Statistical Tests

R and Rstudio

Added: 05/11/2017

  1. R is a language and environment for statistical computing and graphics. R provides a wide variety of statistical (linear and nonlinear modelling, classical statistical tests, time-series analysis, classification, clustering, …) and graphical techniques, and is highly extensible. You can download and install R for free here.

  2. Though R is self-sufficient, some prefer to use Rstudio along with R. Rstudio is a "quality of life" addition that provides a more user-friendly user interface a lot of users find helpful. You can download Rstudio for free here.

 

Ecoengine, R package for VertNet

Added: 11/15/2017

  1. Doing historical museum work sometimes require us to go through VertNet to look for specimens in collections. You can now use the package ecoengine by UC Berkeley to extract the data. 

  2. You can download the code we use here

 

Clopper-Pearson Binomial Confidence Interval to Calculate Error Bars for Prevalence Data

Added: 05/11/2017

  1. Basics of Clopper-Pearson Binomial Confidence Interval  
  2. Manual for the R package "binom"
  3. You can download the code we use here

 

Power Analysis for Likelihood of Detecting no Bd

Added: 10/10/2017

  1. Manual for the R package "reshape 2"
  2. You can download the code we use here

 

Bayesian Modeling for Bd Invasion Year Estimate

Added: 05/11/2017

  1. Manual for the R package "rJags" to run the iterations 
  2. Basics of MCMC Bayesian graphical models by Oxford University  
  3. An example of how the analysis was used in De Léon, Piovia-Scott, & Vredenburg, 2017
  4. You can download the code we use here 

 

GLM and Zero-inflated GLM for Environmental and Climate Data with Stepwise Regression

Added: 05/11/2017

  1. Beginner-friendly introduction to GLM by Colorado University
  2. Manual for the R package "pscl" used for zero-inflated GLM
  3. Comparing GLM to Zero-inflated GLM by UCLA
  4. Interpreting the output of GLM