It depends entirely on the field you are in. What's regarded as an unreasonably low correlation in (say) physics may be unreasonable high in (say) psychology. HTH -- This message was distributed by s
My boss is doing some analyses comparing two groups on a continuous variable. In one case, the n in one of the groups is 4 (total N is 120). A regular t-test was highly significant (for the larger g
In the STRIPPLOT function, jitter is a logical flag. But even with JITTER = TRUE, the amount of jitter is fairly small. Is there a way to increase it? Thanks in advance Peter Peter L. Flom, PhD Assis
Isabelle asked Then my question is: how does one choose which setting of minbucket is appropriate for their problem? Because I get quite different results with minbucket=1 then if I leave it on the d
I am using S-Plus 6.0 on a Windows machine. Is there a way to get either plot.rpart and text.rpart to use multiple pages? Thanks in advance Peter Peter L. Flom, PhD Assistant Director, Statistics an
I am starting to explore trellis graphics. Looking at various sources (e.g. Cleveland; Venables & Ripley etc.) I see lots of good examples using various panel functions (e.g. panel.xyplot), but I hav
Thanks to all who replied. A summary of replies: Several people referred me to the Programmer's Guide, which is indeed quite helpful. Not sure why I didn't think of it on my own, but I didn't. Regard
I am running 6.0 on a Windows 98 machine. I tried the following command sas.get ('C:\\NDRI\\Stat core\\consults\\Don\\data', tree, formats = F) and got the following error Problem in sas.get("C:\\NDR
Thanks to Carlos Alzola, who pointed out that the word tree had to be in Peter Looks like your 'tree' should be in quotes. Carlos Alzola calzola@cox.net (703) 242-6747 I am running 6.0 on a Windows 9
(I hope this one isn't just a typo.....) I ran don.tree <- sas.get("C:\\NDRI\\Stat core\\consults\\Don", "tree", sasprog = 'C:\\Program Files\\SAS Institute\\SAS\\V8\\sas', formats = F) and got the f
Thanks to the several people who suggested possible fixes. These included using a path name with no blanks (Brian Ripley) Checking that the right SAS engine (v.6 vs. v 8) was being used (Gerry Blais)
I am running S-Plus 6 on a Windows machine. I am trying to fit a classification tree with independent variables that are ordinal. However the result does not take the ordinalaity of the variables in
I am trying to fit a multinomial model using model1 <- multinom(method~sex2 + harddrug) where method is a factor with 4 levels. It was my understanding that this would give me 3 formulas (using one
I am attempting to create a Quantile plot comparing values of ypsx (a vector with 528 cases, mean = 5.6) to a Poisson with the same mean. I don't expect this to fit well, but want to use it as a sta
This is probably very easy, but I can't get it..... I have 3 columns of data: V1 is categorical (A or B); V2 and V3 are continuous. I'd like to get a plot with two regression lines, each of Y ~ X, do