Course Description

This course covers issues related to the proper manner in which to develop and conduct a research project. Statistical issues related to environmental evaluations will be discussed, including minimal detectable levels, proper sample size, and determination of proper methods for evaluation of data, using both parametric and non-parametric procedures.

Course Materials

Section	Topic	Additional Reading
01	Introduction to R	Software Carpentry - Intro to Programming
02	Variables and data.frames	Data Carpentry - Exploring and Understanding Data
03	Data Visualization and Exploration	R Graphics Cookbook; R4DS - Data Vis
04	R Programming	Software Carpentry - Intro to Programming
05	Data Wrangling	Data Carpentry - Working with Data
06	Introduction to Probability	Vu & Harrington - Chapter 2: Probability
07	Probability Distributions	Vu & Harrington - Chapter 3: Distributions of random variables
08	CLT and Confidence Intervals	Vu & Harrington - Chapter 4: Foundations for inference
09	Introduction to Hypothesis Testing	Vu & Harrington - Chapter 5: Inference for numerical data
10	Introduction to ANOVA	Vu & Harrington - Chapter 5: Inference for numerical data
11	Interpreting ANOVA Coefficients	video, Rmd file
12	Correlation and Regression	Vu & Harrington - Chapter 6: Simple linear regression
13	Understanding Regression Coefficients	video, Vu & Harrington - Chapter 6: Simple linear regression

Practice Assignments

Topic	HTML	Rmd
Practice with Rmd and data.frame summaries	assignment 1 - web	assignment 1 - Rmd
Practicing with ggplot2	assignment 2 - web	assignment 2 - Rmd
Practicing with functions	assignment 3 - web	assignment 3 - Rmd
Working with data	assignment 4 - web	assignment 4 - Rmd
Data report - NYS Spills Incidents	data report 1 - web	data report 1 - Rmd
Calculating confidence intervals	assignment 5 - web	assignment 5 - Rmd
Data report - Soil nutrients on a college campus	data report 2 - web	data report 2 - Rmd

Supplementary Notes

These notes go along with the videos I’m posting:

• Multiple Linear Regression - video, notes, Rmd file
• Multiple Linear Regression with Interaction - video, notes, Rmd file
• Analysis of Covariance (ANCOVA) - video, notes, Rmd file

Analysis Project Overview

During the semester, you will carry out an independent research and analysis project, using the skills we learn in this class. The project represents 30% of your grade, but is broken up into several components.

Guidelines and Requirements

• Your analysis project should be submitted in both *.Rmd and *.docx format on the course Blackboard page
• Your write up should include the following sections
  • Introduction (approx. 250 - 500 words) - an overview of the data set you are using in your analysis. If you generated the data yourself, describe how you collected these data. If you are using data from another person’s or group’s project, describe why and how these data were collected by that individual or group.
  • Research Question (approx. 250 - 500 words) - describe your research question that you are trying to answer with these data. Why is this question important in a broader context (i.e., with respect to environmental science in general).
  • Statistical Analysis (approx. 500 - 750 words) - describe the analysis you are using to answer your question. Why is this the most appropriate analysis for your data and question? What assumptions are there in this analysis? Do you data meet these assumptions? If not, how much of an influence might these violations have on the interpretation of your results? Are there any other studies that have used a similar analysis to answer a similar question?
  • Results (approx. 500 - 750 words) - provide a description and interpretation of your results.
• You should include any and all in text citations and a works cited section to support your description of your data, question, analysis choice, and results interpretation.
• Figures and Tables - you should include any and all figures and tables that support your analysis. Each figure and table should have it’s own caption that stands alone from the paper in briefly describing what information the figure/table is meant to convey.

Resources

Here are some useful resources for learning R, biostats, research methods, and grants.

Textbooks

• Introductory Statistics for the Life and Biomedical Sciences - by Vu and Harrington; An open-source textbook published by the OpenIntro group. This is a very good overview of biostatistics that can be adapted for many class levels. The PDF version of this text can be downloaded for free.

R

• Quick R - A site filled with great tutorials on basic and advanced stats methods in R. Also has good plotting resources.

• Cookbook for R - Another great site for all things R. Especially good resource for making ggplot2 plots.

Biostats

• Diagram of distribution relationships - Here’s a good site outlining the different relationships between various statistical distributions. It’s based on a well known paper by Leemis and McQueston.