Major Probability Distributions in Data Science and Statistics

You requested the full list of major probability distributions used in computational statistics, machine learning, and data science. Below is a classification with key examples.

Types of Probability Distributions

1. Discrete Distributions (Countable Outcomes)

• Bernoulli Distribution: Binary outcome (0 or 1, e.g., a coin toss).
• Binomial Distribution: Number of successes in n independent trials.
• Negative Binomial Distribution: Number of trials required to achieve k successes.
• Geometric Distribution: Number of trials until the first success.
• Poisson Distribution: Number of events occurring in a fixed interval of time or space.
• Multinomial Distribution: Generalization of the binomial distribution for multiple categories.
• Discrete Uniform Distribution: Each outcome has an equal probability of occurring.

2. Continuous Distributions (Uncountable Outcomes)

Basic Continuous Distributions

• Uniform Distribution: All values within a range are equally likely.
• Normal (Gaussian) Distribution: The classic bell curve; the most common distribution in nature.
• Log-Normal Distribution: Data where the logarithm is normally distributed (e.g., income, stock prices).
• Exponential Distribution: Models the time between events in a Poisson process (memoryless).
• Gamma Distribution: Models waiting times and serves as a generalized exponential distribution.
• Beta Distribution: Models probabilities or proportions, bounded between 0 and 1.

Reliability and Lifetime Models

• Weibull Distribution: Used to model product lifetimes and failure rates.
• Rayleigh Distribution: Frequently used in signal processing and wind speed analysis.
• Chi-Square Distribution: A special case of the gamma distribution used in hypothesis testing.
• t-Distribution (Student’s t): Used for testing the mean of small samples.
• F-Distribution: Used for comparing variances (e.g., in ANOVA and regression).

3. Multivariate Distributions

• Multivariate Normal Distribution: A generalization of the normal distribution for vectors.
• Dirichlet Distribution: A generalization of the beta distribution for probability vectors.
• Multivariate t-Distribution: A heavier-tailed version of the multivariate normal distribution.

Quick Summary

• Discrete: Bernoulli, Binomial, Poisson, Geometric, Negative Binomial, Multinomial.
• Continuous: Uniform, Normal, Log-Normal, Exponential, Gamma, Beta, Weibull, Rayleigh, Chi-Square, t, F.
• Multivariate: Multivariate Normal, Dirichlet, Multivariate t.

Would you like me to convert this into a comparison table with applications for each distribution for your study notes?