“There are three kinds of lies: lies, damned lies, and statistics.” — Benjamin Disraeli, British P.M.
“The sexy jobs in the next ten years will be statisticians.” — Hal Varian, Chief Economist, Google
Statistics is the science of learning from data. Businesses, governments, academics, nonprofit organizations, consultants, and many other professions are using more data than ever. The rise of the internet and the ability for organizations to track many things about their users, known as “big data,” make statistical literacy and competency one of the most in-demand skills that most employers today are looking for.
This course is designed as an introduction to data and how it is collected, described, and used to make useful inferences about the world. I am an economist, not a business expert nor a mathematician. While we will be dealing with elementary statistical and probability theory, we will be keeping our eye towards applications in business and economics. If you want a more ``pure” class in statistics or mathematics, they are offered by the department of mathematics. The formal prerequisites for this course are MATH 120 or equivalent. I assume that you have no background in statistics or probability (we will start from square one), but that you are competent in basic algebra and graphing skills (we may do a brief review as necessary).
I have three goals for everyone taking this course: (1) to understand and evaluate statistical and empirical claims; (2) to understand research design and hypothesis testing; (3) to gain experience working with, interpreting, and communicating real data. I am less concerned with forcing you to memorize and recite proofs of statistical estimator properties, and more concerned with the development of your intuitions and the ability to think critically as a businessperson, a social scientist, and a democratic citizen—although this will require you to demonstrate proficiency with some statistical and mathematical tools.
To these ends, in addition to lectures about statistical methods, you will be working on problem sets that use theory, as well as using Microsoft Excel to complete problem sets using data, and write a brief empirical paper using data. By the end, you should feel comfortable working with data and understanding the empirical claims of others. The best training is for you to learn by doing.
|1. Sampling and Data||Slides|
|2. Descriptive Statistics||Slides||Descriptive Statistics; Boxplots|
|4. Discrete Random Variables||Slides|
|5. Continuous Random Variables||Slides||Modelling Distributions|
|6. The Normal Distribution||Slides|
|7. The Central Limit Theorem||Slides|
|8. Confidence Intervals||Slides||Regression Example|
|9. Hypothesis Testing||Slides|
|10. Linear Regression||Slides|