similar to: C Source code

Dear R People: Here is an interesting question(I think) Suppose I want to calculate Centered Moving Averages; i.e. x[1] <- ( sum(y[1:12]) )/12 x[2] <- ( sum(y[2:13]) )/12 and so on. Of course, this is easily done through loops. However, I have been trying to do this more elegantly, but have failed. I have tried things like j1 <- 1:109 j2 <- 12:120 x[1:109] <- ( sum( y[j1:j2])

Dear R People: I have the source for R version 1.1.1 on a UNIX system alpha-dec-osf4. The ./configure works fine. When I do the make, it works fine until it tries to build the package tcklc. I get an error of Tk_Saf_Init not identified Then it kicks out. Any suggestions, please? Thanks! Sincerely, Erin M. Hodgess, Ph.D. Associate Professor Department of Computer and Mathematical Sciences

Dear R People: Is there a function for exponential smoothing, please? R version 1.4.1 for Windows. Thanks in advance! Have a great weekend! Sincerely, Erin Hodgess Associate Professor Department of Computer and Mathematical Sciences University of Houston - Downtown 1 Main Street Houston, TX 77002 mailto: hodgess at uhddx01.dt.uh.edu

Dear R people is there a module for quality control, please? X bar charts, and such? perhaps a contributed package? Thanks in advance! Erin Hodgess Associate Professor Department of Computer and Mathematical Sciences University of Houston - Downtown 1 Main Street Houston, TX 77002 mailto: hodgess at uhddx01.dt.uh.edu

Dear R People: Here is a very simple question, please: I have a data frame with the state name, state division, and population. Note: state division is something like Atlantic, Mountain, etc. I want to produce a table with the state division and the total of the populations for the states within that division. I've been messing with "table" but so far, no luck. This is R1.3.1,

Dear R People: Do any of the linear model or regression function calculate the Durbin-Watson test statistic for serial correlation, please? I found the hat matrix, studentized residuals, and so on, but no D-W. Thanks so much! Sincerely, Erin M. Hodgess, Ph.D. Associate Professor Department of Computer and Mathematical Sciences University of Houston - Downtown One Main Street Houston, TX 77002

Hello, R People: How do I change the size of a graph, please? I tried par(cin=c(8.5,11)) and it said that Warning message: parameter "cin" can't be set in: par(args) > par(fin=c(8.5,11)) > plot(xa,ya) Error in plot.new() : Figure region too large Also, can I set for portrait or landscape, please? Thanks in advance! Erin M. Hodgess, Ph.D. Associate Professor Department

Dear R People: I'm trying to use the predict command on an arima0 object. I do the following: xm.arma <- arima0(xm2,order=c(1,0,1)) predict(xm.arma,n.ahead=2) and I get the message: Error in round(x, digits) : Non-numeric argument to mathematical function Any ideas what the problem might be, please? R version 1 4 1 on Windows. Thanks in advance! Sincerely, Erin Hodgess Associate

Hello, Although your message is not very explicit about the structure of your data frame, I think you can get what you want by using a combination of the function "split" and the "apply" functions family: apply, lapply and sapply. If you provide a more detailed organization of your data frame, perhaps we can give to you a more wiser advice. Thanks, Carlos. P.S: By the way,

Dear R People: I am drawing graphs for a College Algebra class. I would like to have the x and y axes, along with the lines that I am plotting. So I leave off the axes, and use xlim and ylim. Then I add my abline(v=0). However, I would like to have tick marks on the abline. How would I do that, please? Thanks in advance! Sincerely, Erin M. Hodgess, Ph.D. Associate Professor Department of

Dear R People: Does anyone have any code for Fractals, chaos, or anything like that, please? This is strictly for demo purposes...decorative only. This is R version 1.5.1 for Windows. Thank you in advance! Have a great weekend! Sincerely, Erin Hodgess Associate Professor Department of Computer and Mathematical Sciences University of Houston - Downtown 1 Main Street Houston, TX 77002

Hello R People: Suppose I create a function, x.e, via the fix command: > x.e <- fix(x.e) When I type in x.e, the function code appears, along with the name/number of the environment. However, if I create a function, y.e, and source it in, when I type in y.e, the function code only displays(no environment). Why is this, please? (It's not a bug....I just wondered). I am using

Dear R People: Here is a non-R probability question, please: There is a problem, originally posed from an American game show, called "Let's Make a Deal." A contestant makes a selection of one door, from Doors 1 through 3. He or she knows that there are 2 goats and 1 car behind those doors. Once the contestant makes the selection, say Door 2, then the host, Monty Hall, tells him

Dear R People: Is there a library for Multivariate time series, please? For some reason, I'm thinking that Dr. Paul Gilbert may have one? R Version 1.6.2 (i've updated!) for Windows Thanks so much! Sincerely, Erin Hodgess University of Houston - Downtown mailto: hodgess at uhddx01.dt.uh.edu

Dear R People: Suppose I put in the following: > w1 <- expression(2*x) > v1 <- expression(x^2) and I want to get the derivative of w1 * v1 with respect to x > D(w1*v1,"x") Error in w1 * v1 : non-numeric argument to binary operator Is there a way around this, please? Thanks in advance! Sincerely, Erin M. Hodgess, Ph.D. Associate Professor Department of Computer and

Dear People: Here is a non-R question, please: Does anyone use hevea for Windows to translate LaTex to HTML? If so, how do you get \bar, \sqrt, and \ne, please? I get an error message of unknown macro. Thanks in advance for any help! Sincerely, Erin M. Hodgess, Ph.D. Associate Professor Department of Computer and Mathematical Sciences University of Houston - Downtown One Main Street

Dear R People: Suppose I want to estimate the parameters of the following AR model: (1 - phi_1 B - phi_2 B^2 - phi_9 B^9) x_t = a_t and I want to use the arima0 command from the ts library. How would I use the order subcommand, please? R Version 1.4.1 for Windows. Thanks! Sincerely, Erin Hodgess Associate Professor Department of Computer and Mathematical Sciences University of Houston -

Dear R People: On the functions qqnorm and qqline, (found in the base package), what are the references, please? This is R for Windows, Version 1.4.1. Thank you so much! Sincerely, Erin Hodgess Associate Professor Department of Computer and Mathematical Sciences University of Houston - Downtown 1 Main Street Houston, TX 77002 mailto: hodgess at uhddx01.dt.uh.edu

Dear R people: I am trying to download the package polynom to R version 1.0.1.1. on Windows. Here are my commands and output: > install.packages("polynom",lib="c:\rw1011\library",CRAN="http://www.r-project.org/src/contrib/") Error in start[k]:(start[k + 1] - 1) : NA/NaN argument In addition: Warning message: Download had nonzero exit status in:

Dear R People: I have a few questions about multiple comparisons and contrasts for ANOVA, please. I've tried some things but with no success. Suppose I have a completely randomized design, and I want to have the contrast \mu_1 - 0.5 \mu_2 - 0.5 \mu_2 How do I set that up, please? I used the C command, and ran aov, but the results were identical to those with no contrasts. Also, is there