Probability and Statistics Foundations for Trading Examples
Summary
The article introduces probability spaces, events, probability measures, conditional probability, and independence, then develops finite-outcome probability through counting. Examples explain permutations, ordered selections, combinations, and the hypergeometric distribution. It also describes Bernoulli trials and applies elementary statistical methods to trading-related data, including parameter estimation and hypothesis testing.
Worked examples include estimating a success probability from discretized price moves, comparing two Bernoulli samples, modeling transitions in a two-state sequence, and testing a specified probability. The discussion frames market uncertainty as involving both randomness and the actions of other participants, while noting that probabilistic models simplify this complexity. The treatment is introductory: it omits descriptive statistics, interval estimation, asymptotic methods, Bayesian analysis, and the broader theory of random variables, which the author reserves for later material. The examples teach foundational tools but do not establish that their models adequately describe market behavior.
Key ideas
- A probability model specifies possible outcomes, events, and probabilities assigned to those events.
- Conditional probability describes how observing one event changes the probability of another.
- Combinatorial counting gives event probabilities when elementary outcomes are finite and equally likely.
- The hypergeometric distribution models the count of marked items in a sample drawn without replacement.
- Bernoulli and Markov models can be estimated from discretized trading observations, subject to model assumptions.
- Parameter estimation and hypothesis tests provide ways to assess probabilities in observed data.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.