S-news readers, I am soliciting advice for how to edit s-plus graphs and plots. By edit, I mean annotate or modify existing graphs and plots. My experience has been that although it is possible to ad
S-News readers, I would like to combine greek symbols and regular text in the axis labels of my plots. I suspect that this is a common problem/question, and I would appreciate some tips or pointers t
S-News readers, I'm interested in learning about the algorithms used to compute empirical or sample semivariograms. I have S+SpatialStats, for example, so I have the means for calculating empirical s
S-News readers, One of the nice things about using the na.exclude option for the na.action argument of lm() and glm() is that the fitted() function will pad the fitted values vector with NAs as place
S-News readers, I was wondering whether anyone had S-PLUS code or examples for estimating the parameters of a variogram model (e.g., exponential, spherical) using restricted maximum likelihood (REML)
Hi S-news readers: I'm looking for an easy way to calculate standardized regression coefficients for a regression model e.g., either lm() or glm(). By standardized, I mean: Bi = bi * sqrt(sum(xi)/sum
Hi S-News readers, I'd like to generate random vectors of length n that contain of N 1s assigned to random positions within the vector and n-N 0s elsewhere. So for example, a vector of length 8 with
S-news readers, I'd like to add the model formula to a plot as a subtitle. In general, using as.character(fit$call)[2] works pretty well for a model fitted using lm() for example. However, I've notic
S-news readers, "Distances" between pairs of observations are used frequently in multivariate analyses, and the dist() function will calculate the euclidean distance, or a few other distance metrics,
Hi S-news readers, I've been trying to use the round() function along the key() function to display regression coefficients in the legend for a plot. I'd like to make sure that all the numbers are fo
S-News Readers, Does anyone have experience in using lme() and corSpher() or corExp() to fit linear models with a spatial covariance structure using REML? I have been using S+SpatialStats and nls() t
Hello S-News readers, It is straightforward to use the standard S-PLUS plotting functions to depict the point locations of my field sampling quadrats, create contour plots, etc., but I would like to
I suspect that there is a simple solution to this programming problem, but so far it eludes me. I am trying to write a function that allows me to plot variables from a dataframe without specifying t
I need some help with a data manipulations problem. I have several data files (dataframes), one for each of 3 sites, with the following variables/columns: plot#, tree#, species, basalarea In other w
I've been reading everything that I can find about contrasts in S-PLUS, but unfortunately I still don't get it. I've included below the data from a homework problem that I had a few years ago where
S-News readers, In my attempt to better learn my way around S-PLUS, I'd like to write a function that would calculate a confidence interval for an estimated regression coefficient. This effort has ra
S-News Readers, Following my question yesterday regarding how to access the variance-covariance matrix and sums of squares terms of a regression object, I have been investigating the output from the
I'd like to fit a model like the following: Y = B0 + B1*X1 + B2*X2 +B3*X1^2 + B4*X2^2 + B5*X1*X2 + e That is, the model is a polynomial of degree 2 with 2 predictors. Now as I understand, I should u
S-news folks, Pardon me if this has been asked and summarized before. I've poked around in the archives some but didn't find a recent discussion of the topic of Fortran compilers for use with S-PLUS
I'm looking for an easy way to add a diagonal 1:1 line to an existing scatter plot i.e., a line that extends from the lower left hand corner to the upper right hand corner. I've been plotting the re