Evaluators have access to an ever-increasing array of technologies that add efficiencies to their workflow and enhance evaluation products. Dedicating the time necessary to become proficient in any one of them to realize these efficiencies takes time and, often, a bit of self-taught learning. R is one such powerful tool, and its open-source framework lends itself to a variety of applications. Specific to the field of evaluation, it is a data wrangling, analysis, visualization, reporting, and documentation software all-in-one. It's open source nature contributes to its flexibility and adaptability in ways that competing software struggles. This same feature makes it a daunting endeavor for individual evaluators or teams to embrace: support and troubleshooting is conducted via online forums typically used by "coders" and many evaluators can be intimidated by learning to code.
As our world becomes more data-centric and data-rich, evaluators need to employ tools to build efficiencies in their data management, analysis, and reporting workflows in order to make sense of an ever-growing data environment. R allows for reproducible and standardized procedures across the data and reporting continuum. Files can be accessed on any computer platform without expensive software and the entire process can be completed in one software. Building greater efficiencies into one's evaluation practice allows an evaluator to dedicate more time and resources into the critical evaluator competency domains of context, planning and management, interpersonal, and professional practice.
This three-part professional development series will introduce evaluators to R and R Markdown, with a focus on practical applications and streamlining workflows. Participants may choose to attend one, two, or all three sessions depending upon their experience and learning goals. Each session will be 90 minutes.
March 9: The first session is designed for evaluators who are new to R and/or have limited experience with coding or SQL. We will focus on the layout of the software, helpful new-to-R resources, basic functions, and example projects. We will discuss demographic analysis, survey/Likert analysis, and narrative reports.
March 23: The second session will focus on core tidyverse functions, de-bugging basics, and visualization options.
April 6: The third session will focus on automated reporting and reproducible work in R Markdown.
Please download R and R Studio prior to the first session:
REGISTRATION
Registration open for full series registration. Individual session registration will be opened upon availability. Registration is limited to 10 people per session.
Full-Series Registration (~15% discount applied): Members $50 | Nonmembers $100
Individual Session Registration (opening upon availability): Members $20 | Nonmembers $40
ABOUT THE PRESENTER
Nicole Harty has 10 years of public health program implementation, research, and evaluation experience, and has worked on a variety of clinical quality projects, community outreach efforts, behavioral health programs, and youth violence prevention projects as both an internal and external evaluator. Nicole has worked for the Colorado School of Public Health, Mental Health Center of Denver, and joined Routt County Public Health as the Epidemiologist/Data Manager in September 2020. In this role, she is primarily focused on the COVID-19 pandemic by conducting case investigation, contact tracing, data analysis, and reporting on disease transmission and mitigation in Routt County. Nicole started her R journey in 2015 and continues to use it as her tool of choice for data manipulation, statistical analysis, data visualization, and reporting. Nicole lives in Steamboat Springs, CO and received her bachelor's in neuroscience from New York University and masters in public health from the Colorado School of Public Health.
LEARNING OBJECTIVES
Session 1: Introduction to R and RStudio for Evaluators
At the end of this session, participants will be able to:
-
Explain file directories, file types, and project structure
-
Install and use major packages to import data and create data frames
-
Access and use reliable online help
Session 2: Data Manipulation and Introduction to the Tidyverse
At the end of this session, participants will be able to:
-
Explain the purpose and function of key tidyverse packages (dplyr, lubridate, stringr, forcats, ggplot2)
-
Author code to manipulate data using the pipe operator
-
Generate summary statistics and aggregations using the tidyverse
-
Perform common factor manipulations (reordering, collapsing factors) and work with strings (trucating, matching)
-
Create new variables using criteria in the data using case_when and if_else
Session 3: Reporting and Visualization Using RMarkdown, likert, ggplot2, and Plotly
At the end of this session, participants will be able to:
-
Explain the structure of files used in creating an RMarkdown report (.R, .Rmd, .md, .html)
-
Author in-line and chunk R code
-
Interpret and correct common errors
-
Generate basic plots using ggplot, likert, and plotly packages
