Chapter 1 Significance: How Strong is the Evidence?

1.1 Intro

  • Statistics – Estimate broad populations
    • No way to collect all information
    • When is a sample Statistically Significant?
  • Statistical Significance
    • “Is our result unlikely to have occurred by random chance?”
    • Helper vs. Hinderer
      • Is 14/16 significantly higher than 8/16?
      • Is 10/16 significantly higher than 8/16?
  • Probability
    • Long-run proportion of times an outcome from a random process occurs
    • Probability Distribution- Pattern of long run outcomes

1.2 Definitions

  • Sample: The set of observational units on which we collect data.
  • Sample size: The number of observational units in the sample.
  • Statistic: The number summarizing the result of the sample.
  • Population: The complete collection of ALL elements that are of interest for a given problem.
  • Parameter: The long-run numerical property of the process.

Population and Sample: Use Statistics (observed from sample) to Estimate the Parameter (population unknown value). Use Statistics to Estimate the Parameter

1.3 Chance Models

1.3.1 Doris and Buzz Example

1.3.2 Coin Flipping Activity

1.4 Strength of Evidence

1.4.1 Rock-Paper-Scissors Example