similar to: AIC vs. extractAIC

Use extractAIC in frailty cox model (estimated with coxph function, gaussian random effect) i obtaided > extractAIC(fit.cox.f) [1] 11.84563 8649.11736 but I don't know why I can't use the classic formulation of the AIC where the degree of freedom are the number of the parameter (in my case 3). -- View this message in context:

Hello. The sentence in extractAIC's help <http://www.stat.psu.edu/~dhunter/R/html/stats/html/extractAIC.html> which discusses AIC's estimate of -2logL from RSS reads: "AIC only handles unknown scale and uses the formula n log (RSS/n) - n + n log 2pi - sum(log w) where w are the weights. Further AIC counts the scale estimation as a parameter in the edf and extractAIC does

Full_Name: Dave Ramsey Version: 1.8.0 OS: win2000 Submission from: (NULL) (202.27.240.6) there is a bug in extractAIC.survreg in library MASS. A survreg model object has no component called "residuals". Hence n <- length(fit$residuals) returns 0 resulting in errors workaround: replace n <- length(fit$residuals) with n <- length(residuals(fit)) ### sorry: error

Hi, I have sent this message to this list the July, 7th. It was about a problem in MASS package. Until now there is no change in the devel version. As the problem occurs in a package and not in the R-core, I don't know if the message should have been sent here. Anyway, I have added a copy to Pr Ripley. I hope it could have been fixed. Sincerely Marc Le 09/07/2017 ? 16:05, Marc Girondot via

Hi, It is not critical but in case of coxph.null model (~1) extractAIC function generates Warning message: In is.na(fit$coefficients) : is.na() applied to non-(list or vector) of type 'NULL' As I understand it happens because of absent coefficients attribute. Function stats:::extractAIC.coxph Line edf <- sum(!is.na(fit$coefficients)) I think extra null-checking

Although the 'spatial' documentation doesn't mention that extractAIC works, it does seem to give an output. I may have misunderstood, but shouldn't the following give at least the same d.f.? > library(spatial) > data(topo, package="MASS") > extractAIC(surf.ls(2, topo)) [1] 46.0000 437.5059 > extractAIC(lm(z ~ x+I(x^2)+y+I(y^2)+x:y, topo)) [1]

Hello, I am using a simple linear model and I would like to get an AIC value. I came across both AIC() and extractAIC() and I am not sure which is best to use. I assumed that I should use AIC for a glm and extractAIC() for lm, but if I run my model in glm the AIC value is the same if I use AIC() on an lm object. What might be going on? Did I interpret these functions incorrectly? Thanks,

I would like test AICc as a criteria for model selection for a glm using stepAIC() from MASS package. Based on various information available in WEB, stepAIC() use extractAIC() to get the criteria used for model selection. I have created a new extractAIC() function (and extractAIC.glm() and extractAIC.lm() ones) that use a new parameter criteria that can be AIC, BIC or AICc. It works as

Dear R users: I am looking for the source code for the R function extractAIC. Type the function name doesn't help: > extractAIC function (fit, scale, k = 2, ...) UseMethod("extractAIC") <environment: namespace:stats> And when I search it in the R source code, the best I can find is in (R source root)/library/stats/R/add.R: extractAIC <- function(fit, scale, k = 2,

Howdee, I am able to fit a 4-parameter logistic growth curve to a dataset which comprise many individuals (using R v. 2.3.1). Yet, if I want to obtain the parameters for each individual (i.e., for each 'id') using nlsList, then I obtain an Error message which I have trouble interpreting. Any advice as to how I can solve this problem? Thanks for your time, Marc > reg <-nls(mass ~

Hi, I have been trying unsuccessfully to plot data using different colors based on a variable within a subset of an imported file. The file I am reading is about 20000 lines long and has a column (in the example called FILE) that contains approximately 100 unique entries. I would like to plot a subset of the data from the file and key the color from the FILE column, This is what my file looks like

Hello metafor users, I'm using metafor to perform a single-effect summary estimate of the raw proportion of patients experiencing a post-operative complication, and I'm interested in seeing if this proportion differs between the three most commonly used surgical techniques. The software is working as expected, but I would like to double check on the interpretation of my mixed-effect model

Dear Professor Lumley I am relatively new to using R and also to logistic regression. We have analysed our Dudley Health Survey using the survey package. I am now trying to look at associations using svyglm but I am unsure of how to interpret the output and present the resulting model or whether there are any other things I should do to check the validity of the model. Below is an example of

Dear All- I have a dataset that is comprised of the following: doy yr mon day hr hgt1 hgt2 hgt3 co21 co22 co23 sig1 sig2 sig3 dif flag 244.02083 2005 09 01 00 2.6 9.5 17.8 375.665 373.737 373.227 3.698 1.107 0.963 -0.509 PRE 244.0625 2005 09 01 01 2.6 9.5 17.8 393.66 384.773 379.466 15.336 11.033 5.76 -5.307 PRE 244.10417 2005 09 01 02 2.6 9.5 17.8 411.162 397.866 387.755 6.835 5.61 6.728

The R poisson random generator rpois appears to have a bug for theta 10 or larger. The sample mean of the pseudo variates is too small: sample mean approx theta - 0.5. I use Version 1.1.1 (August 15, 2000) Of R on a Dell OptiPlex computer with the Windows XP Professional operating system. Has this bug been fixed in later versions? (I found another reported rpois bug, but it appears to be

Hi All , Can anybody tell me if there's any way to get the summarized anova values.Now i will explain what i mean , when i say "*summarized*". Below you can see the anova table of recmeanC1 with rest* all* i.e from recmeanC2 to i15(predictors),as shown in table. Df Sum Squares Mean Square F value Significance [Pr(>F)] recmeanC2 1 89.272 89.272

Hello! I'm puzzled by the following problem. It occurs while trying to predict responses in a test-dataset using a linear model fitted with regFit from the rMetrics "fRegression"-package. All goes well when I call "predict" using the training dataset. However, a call using the test-dataset retuns an error message - telling me that the latter dataset provides variables

Hi R Gurus! I conducted regression and anova followings : Coefficients: Estimate Std. Error t value Pr(>|t|) (Intercept) 6.07e-01 5.95e-02 10.19 < 2e-16 *** nemp 2.87e-06 1.04e-07 27.63 < 2e-16 *** as.factor(corridor1)A -8.81e-02 2.13e-02 -4.14 3.6e-05 *** as.factor(corridor1)B

Hello Monty, I tried to complile vorbis under win32 (using MS Visual C 5.0) I found some things: 1.) In bitvise.c there must be buffer cleared after malloc: void _oggpack_writeinit(oggpack_buffer *b){ memset(b,0,sizeof(oggpack_buffer)); b->ptr=b->buffer=malloc(BUFFER_INCREMENT); + memset(b->ptr,0,BUFFER_INCREMENT); b->storage=BUFFER_INCREMENT; } void

Hello Monty, I tried to complile vorbis under win32 (using MS Visual C 5.0) I found some things: 1.) In bitvise.c there must be buffer cleared after malloc: void _oggpack_writeinit(oggpack_buffer *b){ memset(b,0,sizeof(oggpack_buffer)); b->ptr=b->buffer=malloc(BUFFER_INCREMENT); + memset(b->ptr,0,BUFFER_INCREMENT); b->storage=BUFFER_INCREMENT; } void