Introduction

Overview

Teaching: 5 min
Exercises: 0 min

Questions

• What is statistical inference?

• Why do biomedical researchers need to learn statistics now?

Objectives

• Explain how technology has changed biomedical measurements from past to present.

Technological changes in biomedical research drive data production in greater quantity and complexity. High-throughput technologies, such as sequencing technologies, produce data whose size and complexity require sophisticated statistical skills to avoid being fooled by patterns arising by chance. In the past researchers would measure, for example, the transcription levels of a single gene of interest. Now it is possible to measure all genes at once, often 20,000 or more depending on the organism. Technological advances like these have driven a change from hypothesis to discovery-driven research. This means that statistics and data analysis in the life sciences are more important than ever.

This lesson will introduce the statistical concepts and data analysis skills needed for success in data-driven life science research. We start with one of the most important topics in statistics and in the life sciences: statistical inference. Inference is the use of probability to learn population characteristics from data. A typical example is determining if two groups (for example, cases versus controls) are different on average. Specific topics include:

• p-values
• the t-test
• confidence intervals
• association tests
• permutation tests
• and statistical power

We make use of approximations made possible by mathematical theory, such as the Central Limit Theorem, as well as techniques made possible by modern computing.

Key Points

• Novel technologies produce data in great complexity and scale, requiring more sophisticated understanding of statistics.