• Wed Nov 16, 7:30pm-10:00pm in Warner 506/507.
• Target median completion time is about 1h15m
• Closed book, no calculators, but you may bring dplyr cheatsheet.
• You won't need to write 100% correct R code, but rather rough pseudocode

• Suggested approach
  • Read the slides from each lecture to get the executive summary
  • Chalk talks went slow for reason: they are important concepts not worth rushing
  • Learning check discussions
  • Problem Sets

• Focus on Lec17 through Lec24. For Lec24 ignore anything involving p-values: Slides 6-9.
• However the midterm is still cumulative in that ggplot2/dplyr are now not goals in and of themselves (like with Data Science), but rather the tools we use for
  • Performing simulations, studying sampling, etc…
  • Examining results

• Note the paradigm shift:
  • PS-07: recap of the tools of data visualization/manipulation to the end of data science
  • PS-08: using the tools of data visualization/manipulation to the end of sampling and probability
• Think of reading/writing as a tool for communication for various essay-based classes
• Much in the same way, we are using coding as the language for expressing statistical ideas.

Especially for the section 3 of the syllabus: Statistical Inference, look at the OpenIntro textbook from Problem Set 08 and use the index to find the topics (mostly at the front of the text).

• Definitions relating to sampling. Ex:
  • Tub of rice
  • LC: Comment on the generalizability/representativeness of situations
• Being able to describe any sampling situation in terms of the Powerball analogy
• Components of designing experiments. Ex: Fried chicken face off
• Defintions relating to hypothesis testing. Ex: Lady Tasting Tea

The tools for sampling, randomization, and probability from the mosaic package:

• rflip() a coin
• shuffle()
• do() many, many, many times
• resample(): the swiss army knife. Understand the three knobs you can control to have different types of sampling.