Convergence

Three senses of convergence

  • Almost sure: Each individual sequence settles

  • In probability: Total mass of bad events vanishes

  • In distribution: Only the CDFs match the limit

Continuous distributions

  • Uniform: Randomness with no preference f(x)=1b−af\left(x\right)=\frac{1}{b-a}

  • Normal

  • Log-normal

  • Exponential

  • Gamma

  • Beta

Central Limit Theorem: For any distribution with finite mean and variance, the standardized sample mean is asymptotically normal

  • Finite Variance is an important thing to remember

The distribution of Xn approaches the distribution of X

Quantile: Cutoff point that gives a percentage

The t-distribution can be used when the standard deviation is unknown and the data is normally distributed

Bayesian Reasoning: Designed to minimize uncertainty

Base Rate Fallacy: People anchor on the likelihood and ignore the prior, but you should use the Bayesian equation for conditionals