument 'param' of jointModelBayes() specifies the association structure between the longitudinal and survival processes; available options are: - "td-val...

...function called jointModelBayes(), which accepts as main arguments a linear mixed effects object fit returned by function lme() of package nlme, and a Cox model object fit returned by function coxph() of package survival. * jointModelBayes() allows for joint models with relative risk survival submodels with Weibull or B-spline approximated baseline hazard functions (controlled by argument 'survMod'). * In addition, argument 'param' of jointModelBayes() specifies the association structure between the longitudinal and survival processes; available options are: - "td-val...

Hi, I know that is not possible make a stepwise procedure using REML in R, I can use ML for this. For nested design it may be very dangerous due the difference in variance structure, mainly in a splitplot design. ML make significative variables that REML dont make. I read an article that is made a stepwise procedure using GENSTAT. from article: "Terms were dropped from a model in a

Hello all, I am trying to figure out an optimal linear model by using stepwise regression which requires partial f-test, I did some Googling on the Internet and realised that someone seemed to ask the question before: Jim Milks <jrclmilks at joimail.com> writes: > Dear all: > > I have a regression model that has collinearity problems (between > three regressor variables). I

Dear R users, I am using lme and nlme to account for spatially correlated errors as random effects. My basic question is about being able to correct F, p, R2 and parameters of models that do not take into account the nature of such errors using gls, glm or nlm and replace them for new F, p, R2 and parameters using lme and nlme as random effects. I am studying distribution patterns of 50 tree

Dear R-helpers, I have run the code below which I expected to make an object called dd1, but that object does not exist. So, in summary, my problem is that my function is meant to make an object (dd1), and it does indeed make that object (I know that the last line of the function prints it out) but then, after the function has run, the object has disappeared. It's late on a Friday so I may

...family=gaussian) target.model <- dredge(mig.stds, subset=datam.std$temp_ran) error in eval(expr, envir, enclos), 'temp_ran' not found Q3 showing sub-models for two assigned explanatory variables The manual only explains how to exclude two variables. Please advise how to contain submodels regarding certain two or more variables. Elaine [[alternative HTML version deleted]]

Hey, I'm trying to implement a GARCH model with Johnson-Su innovations in order to simulate returns of financial asset. The model should look like this: r_t = alpha + lambda*sqrt(h_t) + sqrt(h_t)*epsilon_t h_t = alpha0 + alpha1*epsilon_(t-1)^2 + beta1 * h_(t-1). Alpha refers to a risk-free return, lambda to the risk-premium. I've implemented it like this: #specification of the model

Dear R-users, I'd like to announce the release of the new package JM (JM_0.1-0 available from CRAN) for the joint modelling of longitudinal and time-to-event data. The package has a single model-fitting function called jointModel(), which accepts as main arguments a linear mixed effects object fit returned by function lme() of package nlme, and a survival object fit returned by either

Dear R-users, I'd like to announce the release of the new version of package JM (soon available from CRAN) for the joint modelling of longitudinal and time-to-event data using shared parameter models. These models are applicable in mainly two settings. First, when focus is in the time-to-event outcome and we wish to account for the effect of a time-dependent covariate measured with

Does anyone know how to do an Hausman test? I?ve estimate a modell (some alternatives) with clogit an wanted to test the IIA test (Independence of Irrelevant Alternatives) after estimating a multinomial logit model? Thank you

Dear R-users, I'd like to announce the release of the new package JM (JM_0.1-0 available from CRAN) for the joint modelling of longitudinal and time-to-event data. The package has a single model-fitting function called jointModel(), which accepts as main arguments a linear mixed effects object fit returned by function lme() of package nlme, and a survival object fit returned by either

Dear R-users, I'd like to announce the release of the new version of package JM (soon available from CRAN) for the joint modelling of longitudinal and time-to-event data using shared parameter models. These models are applicable in mainly two settings. First, when focus is in the time-to-event outcome and we wish to account for the effect of a time-dependent covariate measured with