Linear Models with R
Books on regression and the analysis of variance abound-many are introductory, most are theoretical. While the majority of them do serve an objective, the actual fact remains that data analysis can't be properly learned without actually carrying it out, which means utilizing a statistical program. There are several to choose from as well, all with their unique strengths and weaknesses. Lately, however, one particular package has begun to go up above others because of its free availability, its versatility as a program writing language, and its own interactivity. That software is R.
In the first book that directly uses R to instruct data analysis, Linear Models with R targets the practice of regression and analysis of variance. It obviously demonstrates the various methods available and more importantly, where situations each one applies. It covers all the standard topics, from the fundamentals of estimation to missing data, factorial designs, and block designs, but it offers discussion on topics also, such as model uncertainty, addressed in books of the type rarely. The presentation incorporates a good amount of examples that clarify both use of every technique and the conclusions you can draw from the results. Every one of the data sets found in the book are for sale to download from http: //www.stat.lsa.umich.edu/ faraway/LMR/.
The author assumes that readers know the requirements of statistical inference and also have a basic understanding of data analysis, linear algebra, and calculus. The procedure reflects his view of statistical theory and his belief that qualitative statistical concepts, while more challenging to learn somewhat, are just as important because they allow us to apply statistics rather than simply discuss it.