ABSTRACT
The initial phase of every data analysis should include exploratory data evaluation (Tukey 1977). Once data are collected, they can exhibit a number of different distributions. Plotting your data and reporting various summary statistics (e.g., mean, median, quantiles, standard error, minimums, and maximums) allows you to identify the general form of the data and possibly identify erroneous entries or sampling errors. Anscombe (1973) advocates making data examination an iterative process by utilizing several types of graphical displays and summary statistics to reveal unique features prior to data analysis. The most commonly used displays include normal probability plots, density plots (histograms, dit plots), box plots, scatter plots, bar charts, point and line charts, and Cleveland dotplots (Cleveland 1985; Elzinga et al. 1998; Gotelli and Ellison 2004; Zuur et al. 2007). Effective graphical displays show the essence of the collected data and should (Tufte 2001):
1. Show the data. 2. Induce the viewer to think about the substance of the data rather than about
methodology, graphic design, or the technology of graphic production. 3. Avoid distorting what the data have to say. 4. Present many numbers in a small space. 5. Make large data sets coherent and visually informative. 6. Encourage the eye to compare different pieces of data and possibly differ-
ent strata. 7. Reveal the data at several levels of detail, from a broad overview to the
fine structure. 8. Serve a reasonably clear purpose: description, exploration, or tabulation. 9. Be closely integrated with the numerical descriptions (i.e., summary statis-
tics) of a data set.
