Target Audience: Biologists and others with little or no prior experience with R or statistics who need to collect and analyze data for purposes such as impact assessment and biological monitoring.
Summary and Objectives:
This course, along with Field Data Management using MS Access (CSP1003), is a foundational course in the toolbox series of courses that build skills in data management, data analysis, monitoring, and species distribution modeling. Two focal points of this class are improving abilities to think like a scientist (e.g., framing questions, choosing appropriate indicators, and following data analysis steps) and gaining a working knowledge of the R software package. Participants will use R for several tasks, including exploratory data analysis, cleaning and restructuring messy data, and hypothesis testing. Other important themes include estimating population parameters with uncertainty (confidence intervals) by formula and bootstrapping, determining what statistical tests are appropriate given the data type and distribution, estimating the power to detect change, and learning the basics of sampling design and types of statistical models. Depending on class needs, the course will conclude with use of either analysis of variance or simple linear regression as a bridge to the next course, Statistical Modeling for Conservation (CSP4210).
Upon completion of this course, participants will be able to:
- Use R software to manipulate, explore, analyze, and graphically display their field data.
- Estimate population quantities (e.g., density and mean wing length) based on data.
- Use bootstrapping techniques to resample data sets and create confidence intervals.
- Perform hypothesis tests and interpret p-values.
- Explore how sampling effort directly affects the ability to make conclusions from their data.
This blended course consists of guided asynchronous lessons and optional live time with an instructor.