4.13 Unit 4 summary

4.13.1 You should be able to

  • Conduct a statistical hypothesis test of an observed difference between two groups
    • Write an appropriate null hypothesis for a study that compares two groups
    • Use Monte Carlo simulation in TinkerPlots™ to find the expected variation if the null hypothesis were true (randomization test)
    • Formulate a conclusion
  • Evaluate the internal validity evidence of a study to make a cause-and-effect inference, using the following criteria:
    • Association of cause and effect
    • Timing
    • No plausible alternative explanations

4.13.2 You should understand

  • How to interpret the mean of a dummy variable
  • How to interpret the difference in means between two groups
  • The logic behind a randomization test, including:
    • Why we take the observed outcomes as fixed
    • Why we randomly reassign the observed outcomes to experimental groups
    • Why we sample without replacement
    • What the distribution of results represents
  • What “internal validity” means
  • The role of random assignment in establishing internal vaidity evidence for drawing cause-and-effect conclusions

4.13.3 TinkerPlots™ skills

  • Create a split dot plot
  • Create a “shuffler” sampler
  • Use the Ruler tool to find the difference in means

4.13.4 Vocab

  • Experiment
  • Random assignment
  • Observational study
  • Confounding variable
  • Cause-and-effect
  • Internal validity evidence
  • Probabilistically equivalent