similar to: Simulated annealing method with restarts

This was sent to me by someone on the R-list ( I don't know her ) but I don't have time to look at this right now so I told her I would send it to the R-list because she said it keeps getting bounced when she sends it. #======================================================================= ==================================================================== I am a bit confused with

Hi All, I created a two variable lm() model slm<-lm(y[1:3000,8]~y[1:3000,12]+y[1:3000,15]) I made two predictions predict(slm,newdata=y[201:3200,]) predict(slm,newdata=y[601:3600,]) there is no error message for either of these. the results are identical, and identical to slm$fitted as well. if this is not the right way to apply the model coefficients to a new set of inputs, what is

I have comma delimited asci data with each row being in the format : 2006-01-24 02:41:24.00011,1.22930000,5,1.22950000,7 . . . . and i'm trying to use read.zoo ( which is similar to read.table ) to read in the data. the data goes all the way out to milliseconds and i can't figure out what to put for the format field. if i put nothing, then read.zoo gets rid of the the whole time and

I did a ?do.call but i don't think i understand it. if a, b,c,d are numeric vectors then could someone explain the difference between do.call("cbind",list(a,b,c,d)) and cbind(a,b,c,d). or point to an archive on it. the return value of cbind is a matrix or dataframe depending on what is sent in but i don't understand wheen it would be useful to use do.call. i realize it

I have two numeric vectors each of length 17 and each is named the exact same way. so obsnum ppppp ppppm pppmp . dot dot dot...... temp1 is 1417 52 63 85 obsnum ppppp ppppm pppmp . dot dot dot...... temp2 is 1213 41 50 97 what i want to have is a resultant matrix with 2 rows and 16 columns where the 16

A development note: In the function "install.packages", it would be helpful to those of us who have atypical installations and install manually from ZIP files to have pkgnames <- sub("\\.zip$", "", pkgnames) replaced with pkgnames <- sub("\\.zip$", "", pkgnames, ignore.case = TRUE) because the contributed zipfiles are ZIPfiles. The

A development note: In the function "install.packages", it would be helpful to those of us who have atypical installations and install manually from ZIP files to have pkgnames <- sub("\\.zip$", "", pkgnames) replaced with pkgnames <- sub("\\.zip$", "", pkgnames, ignore.case = TRUE) because the contributed zipfiles are ZIPfiles. The

I have some time series data like 01/02/1990 0.531 0.479 01/03/1990 0.510 0.522 01/06/1990 0.602 0.604 there is no weekends and holidays. how do I graph them in a single plot that the x-axis is the dates and the y-axis is the time series? Thank you Regards, Jincai Jiang (Office) 212-761-3984 -------------------------------------------------------- This is not an offer (or solicitation

I am trying to fit a B-spline regression model with a corStruct using gls. I am using bs() and specifying the knots myself. If I make the knots data-dependent, this works but has undesirable side-effects. I prefer to reference an auxilliary variable "knots" in my model formula. It should not be part of the data frame, as it is a vector of a different length. How can this be done? The

Hi : Whenever I try to run R in a second session( but not in the same working directory ) , I get the error below Error in dyn.load(x, as.logical(local), as.logical(now)) : unable to load shared library '/u/etlfs/dev/users/leedsmar/res/R/lib/chron/libs/chron.so': /lib/i686/libc.so.6: version `GLIBC_2.3' not found (required by

i am looping and creating plots which are coming to the screen. i am in linux and remember ( in a previopus life ) i used to use a command so that the next graph n + 1 didn't appear on the screen until i hit the return key after graph n appeared. i thought i remeber using the command unix but when i type unix at the r prompt, it gices me system. it's probably a deprecated command then but

I have a question and it's only relation to R is that I probably need R after I understand what to do. Both models are delta y_t = Beta + epslion and suppose I have a null hypothesis and alternative hypothesis H_0 : delta y_t = zero + epsilon epsilon is normal ( 0, sigmazero^2 ) H_1 delta y_t = beta + epsilon epsilon is normal ( sigmabeta^2 )

as jim pointed out ( i think we were figuring this out simultaneously. thanks a lot jim ), it looks it does have something to do with the fact that it's a zoo object because below i consider two cases. in the first case, fxdatab is a zoo object and i get the length of temp to be 1. in the second case, fxdatac is a matrix and the results in temp are correct. gabor : i really hate to bother

Thanks to Peter Dalgaard , I have made some decent progress as far as getting R to work in linux . I just want to set my environment variable R_LIBS to /u/etlfs/dev/users/leedsmar/R/library ( in linux ) so that I can install specific packages. Does anyone know the syntax and in which file I set this variable ( .Rprofile etc ). I've looked in the installation manual ( i'm mainly on pg 14

I familarized myelf with kalmanlike and structts which are approaches for building and estimating ( and forecasting ) state space models ( or the equivalent arima models ). back in 2003, gavin simpson wrote an email describing the west and harrison apprach to estimate state space models and asked if anything was out there for using that approach. the goals of this approach are the same as kalman

Yes you are right ... an example is mandatory. So ... I have a matrix of 0 with just a single 1 per row and per column I need to extract all maximal 'diagonal' submatrices Let's say I have the following matrix A B C D E a 0 1 0 0 0 b 1 0 0 0 0 c 0 0 1 0 0 d 0 0 0 1 0 e 0 0 0 0 1 well I would like to get, for this example, the two following submatrices A B C D E

i'm doing a bar plot and there are 16 column variables. is there a way to make the variable names go down instead of across when you do the barplot ? because the names are so long, the barplot just shows 3 names and leaves the rest out. if i could rotate the names 90 degrees, it would probably fit a lot more. or maybe i can use space to make the horizontal width longer ? I looed up ?barlot but

hi everyone : i'm trying to rotate the x axis labels in my barlot ( yes, since yesterday ) and my prob12matrix is 2 rows and 16 columns and i followed the instructions in the archive "rotate barplot labels". i was really looking forward to seeing my labels turned but the plot just came back with no labels ? can anyone see what might be going on ? it worked when i followed the

this one is not a false alarm like my previous message. i have cut and paste the code below so if anyone could run it would be appreciated. basically, my question is why the horizontal axis of the acf plot is labelled with such huge numbers when the labels should be 1 through 10 since may lag.max = 10 ? i looked at the cdoe of acf but it was pretty much beyond me. i think it has something to

when i do ?whatever at the R prompt ( i use linux ), the help comes up but it comes up like a man page. i would prefer to send it to a file. i did a ?help and it says something about sending the output to a file but nothing specific enough that i can figure out what to do. the help page talks about a parameter called "type" but as far as i can tell, there is no "type" parameter