5  Module 5: Confidence intervals based on distributional assumptions

Learning objectives

  • Describe the Law of Large Numbers. (Move to model 2!)

  • Describe a normal distribution. (Move to model 2!)

  • Explain the Central Limit Theorem (Move to model 2!)

  • Explain the role of Central Limit Theorem and other general asymptotic results (such as for quantiles) in constructing confidence intervals.

  • Write a computer script to calculate confidence intervals based on the assumption of normality or the Central Limit Theorem.

  • Discuss the potential limitations of these methods.

  • Decide whether to use asymptotic theory or bootstrapping to compute estimator uncertainty.

5.1 Proposed structure of this chapter

5.1.1 introduction + motivation

  • recall CIs using bootstrapping
  • recall sampling distribution + Normal model
  • general form of confidence interval

5.1.2 one sample

  • CI for one proportion formula

  • finding critical value

  • assumptions + conditions

  • interpretation

  • CI for one mean when sd known formula

  • problem when sd not known

  • introduction to t value

  • finding critical value

  • assumptions + conditions

5.1.3 Extending to two samples

  • sampling distribution for difference in proportions + means
  • introduce idea of dependent and independent samples?
  • CI for two proportion
  • CI for two mean (independent groups)
  • CI for two mean (dependent groups)

5.1.4 Contrast bootstrap vs traditional methods