In this phase, we’ll learn the basics of data analysis by working through 5 learning modules devoted to core topics in the field. This will most likely be the most challenging part of the course because many, if not most of you will not have ever designed and built instruments and data acquisition systems, let alone analyzed data from them. Rest assured, your experience will be curated, sticking to the bare bones of instrument design and data science. This introductory phase will set the groundwork for Phase II, the independent development of sensors and data analysis.
In this module we’ll tackle where to find resource you’ll need on a week-to-week, module-by-module basis. In addition, we’ll work on the first important topic of the course: an introduction to R, an ever more popular language for data analysis and visualization. We’ll focus on the basics of importing and tidying data in R. By importing, we mean loading data collected by scientists and stored in text files, the common currency of scientific analysis. By tidying, we mean preparing data for analysis.
Wednesday, 8/28: Establish GitHub account and add your handle to this form
Wednesday 9/3: WCR 1
Sunday, 9/8: Commit Module 1 Project report
All assignments are due at 11:59 on the specified date.
for loopUpon completion of this week and module, students will be able to:
for loop in R to automate a
interatively redundant task.From Hands on Programming with R (HOPR)
When reading through HOPR, make sure to have R and R Studio up and running so that you can copy and paste code from HOPR into an R file and run the specified commands and complete the books project tasks. This will help tremendously in getting the hang of things.
From Happy Git with R
Be sure you’re familiar with the prerequsites outlined in Chapter 12. We’ll cover git and github in class on August 28th. Just introduce yourself to the concepts.
Check out the new github access token requirements.
for loop work and when should it be
used?This module is intended to give students the background and skills to begin simple data tidying and transformation operations. We need our data to be tidy before we can analyze it, that is, structured in a way that makes analysis possible. In addition, often the data we have aren’t exactly what we want to analyze. In this module, we’ll focus on how to read, tidy, and merge data.
Sunday, 9/15: commit Module 2 Project report
Upon completion of this week and module, students will be able to:
All form R for Data Science (R4DS):
All from the Wrangle Section of R4DS:
In Module 3, we’ll cover the basics of visualizing and modeling data
and hypothesis testing. We’ve used some simple visualization techniques
in ggplot already and we’ll leverage this introduction to
dig deeper into how data can be plotted to explore and ask informed
questions about it. In addition, we’ll learn how and when to compared
the fit of models.
Sunday9/22: Commit Module 3 Project report
ggplotUpon completion of this week and module, students will be able to:
ggplot environment.All form R for Data Science (R4DS):
Chapter 3:Data Visualiation
Section IV: Models
From Phylogenetic Comparative Methods by Luke Harmon [don’t worry too much about the mathematics, focus on the definitions and concepts]
ggplot?In Module 4, we’ll cover the basics of authoring reports in R Markdown, a markup language used to communicate the results of analysis in R. With R Markdown, you’ll develop a framework for compiling ideas, code, and graphics in one reproducible document.
Sunday, 9/29: Commit Module 4 Project Report
Upon completion of this week and module, students will be able to:
In Phase II, we’ll use our new-found instrument- and code-development skills to address key questions in organismal biology. These will be self-guided explorations of instrument design and use and data analysis meant to challenge you to put these skills to good use in answering how vertebrates muscles work, phylogeny matters in physiological systems, and how a changing climate impacts the distribution of vertebrates. Within this phase we’ll break up into our teams to focus on 4 modules, some data driven, the others both data and instrument driven.
This module puts our newly formed data analysis and markdown skills to use in answering how head shape has evolved in the Actinopterygii (i.e., the ray-finned fishes). Specifically, we’ll test head shape has evolved differently between major groups within the lineage.
Thursday, 10/10: Upload data Sunday, 10/20: Commit Module 5 Project Report
Upon completion of this module, students will be able to:
Sunday, 11/10: Commit Module 6 Project Report
In this module, we’ll explore the phenology of spring arrival timing
for neotropical passerines as it relates to historical weather
conditions. To do so, we’ll download species occurrence data from the
Global Biodiversity Information Facility (GBIF), an international
network and data infrastructure whose goal is to provide users open
access to data about all types of life on Earth. We’ll access GBIF data
using rgif, an R
package that permits access to GBIF’s application programming interface
(API). An API permits a user to interact with multiple software pieces
(databases, code sources for processing and analysis, etc.). To assemble
historical weather data, we’ll also use another R package,
rnoa. This package contains functions that interact with NOAA’s National
Climatic Data Center’s API.
Sunday, 11/24: Commit Module 7 Project report
Upon completion of this week and module, students will be able to:
Wednesday,12/16: Commit Final Project report
In Phase III, you’ll be tasked with quickly developing a project of your own design that either (1) requires the fabrication of a new or modified data acquisition system or (2) the acquisition of data from a peer-reviewed study or database. The goal of this project is to answer a question personal and interesting to your team. The question should be new within the context of the course and reflect a physiological focus (i.e., not ). This project will require you to first delve into the the scientific literature to set the stage and then leverage your new data-analysis and report-writing skills in the synthesis of 4-5 page markdown. This final project report should follow the same format and requirements of the reports produced in Phase II, but with expanded content.
More details about the final project and its expectations can be found here.