similar to: Questions on factors in regression analysis

This is my first excursion into using reshape2 and I want to ensure that the melt() function call is syntactically correct. The unmodifed data frame is organized this way: head(tds.anal) site sampdate param quant 1 UDS-O 2006-12-06 TDS 10800 4 STC-FS 1996-06-14 Cond 280 7 UDS-O 2007-10-04 Mg 1620 9 UDS-O 2007-10-04 SO4 7580 19 JCM-10B 2007-06-21 Ca 79 20

I don't find how to do what I need to do in Dalgaard or 'R Cookbook', so I'm asking here. I have a data frame with water chemistry data and I want to start exploring these data. There are three factors (site, date, chemical) associated with each measurement. The data frame looks like this: > summary(chemdata) site_id.sample_date.param.quant

Thanks to David's help I subset my large data set and produced a smaller one for a single stream and 7 factors of interest. The structure of this data frame is: str(burns.tds.anal) 'data.frame': 718 obs. of 4 variables: $ site : Factor w/ 143 levels "BC-0.5","BC-1",..: 1 1 4 6 4 4 4 5 5 5 $ sampdate: Date, format: "1996-06-02"

Dear all, We want to test if the invasiveStatus is predicted by the amount (quant) of animals arriving to a country of a certain species (taxonid). We are using lmer to perform the model. The model is: lmer(invasiveStatus~I(log(quant+1))+I(log(inDegree+1))+(1|taxonid)+(1|country), family=binomial,data=td), where invasiveStatus is a binary variable, quant and inDegree are integer variables, and

Hello Everyone, I'm currently learning about quantile regressions. I've been using an optimizer to compare with the rq() command for quantile regression. When I run the code, the results show that my coefficients are consistent with rq(), but the intercept term can vary by a lot. I don't think my optimizer code is wrong and suspects it has something to do with the starting

Dear, I want to make an application to calculate quantile within a For() I tried the following without success: ej. date p_val <- matrix(sample(10, 1000, replace=TRUE), 200,5) test 1 rr <- paste("p_val$",names(p_val[1]), sep="") quant <- quantile(rr, probs = c(0, 10, 20, 30, 40, 50, 60, 70, 80, 90, 100)/100, na.rm=FALSE, type=1) test 2 rr <-

I set up a local repo for testing packages. My packages are not showing up from the repository when viewed by Linux clients. I suspect this is a web administrator/firewall issue, but it could be I created the repo wrongly. I am supposed to run write_PACKAGES separately in each R-version folder. Right? Maybe other novices can use these scripts, if they are not wrong :) Here's the file

Hello, I am using Dr. Harrell's design package to make a nomogram. I was able to make a beautiful one without stratifying, however, I will need to stratify to meet PH assumptions. This is where I go wrong, but I'm not sure where. Non-Stratified Nomogram:

Hillary, Richard M wrote: > Morning chaps, I have a little question for your capable minds... Say > I have an observed and predicted set of quants (in my case, length > frequencies by year and age/length), is there a way to use lattice > plots to plot the observed and predicted data together, panel by panel? > Obrigado/gracias (thankyou in Galego is?...) > Rich Hi Richard, If

Hillary, Richard M wrote: > Morning chaps, I have a little question for your capable minds... Say > I have an observed and predicted set of quants (in my case, length > frequencies by year and age/length), is there a way to use lattice > plots to plot the observed and predicted data together, panel by panel? > Obrigado/gracias (thankyou in Galego is?...) > Rich Hi Richard, If

The data set (called 'chemdata') has 6 columns (4 factors, 1 date, 1 numeric) and I need to create subsets for each of one of the factors ('stream'). This has worked flawlessly for all but two streams which were created yesterday. The command I use to create the subsets is like this: > rnchH <- subset(chemdata, stream == 'RanchSpgsH', select = c(site, sampdate,

I've a data frame with this structure: 'data.frame': 1987 obs. of 11 variables: $ site : Factor w/ 24 levels "B(W)","BC-1",..: 1 1 2 2 2 1 1 1 ... $ sampdate : Date, format: "2000-07-18" "2000-07-18" ... $ tclass : Factor w/ 8 levels "Annelida","Arachnida",..: 1 5 5 5 5 ... $ torder : Factor

I'm not able to create the proper syntax to specify a lattice bwplot() for only one of two conditioning factors. The syntax that produces a box plot of each of the two conditioning factors is: bwplot(quant ~ param | era, data=mg.d, main='Dissolved Magnesium', ylab='Concentration (mg/L)') What I've tried unsuccessfully are: bwplot(quant ~ param |

Hello, I have a question regarding shading regions under curves to display 95% confidence intervals. I generated bootstrap results for the slope and intercept of a simple linear regression model using the following code (borrowed from JJ Faraway 2005): > attach(allposs.nine.d) > x<-model.matrix(~log(d.dist,10))[,-1] > bcoef<-matrix(0,1000,2) > for(i in 1:1000){ +

Before reading water chemistry into a data frame I removed all missing data. Yet when I try to run cenros() to summarize a specific chemical I get an error that I do not understand: with( subset(chem, param=='Ag'), cenros(quant,ceneq1) ) Error in lm.fit(x, y, offset = offset, singular.ok = singular.ok, ...) : NA/NaN/Inf in 'y' I would like to learn what I did incorrectly

If there's a separate ESS user mail list, please point me to it. I'm using emacs with ESS and want to enter multiline commands for plots. Examples in my reference books show each line terminating with a comma so labels and other attributes can be specified for the plot before it is submitted for rendering. When I try to do this, however, I get an error: > boxplot(chemdata$quant ~

On Wed, 10 Feb 2016 10:18:51 -0600, Dirk Eddelbuettel wrote: > Thanks for bringing the question over from StackOverflow [1]. I am not > very impressed that you STILL hide behind a pseudonym and I am starting > to question my sanity as to why I take time out to help someone like > that. Anyway, read on ... > > [1]

Data frame has this structure: 'data.frame': 11169 obs. of 4 variables: $ stream : Factor w/ 37 levels "Burns","CIL",..: 1 1 1 1 1 1 1 1 1 1 ... $ sampdate: Date, format: "1987-07-23" "1987-09-17" ... $ param : Factor w/ 8 levels "As","Ca","Cl",..: 1 1 1 1 1 1 1 1 1 1 ... $ quant : num 0.01 0.01 0.01 0.01

After playing with the vorbis code for a while and doing tons of hacks and analysis on it, I've found it to perform very poorly with impulse signals. The MDCT seems to cause lots of spreading, and it seems to result in much worse impulse performance then mp3. What is the current plan on handling this? Will a smart quantizer be able to avoid it? I've been looking at various ways of

Hi r-users, I have a matrix B and a list of 3x3 matrices (mylist). I want to calculate the quantiles in the list using each of the value of B as probabilities. The codes I wrote are: B <- matrix (runif(12, 0, 1), 3, 4) mylist <- lapply(mylist, function(x) {matrix (rnorm(9), 3, 3)}) for (i in 1:length(B)) { quant <- lapply (mylist, quantile, probs=B[i]) } But quant