Rao C.R. Computational Statistics with R

Amsterdam: Elsevier, 2014. — 396 p. — (Handbook of Statistics).A renaissance is currently in progress in all that is statistical. Those were the days when we used desk calculators to fit one of the Pearsonian distributions to the data collected from the field. Those were the days when we used punch cards on a computer occupying an entire large room to work out the Fisher’s discriminant function on a large multivariate data. Those were the days some people felt that all Statistics does were to indulge in some uninspiring drab calculations. Those days were gone. A revolution occurred with the advent of sophisticated computers. Size of the data was no hindrance in fishing information from the data. A number of statistical software programs mushroomed. Statistics made inroads into realms not ventured before. News paper articles mine vast amounts of data to hammer out the essence of the point under discussion.
Another revolution is occurring: personal computers and open source statistical software. If established statistical software were to be regarded as brand name palliatives, the free software R is generic doing as good as the brand name ones and more. The software R is empowering data analysts to venture deeper into data analysis. All it requires for empowerment is downloading R, which takes less than 5 min mostly. The software has more than 4000 packages. The Bioconductor package has more than 6000 packages.
Each is tailored to focus on certain statistical methodologies. Most packages have data sets and R codes specific to that package. Each code has documentation and examples of usage of the code. Anyone can develop a package. Figuratively, we can say that there are a million brains behind R, volunteering their time and effort to bring out a package. In any commercial software setup, a few dedicated groups of code writers are behind the software.
It is easy to immerse oneself into all that is R. All one needs is a laptop, an internet connection with R downloaded, and a decent working knowledge of Statistics. Running the examples provided in the documentation of the codes is educational and knowledge-fulfilling.
The handbook is addressed to those who have some background knowledge of statistics and some experience of usage of some statistical software and would like to explore what R can offer. We have requested experts to contribute to the handbook with the hope that the book will provide some basics and whet the appetite for more.Introduction to R
R Graphics
Graphics Miscellanea
Matrix Algebra Topics in Statistics and Economics Using R
Sample Size Calculations with R: Level 1
Sample Size Calculations with R: Level 2
Binomial Regression in R
Computing Tolerance Intervals and Regions Using R
Modelling the Probability of Second Cancer in Controlled Clinical Trials
Bayesian Networks