[R] statistical help
M. Edward (Ed) Borasky
znmeb at aracnet.com
Fri Feb 23 20:39:32 CET 2001
On Fri, 23 Feb 2001, Antonio [iso-8859-1] Rodríguez Verdugo wrote:
> Briefly, I belong to a fisheries research group. At this time I'm working
> on my PhD and I'm looking for some statistical help. My mathematical and
> statistical skills are still scarce, I've gathered many different types of
> data (landings, climate and upwelling indexes, rains, etc) and I wonder
> about what kind of statistical procedure use with them. I'm a little
> confused about uni, bivariate, nonlinear, nonparametric, time series, etc
> terms. I'm looking for someone or maybe a research group to afford the
> implemantation of a statistical procedure to manage those data. Keeping
> always on mind the possibility of publishing our results.
Well, short of taking a "how to do research" course (which our Oregon Graduate
Institute has and *requires* its students to take), I have two recommendations:
1. Pick up a good book on "modern" exploratory data analysis. The classic, "EDA"
by Tukey, is very good, but I think there are better books on the subject.
2. Download R from CRAN (http://cran.r-project.org/), work through the
"Introduction to R" document, then look at some of the many example datasets.
There are many EDA tools built into R and I recommend exploring them first.
I've been doing computer performance analysis statistically for a little over
eight years now, and I still spend at least 80 percent of my time in exploratory
data analysis, looking at pictures. What I code and automate is the generation
of those pictures. Of course, this is a business situation and not a PhD
research situation -- the requirements are different.
Good luck with it!!
znmeb at aracnet.com (M. Edward Borasky) http://www.aracnet.com/~znmeb
I support the right to keep and arm bears.
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !) To: r-help-request at stat.math.ethz.ch
More information about the R-help