Supplement 1. R script, results, and example data set provided to early-career ecologists for a survey of statistical methods used in a standard analysis.
Datasets usually provide raw data for analysis. This raw data often comes in spreadsheet form, but can be any collection of data, on which analysis can be performed.
acorn_analysis.Rmd (MD5: 8e0fe41f782f827ba9ae1fd0554a492a)
pairs-JSG.R (MD5: 6d965dbd767200c3acb5ea113d3768b1)
stats_data.csv (MD5: a715516b78895a535385fa3e36d674db)
selected_variables.csv (MD5: 05470bba822f24231a2dc3bd473b1ad8)
This supplement includes an R (R Core Team 2013) markdown script (acorn_analysis.Rmd) and required functions (pairs-JSG.R) that provides an analysis of the example data set provided to survey participants. The data set provided to survey participants (stats_data.csv) is a subset of data file from the paper "Walter D. Koenig and Johannes M. H. Knops. 2013. Large-scale spatial synchrony and cross-synchrony in acorn production by two California oaks. Ecology 94:83–93.http://dx.doi.org/10.1890/12-0940.1" downloaded from Ecological Archives. Seven of the original 13 environmental variables were selected based on a preliminary analysis of the full data set to reduce complexity of model fitting for participants. Columns were renamed for convenience of analysis in R. We in no way intend this as a criticism or an endorsement of the analysis performed by Koenig and Knops. We quite liked their paper, and simply selected this data set as it was freely available from Ecological Archives and fit our requirements of an observational study with a single response and many predictors. The file (selected_variables.csv) is a summary of the results from survey participants, listing each of the variables included in their final models.