Statistics and Data Science I

Aim

After completion of the course, the student should at an advanced level be able to:

• describe the fundamental postulates and theorems of applied probability;
• differentiate between discrete and continuous probability distributions and relate these to the concept of random variables;
• relate common probability distributions used in the social sciences to various social processes and outcomes.
• use statistical software to generate random samples from key probability distributions;
• explain the principles of Monte Carlo simulation, and implement simulations using appropriate computational tools;
• perform univariate hypothesis testing using data and appropriate computational tools and analyze the interpretation and robustness of hypothesis tests.

Content

This course provides an overview of key results in probability and statistics relevant for social research and introduces programming tools for statistical analysis. Major probability distributions, including the binomial, normal, exponential, and Poisson distributions, used in social science research are introduced and their properties and applications are explored in intensive computer labs. Statistical software is used to simulate from these distributions. Computational methods, including Monte Carlo simulation, are used to explore key theorems under various conditions. Hypothesis tests for parameters and statistics related to common univariate distributions are introduced, and computational alternatives are considered.