Overview

Description

CALENDAR DESCRIPTION:

Introduces statistical methods, concepts and their application to economic data using both spreadsheets (e.g., Excel) and a specialized statistical programming language such as R. Students who have taken ECON 333 first may not then take this course for further credit. STAT 270 or BUS 232 will be accepted in lieu of this course.

COURSE DETAILS:

This course introduces the basics of probability and statistics for economics students. Like BUS 232 or STAT 270, it satisfies the lower-division statistics requirements for the economics major. It differs from these courses in two important ways:

 

1. We will emphasize the use of economic data to answer economic questions.
2. We will learn to use both Excel (the standard analysis tool in the business world) and R (a more powerful statistical analysis package that is increasingly used in the business and academic world, and is the main tool used in ECON 333).

 

Extensive support will be available to help students complete the computer assignments and build their computer skills, so do not shy away from this course just because you lack confidence in your current skills.

Topics:

 

1. Data cleaning and management with Excel
   The first (and often the longest) step in any data analysis project is to obtain the necessary data and “clean” it by correcting errors or clarifying ambiguities in the variables, adding new variables, and linking cases (for example, parents with children). We will learn the basic features of Excel and will use Excel to clean an economic data set. In the process, we will also learn some principles and practices for data management and reproducible data analysis.
2. Probability and random events
   To use data to learn about the world, our analysis needs to be statistical in nature: it needs to be situated in a mathematical model of how the data was generated.  To do that, we need to learn some theory. We will start by learning the language of probability and tools for thinking rigorously about random events.
3. Random variables
   Roughly speaking, a random variable is a number describing a random outcome: the unemployment rate last month, the score in a baseball game, or a number in our data set. We will apply the concepts of probability to develop terminology and tools for working with random variables.
4. Basic data analysis with Excel
   We will take a break from theory to learn some more applied skills: using Excel to calculate basic statistics and create simple graphs.
5. Statistics
   A statistic is any number calculated from data. If we think of our data set as a set of random variables, then any statistic based on that data is also a random variable. We will learn how to apply the tools of probability, random events, and random variables to statistics that are calculated from data.
6. Statistical models, parameters, and estimation
   We typically use statistics to make guesses (estimate) about some unknown quantity in the real world (a parameter). For example, the slope of a supply or demand curve, the effect of a treatment on a medical condition, or the effect of a policy on an economic outcome. We will use the theory of probability and statistics to think about how our estimate relates to the unknown true value of the parameter of interest, and to construct the most accurate estimate available for a given data set.
7. Statistical inference
   Statistical estimates are always imprecise. Statistical inference is a set of ideas and procedures that we use to account for this imprecision, and to make clear statements about what can and cannot be concluded from the available data.
8. Advanced Excel
   We have learned to use Excel for basic data cleaning and analysis, but Excel also has many tools and techniques that are important in more complex environments. We will learn how to construct lookup tables, complex formulas, and pivot tables, as well as some tools for protecting and managing large or important data sets.
9. Introduction to R, R Markdown, and the Tidyverse
   R is a powerful statistical package that can handle complex data analysis tasks that are impossible or difficult in Excel. We will learn how to write simple R programs and create data-based documents using R Markdown. As in most courses these days that use R, we will use an add-on package for R called the Tidyverse. The Tidyverse simplifies and modernizes the R programming language and its capabilities.
10. Data management and analysis with R and ggplot
    Having learned the basics of R, we next use it to clean data, calculate statistics, and create graphs. The package we will use to create graphs is ggplot, which produces dramatically better-looking and more flexible graphs than Excel.
11. Prediction and visualization
    Sophisticated technologies like machine learning, automatic captioning and tagging, and large language models (e.g. GPT/ChatGPT) use very large data sets to form statistical models and make predictions. While these specific techniques are out of scope for this introductory course, the principles of using data to construct prediction models are not. We will finish the semester by learning some introductory concepts and tools for prediction models, including linear regression which is used extensively in ECON 333.

 

Grading

Materials

REQUIRED READING:

REQUIRED READING NOTES: