3. Sampling the Imaginary

Overview

The natural frequency phenomenon is not unique

Why statistics can’t save bad science

• 3.1 Sampling from a grid-approximate posterior

• 3.2 Sampling to summarize

  • 3.2.1 Intervals of defined boundaries

    • Counting with sum

  • 3.2.2 Intervals of defined mass

    • Why 95%?

    • What do confidence intervals mean?

  • 3.2.3 Point estimates

• 3.3 Sampling to simulate prediction

  • 3.3.1 Dummy data

    • Sampling distributions

  • 3.3.2 Model checking

    • 3.3.2.1 Did the software work?

    • 3.3.2.2 Is the model adequate?

      • What does more extreme mean?

• 3.4 Summary