Geen Tomko asks:
Can you recommend a good introductory book for statistical computation? Mostly, something that would help make it easier in collecting and analyzing data from student test scores.
I don’t know. Usually, when people ask for a starter statistics book, my recommendation (beyond my own books) is The Statistical Sleuth. But that’s not really a computation book. ARM isn’t really a statistical computation book either. But the statistical computation books that I’ve seen don’t seems so relevant for the analyses that Tomko is looking for. For example, the R book of Venables and Ripley focuses on nonparametric statistics, which is fine but seems a bit esoteric for these purposes.
Does anyone have any suggestions?
Here are some (more) good R books;
Dalgaard, Introductory Statistics with R – introduces both statistics and programming
Braun and Murdoch, A First Course in Statistical Programming with R – more for programmers learning statistics, than the other way round
Chambers, Software for Data Analysis: Programming with R – good if you want something more advanced
IPSUR may be a little broad, but reading it would definitely enable someone to analyze student test scores.
http://ipsur.r-forge.r-project.org/book/index.php
I had my introduction to R with the Julian Faraway books:
Linear Models with R
and
Extending the Linear Model with R
I thought they were relatively informative. I think the code is a bit outdated in some instances, but it worked for the first R-based class I took in 2007/2008.
I almost forgot, IPSUR is super easy to install.
install.packages("IPSUR")
Andy, you're being too modest. ARM is a terrific book for getting warmed up with statistical computation and data management, in addition to learning concepts. I think the original poster should start there.
Not to sound like a toady, but I still like Gelman and Hill's regression book better than everything else I've seen.
I don't think the requester wanted to learn how to program the models but rather how to analyze the models with an existing system like R. For learning how to code the models you could start with Bishop's machine learning book, though it presupposes a pretty sound knowledge of calc and matrices.
My recommendation is not a book, but I would suggest taking a look at Cosma Shalizi's classes notes about programming (using R).
It's available at his blog.
http://cscs.umich.edu/~crshalizi/weblog/727.html
The following notes could be useful to anyone interested for a quick introduction to R
http://stats.lse.ac.uk/baurdoux/CS/Lecturenotes.p…
Computational Statistics by Hoeting and Givens is the best I've seen. Covers all the basics, and focuses on more useful modern methods. If you want to actually learn about the methods, and not just how to use R, it's a good choice.
A very readable introductory textbook (suitable for undergraduates) is
Scientific Programming and Simulation Using R by O. Jones, R. Maillardet, and A. Robinson, CRC Press, 2009.