similar to: Time series, least squares line

Hi there, I'm plotting some glass RI values just by plotting plot(x) then I put on my lowess smoother lines(lowess(x)) now I want to put on some 95% Confidence Interval bands of the lowess smoother, but don't know how?? Thanks -- Gareth Campbell PhD Candidate The University of Auckland P +649 815 3670 M +6421 256 3511 E gareth.campbell@esr.cri.nz gcam032@gmail.com [[alternative

Hi, I'm doing anova on a matrix of multivariate data where I want to assess the effect of each column (element). My matrix is 86 rows x 31 columns. I've created a grouping factor of length 86 containing group assignments of 6 types. Then I run: x<- aov(matrix~grouping.factor) summary(aov.fit.raw, test="Wilks") This is working fine enough, but I'm getting different

Hi there, I know this is probably a really simple question, but without the correct keywords, or knowledge of the correct function it is hard to search for on the net or within R. How do I increment a dataframe (or similar) name within a loop and assign data? A simple example would be: for(i in 1:10){ test<-i } BUT I want it to be test[i] --- in other words I want my stored data to

Hello all, I'm dealing with geochemical analyses of some rocks. If I use the full composition (31 elements or variables), I can get reasonable separation of my 6 sources. Then when I go onto do LDA with the 6 groups, I get excellent separation. I feel like I should be reducing the variables to thos that are providing the most discrimination between the groups as this is important

Hey team, If I have a matrix: 1, 2, 3, 4, 4, 0, 1, 3, 0, 3 2 columns. I want to write an if command that looks at (in this case) row 3 and looks to see if either [3,1] or [3,2] has a zero in it. IF it does have a zero I want the zero to be placed in another matrix in the same position. I know how to do the latter part, I just can't get the if command to look at both cells and deal with

I have some data (REE plots - geochemistry) where I have values 1:14 for the x axis, but have no data for some x values. Here for example, let's say that I don't have data for x=2,5,8. So x<-1:14 y<-c(4, NA, 5, 9, NA, 3.4, 8, NA, 19, 22, 12, 14, 15.3, 15) if I plot the data plot(x,y) and then I want to join with lines lines(x,y) How do I get it so the points join across the

I have a vector: alleles.present<-c("D3", "D16", ... ) The alleles present changes given the case I'm dealing with - i.e. either all of the alleles I use for my calculations are present, or some of them. Depending on what alleles are present, I need to make matrices and do calculations on those alleles present and completely disregard any formula or other use of the

I've made an LDA model on some data from one source. I have some new data that I want to see if I can "place" to the sources in the LDA model. I used the predict function as follows: predict(wak.insitu.ld, wak.alr.alluvial) where wak.insitu.ld is an LDA model generated from some data and wak.alr.alluvial is new data of similar origin. When I look at the results, there is 86

Hi everyone, I have a PCA plot that I'm writing about in the text. There were so many symbols in different colours on it that I didn't include a legend in the plot as it would be useless. So what I was hoping to do was to talk about each set of replicates in the text and when I do that, use their coloured symbol in the text. So what I want to do is to get R to create some high quality

When I run a summary(anova) I get output for all of the elements (columns) as these are multiple - single anova results. Can I store the F values? I can't find the attribute of the fitted model attributes(fit) that stores these F values, and for that matter, P values. Thanks -- Gareth Campbell PhD Candidate The University of Auckland P +649 815 3670 M +6421 256 3511 E

Hello, What I am trying to do is: Generate a density plot of a population of data. This data has a bimodal distribution so I've isolated a couple of possible sub-populations and I want to overlay these two density plots over the first to see whether they are contributing to the bimodal population. I can do this fine with plot(density(...)) and lines(density(...)) . But the resulting plots

Hello, I have a matrix and I want to sample 20 rows that are the the percentiles of 0-100 in 0.05 increments. I have a vector of my sequence (0, 0.05, 0.10, 0.15,....1.0) and also a normalised vector of rownumbers. That is, there are 234 rows (for example) so I do perc<-c(1:234/234) which looks like a bunch of numbers from 0 - 1. In Excel (which I try not to use at every possible

Sorry, the code is incomplete. You get a better result this way... postscript('Circle.eps',paper='special',width=4,height=4) par(mar=c(0,0,0,0)) plot.new() points(0.5,0.5,pch=21,cex=50,bg='gray') dev.off() -----Mensagem original----- De: Rodrigo Aluizio [mailto:r.aluizio em gmail.com] Enviada em: ter?a-feira, 18 de novembro de 2008 19:28 Para: 'Gareth Campbell'

Hello I'm writing an example PCA analysis for some students. I've done PCA on a 2-column matrix to show it at the most simple form (a rotation of two axes). I can't, however, figure out how to plot the rotated axes as lines over top of the original data plotted on the x-y. Does anyone know how to do this? It will be a good way to show how the rotated axes describing the most

I'm trying to move my Asterisk deployments under a Virtual IP address and now remember why I dislike this. My primary Asterisk system is now behind a firewall in private address space. My question is what ports are needed to be opened just for the purpose of placing outgoing calls. I would have assumed none, but I can't even get replies on registration from any of my 3 VoIP providers.

I'm plotting a lattice bwplot from a data.frame and would like to add some horizontal lines indicating some reference values (preferably with text annotation) as well as a grid of regular log tics. The following illustrates the plot: data(ToothGrowth) require("lattice") p = bwplot(exp(len) ~ supp, ToothGrowth, panel = function(..., box.ratio) { panel.grid(h=-1,

Dear all, When doing nonlinear regression, we normally use nls if e are iid normal. i learned that if the form of the variance of e is not completely known, we can use the IRWLS (Iteratively Reweighted Least Squares ) algorithm: for example, var e*i =*g0+g1*x*1 1. Start with *w**i = *1 2. Use least squares to estimate b. 3. Use the residuals to estimate g, perhaps by regressing e^2 on

Hi All, I've found a few references in the mailing list and documentation to constrained least squares fitting, but little on restrained least squares. To clarify what I mean, a constraint might limit a parameter to a particular value (e.g. x=5.0, or exactly within the bounds 4.9 - 5.1), whereas a restraint adds some further information to the problem about the certainty of the starting point

I am using the non-linear least squares routine in "R" -- nls. I have a dataset where the nls routine outputs tight confidence intervals on the 2 parameters I am solving for. As a check on my results, I used the Python SciPy leastsq module on the same data set and it yields the same answer as "R" for the coefficients. However, what was somewhat surprising was the the

Dear R Users, I would like to make a lesast squares regression similar to that what is done by the command "lm". But additionally, I would like to impose some restrictions: 1) The sum of all regression coefficients should be equal to 1. 2) Each coefficient should assume a value between 0 and 1. (inequality restrictions) Which command is the best to use in order to solve this problem