similar to: using predict() with poly(x, raw=TRUE)

Hi In the following, the graph I see on the screen and the .png output coincide. However, in the .pdf file, the fonts seem to be scaled fairly larger, resulting in the label for the top legend disappearing. Is this an infelicity or bug, or is there something I've missed? More generally, how do I control the size of fonts used in legends and axis labels? library(car) library(ggplot2) qp

Dear R experts, I am observing undesired behavior of predict(fit, newdata), in case when fit object is produced by lm() involving a poly(). Here is how to reproduce: x <- c(1:10) y <- sin(c(1:10)) fit <- lm(formula=y~poly(x, 5, raw=TRUE)) predict(fit, newdata=data.frame(x=c(1:10))) ## this works predict(fit, newdata=data.frame(x=c(1:1))) ## this is broken, error below Error in poly(x,

Bug in predict.lm & poly The predict function doesn't work when used with poly and newdata. For example, I'd expect the following code to work, and plot a fitted cubic to the nearly straight line: x <- 1:10 y <- x + rnorm(10)/100 plot(x,y) fit <- lm(y ~ poly(x,3)) newx <- seq(1,10,len=100) lines(newx,predict(fit,newdata=data.frame(x=newx))) However, the plotted

Dear R list members, I'm encountering a problem with expand.model.frame(): Suppose that I define the following simple function (meant just to illustrate the problem): > fun <- function(model){ + expand.model.frame(model, all.vars(formula(model))) + } > and I have the following model, created with an explicit data argument: > mod Call:

Dear R-devel list members, I'd like to suggest a more flexible procedure for generating contrast names. I apologise for a relatively long message -- I want my proposal to be clear. I've never liked the current approach. For example, the names generated by contr.treatment paste factor to level names with no separation between the two; contr.sum simply numbers contrasts (I recall an

Dear list users How is it possible to visualise both a linear trend line and a quadratic trend line on a plot of two variables? Here my almost working exsample. data(Duncan) attach(Duncan) plot(prestige ~ income) abline(lm(prestige ~ income), col=2, lwd=2) Now I would like to add yet another trend line, but this time a quadratic one. So I have two trend lines. One linear trend line

Dear R-help list members, I'm encountering problems using expand.model.frame. To illustrate, consider the function > test <- function(model){ + expand.model.frame(model, "income") + } > The data frame Prestige (from the car library) has several variables, including prestige, income and education. I've attached this data frame >

Dear Trevor, I've noticed a discrepancy in the degrees of freedom reported by gam() from the gam package in R vs. gam() in S-PLUS. The nonparametric df differ by 1; otherwise (except for things that depend upon the df), the output is the same: --------- snip ------------ *** From R (gam version 0.93): > mod.gam <- gam(prestige ~ lo(income, span=.6), data=Prestige) >

Hello, I''m inexperienced with linux, X11 and R. A font problem have surfaced. When I use pairs in John Fox''s car library e.g.: > pairs(cbind(prestige, income, education, women)) Error in text.default(x, y, txt, cex = cex, font = font) : X11 font at size 16 could not be loaded In addition: Warning message: freeing previous text buffer in GText > Evidently

I've encounted a problem using expand.model.frame. To illustrate, consider the function > test <- function(model){ + expand.model.frame(model, "income") + } > The data frame Prestige (from the car library) has several variables, including prestige, income and education. I've attached this data frame and fit the following model >

Hello, Much clearer now, thanks. It's a matter of changing the function boot calls to return the predicted values at the point of interess, education = 50, income = 75. I have changed the way the function uses the indices a bit, the result is the same, it's just the way I usually do it. pred.duncan.function <- function(data, indices) { mod <- lm(prestige ~ education +

I am getting an error message from scatterplot: > library(car) > scatterplot(Prestige$income~Prestige$type) Error in Summary.factor(c(2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, 2L, : range not meaningful for factors In addition: Warning message: In Ops.factor(x[floor(d)], x[ceiling(d)]) : + not meaningful for factors > The command does output the kind of graph that I want (boxplots).

The poly() function can create more variables than can be fitted when there are replicated values. In the example below, 'x' has only 5 distinct values, but I can apparently fit a 12th-degree polynomial with no error messages or even nonzero coefficients: R> x = rep(1:5,3) R> y = rnorm(15) R> lm(y ~ poly(x, 12)) Call: lm(formula = y ~ poly(x, 12)) Coefficients:

Full_Name: Russell Lenth Version: 2.6.2 OS: Windows XP Pro Submission from: (NULL) (128.255.132.36) The poly() function allows a higher-degree polynomial than it should, when raw=FALSE. For example, consider 5 distinct 'x' values, each repeated twice. we can fit a polynomial of degree 8: ===== R> x = rep(1:5, 2) R> y = rnorm(10) R> lm(y ~ poly(x, 8)) Call: lm(formula = y ~

Dear all, I am trying to transform polynomial coefficients from orthogonal form to the standard power basis. There's poly.transform in S-plus. Does anybody know how to do that in R ? I've found question about that in the archives of R-help but no real answer. Example : I'm doing polynomial regression of percentage of one insect in a community on altitude, precipitations,

I ran into a to me surprising result on running lm with an orthogonal polynomial among the predictors. The lm command resulted in Error in qr(X) : NA/NaN/Inf in foreign function call (arg 1) Error during wrapup: despite my using a "subset" in the call to get rid of NA's. poly is apparently evaluated before any NA's are subsetted out of the data. Example code (attached to

Often in practical situations a predictor has missing values, so that poly crashes. For instance: > x<-1:10 > y<- x - 3 * x^2 + rnorm(10)/3 > x[3]<-NA > lm( y ~ poly(x,2) ) Error in poly(x, 2) : missing values are not allowed in 'poly' > > lm( y ~ poly(x,2) , subset=!is.na(x)) # This does not help?!? Error in poly(x, 2) : missing values are not allowed in

By any chance is anyone aware of an R function that duplicates Octave's poly function? Here is a description of Octave's poly function: Function File: poly (A) If A is a square N-by-N matrix, `poly (A)' is the row vector of the coefficients of `det (z * eye (N) - a)', the characteristic polynomial of A. As an example we can use this to find the eigenvalues

DDear developeRs, about a year ago, Alex Stolpovsky posted an issue with predict.lm on a fit generated using poly with the raw=TRUE option and too few new data (slightly modified reproducible example below). Alex did not get any reply. I have just stumbled on the same problem, and I think that this is a bug of function poly, which arises from the check whether the polynomial degree is

Hi, I am curious about how to interpret the results of a polynomial regression-- using poly(raw=TRUE) vs. poly(raw=FALSE). set.seed(123456) x <- rnorm(100) y <- jitter(1*x + 2*x^2 + 3*x^3 , 250) plot(y ~ x) l.poly <- lm(y ~ poly(x, 3)) l.poly.raw <- lm(y ~ poly(x, 3, raw=TRUE)) s <- seq(-3, 3, by=0.1) lines(s, predict(l.poly, data.frame(x=s)), col=1) lines(s,