Adjunct Instructor: Statistical Reasoning with R

Adjunct Instructor: Statistical Reasoning with R

The Heinz College of Information Systems and Public Policy at Carnegie Mellon University seeks an adjunct instructor for Statistical Reasoning with R for students in the Master of Science in Public Policy and Management (MSPPM) program. We invite professionals with deep experience and demonstrated leadership in the field to apply.

In today's information world, data are available everywhere and the role of statistics is rapidly increasing in public policy, health care, the arts, the entertainment industry, business, academia and many other parts of society. We echo the message of The New York Times which published an article entitled "For Today's Graduate, Just One Word: Statistics."

This course introduces students to statistical reasoning and is essential to learning from data and understanding the strengths and limitations of data analyses. This course is grounded in questions of importance in public policy and focuses on how data and statistical reasoning can inform those questions. We use a hands-on approach to develop skills and critical thinking in the fundamentals of causal inference, univariate and bivariate descriptive statistics, quantifying uncertainty, statistical inference, and linear regression. The hands-on approach involves learning the basics of how to use the R statistical language and weekly labs in which students use R to carry out data analysis on real-world policy issues in a supervised setting.

As this is a rigorous graduate school introductory statistics and data analysis course, the minimum goals of this course are to:

• Use R and R Studio to explore, summarize, and visualize data.
• Apply the concept of potential outcomes to evaluate estimates of causal effects.
• Summarize and interpret univariate and bivariate distributions using histograms, box plots, bar plots, and scatter plots.
• Perform linear regression with single or multiple predictors and assess model fit.
• Interpret the results of linear regression models.
• Use probability to quantify uncertainty in estimators of parameters of interest.
• Make accurate statistical inferences using confidence intervals and standard errors.
• Appropriately interpret results of data analyses and statistical inferences.
• Create reports of data analyses and interpretations of results using R Markdown.

The course is a full-semester (i.e. 14 weeks) during the fall semester. Course times could be afternoons (two 80-minute class sessions per week) or evenings (one 170-minute class from 6:30 to 9:20 PM, inclusive of a break, per week), as preferred.

The course design should at minimum include relevant readings (textbook, research papers, news articles, etc.), in-class discussions, and appropriate evaluations of mastery of concepts for grading purposes (homework, quizzes/exams, etc.). Given the focus of Heinz College graduate programs, utilization of data, strategic thinking, and application of leadership skills are highly encouraged to be integrated into the course.

About Heinz College

The Heinz College of Information Systems and Public Policy is home to two internationally recognized schools: the School of Information Systems and Management and the School of Public Policy and Management. The unique colocation of these two schools sets Heinz College apart to tackle society's most complex problems by teaching our students a firm understanding of policy, technology and analytical foundations, and the management skills to deploy solutions for maximum impact - the intersection of people, policy, and technology to approach complex societal problems. For more information, please visit www.heinz.cmu.edu.

Heinz College adheres to four basic principles of being grounded in real-world problem solving; staying ahead of the curve in innovation; nurturing diversity; and developing compassionate leaders. The College, since its founding in 1968 as the School of Urban and Public Affairs, has had a long history of commitment to diversity, equity, and inclusion, made ever more relevant in today's world of technology-driven social change.

The instructor should be a practitioner with direct experience and proficiency with R Statistical Language. Recent experience in teaching is preferred.