Statistics 104: Summer 2013
Data Analysis and Statistical Inference

with Professor Mine Çetinkaya-Rundel

Unit 1: Introduction to data

Reading:

• OpenIntro Statistics: Chapter 1

Learning objectives:

• Learning objectives for Unit 1 (PDF)

Additional resources:

• How Anecdotal Evidence Can Undermine Scientific Results (Scientific American)
• Placebos Are Getting More Effective. Drugmakers Are Desperate to Know Why. (Wired)

Videos:

All videos are best viewed in full screen.

Types of variables:

This video discussed types of variables (numerical and categorical), how to identify them, and further classifications.

Random sampling vs. random assignment:

This video discusses random sampling and random assignment, and concepts of generalizability and causality.

Correlation vs. causation:

A quick video on correlation vs. causation.


A slower video on correlation vs. causation.

Mean, median, and mode:

This video demonstrates calculating mean, median, and mode using an example from a small dataset.

Visualizing distributions of numerical variables:

This video discusses various methods for visualizing distributions of numerical variables: histograms, dot plots, box plots, intensity maps.

Reading box plots:

This video discusses the anatomy of a box plot.

Exploring relationships between categorical variables:

This video discusses numerical and graphical methods for exploring relationships between two categorical variables, using contingency tables, segmented bar plots, and mosaic plots.