**Resources Every Grad Student Should Peruse (sooner than later)**

- Modest Advice for Graduate Students
- The Academic’s Handbook

- The Chicago Guide to Your Academic Career: A Portable Mentor for Scholars from Graduate School through Tenure – a truly great resource for those considering an academic career or any time pre-tenure.
- Powell (2010) Publish Like a Pro.
- The Elements of Style: 50th Anniversary Edition – classic, short book on writing well

- Zuur et al. (2010) – excellent paper on the first step in the process of analyzing data pdf
- Ellison and Dennis (2010). Paths to statistical fluency for ecologists. Frontiers in Ecology and the Environment. – a must read for all ecologists and especially upper level undergrads and new graduate students.
- Cottingham et al. (2005). Knowing when to draw the line: designing more informative ecological experiments. Frontiers in Ecology and the Environment. – a good review of inference from ANOVA vs. Regression and how to design experiments with this in mind.
- Anderson et al. (2001). Suggestions for presenting the results of data analyses. Journal of Wildlife Management. 65(3): 373-378
- Writing Your Dissertation in Fifteen Minutes a Day or get the kindle version here
- Advice on Getting an Academic Job – for the masochistic individuals out there
- “So Long and Thanks for the PhD”
- Writing and Productivity in Academia – Quick article with good tips. I would add that you don’t have to have all your results and analysis done before you can start writing the methods and introduction of a paper.
- Linear Assumptions from the Analysis Factor – Assumptions of linear regression (and ANOVA) are about the residuals, not the normality or independence of the response variable (Y). If you don’t know what this means be sure to read this brief blog article.
- Generalized Linear Mixed Models (GLMM) – more thoughts (and example R code) on modeling count data and how to diagnose and interpret model fit.

**Books**

Models for Ecological Data: An Introduction (Clark) – While I like aspects of other ecological modeling books (Bolker, Zuur), I find Clark’s book to be the best (but with huge emphasis on Bayesian analysis). It gives lots background on modeling, statistical inference, and reviews probability theory plus matrix algebra, probability density functions, and some relevant calculus. The author uses a variety of understandable examples. Some books hold so tightly to a few examples that you have to read the textbook from the start to make sense of a particular example late in the book. This can cause a text to be of less use as a desk reference. Clark does a good job with the examples and the book can truly be used as a reference or can be read from cover to cover with equal utility. I recommend this book as essential reading for all ecologists. It includes an excellent introduction to Bayesian Statistical Inference and compares Bayesian and Frequentist approaches. An indispensable reference for ecologists. I also second the notion of purchasing the lab manual , if nothing else then for the examples of R code.

Statistical Computation for Environmental Sciences in R: Lab Manual for Models for Ecological Data (Lab Manual) – lab manual of exercises and R/WinBUGS code associated with Clark’s textbook (above).

Ecological Models and Data in R – Bolker gives better descriptions of the statistics and their use in R than most authors of R books. He provides excellent descriptions and diagrams/flow charts for determining what types of models to use (see especially page 301 figure 9.2). He also provides readily understandable and useful examples when discussing each model. Like most statistics books and virtually all programming books the code and text builds upon itself throughout the book making it slightly challenging to jump ahead to later chapters without extensive previous knowledge of statistics and R programming. The book covers a large range of modeling options and therefore omits some details on the statistics and testing the necessary assumptions. This is necessary for a book of this breadth. The reader should use this book to determine what models to use for their dataset and how to write the code in R but should consult a more detailed statistics book written about that specific approach. I would recommend this book for any ecologists interested in using R for data analysis. The first chapter (and then scattered throughout) is a very nice overview of philosophy of ecological modeling. It’s available online and it a must read, at least as a starting point, for anyone interested in statistical or ecological modeling.

Model Selection and Multi-Model Inference: A Practical Information-Theoretic Approach – This book by Burnham and Anderson is a must have for ecologists and conservation biologists.

Mixed Effects Models and Extensions in Ecology with R (Statistics for Biology and Health) – Zuur and colleagues do a good job with this book and I recommend it for any field biologists/ecologists will to take time to analyze their data well. There are good, understandable examples. It is not a statistics book but it has sufficient, clear descriptions of the statistical methods and why one model would be used rather than another.

Introduction to WinBUGS for Ecologists: Bayesian approach to regression, ANOVA, mixed models and related analyses – Kery does an excellent job introducing ecologists to the Bayesian framework and leading the reader step-by-step through WinBUGS and R2WinBUGS (used to interface R and WinBUGS which is WAY more convenient).

Bayesian Methods for Ecology – McCarthy presents a nice introduction to Bayesian Analysis for ecologists. There is a bit more on Bayesian theory than in Kery’s book (see above) and there are examples of WinBUGS code for basic analyses. I own both, but I would just get Kery’s book if I had to choose one. Neither book proceeds to the complex models where Bayesian analysis are most useful but both provide very well-writen, understandable introductions to Bayesian analysis and the associated software packages. I recommend Clark’s book on ecological models for more on the modeling aspect of the analysis (remember: model development and statistical inference are two very different parts of the data analysis process).

The bible for applied mixed models (linear, generalized linear, and nonlinear) is Pinheiro and Bates Mixed-Effects Models in S and S-PLUS (Statistics and Computing)