Discrete Probability Distributions Reference Card

Fundamentals of Probability Distributions

  • Probability vs. Probability Distribution:

    • A probability evaluates the chance of a single event occurring.

    • A probability distribution lists all possible outcomes of an experiment alongside their corresponding probabilities.

  • Core Properties of Probability Distributions:

    • The probability of any outcome xx satisfies 0≤P(x)≤10 \le P(x) \le 1.

    • Outcomes are mutually exclusive and collectively exhaustive, meaning the sum of all probabilities equals 11 (∑P(x)=1\sum P(x) = 1).

    • Outcomes occur randomly and can be qualitative or quantitative.

  • Random Variables:

    • Discrete Random Variable: Takes on clearly separated, countable values (e.g., number of students, card counts).

    • Continuous Random Variable: Takes on an infinite number of values within a given range, typically resulting from measurement (e.g., driving time, height).

  • Distribution Parameters:

    • Mean (μ\mu): The central location, expected value, or long-run average of the random variable.

    • Variance (σ2\sigma^2): Measures the dispersion or spread of outcomes around the mean.

    • Standard Deviation (σ\sigma): The positive square root of the variance (σ=σ2\sigma = \sqrt{\sigma^2}).

Binomial Probability Distribution

  • Criteria for a Binomial Experiment:

    • A fixed number of trials (nn).

    • Exactly two mutually exclusive outcomes per trial: success or failure.

    • Constant probability of success (pp) and failure (1−p1 - p) across all trials.

    • Independent trials, where the outcome of one trial does not affect any other.

  • Binomial Parameters:

    • Mean:     μ=np\mu = np

    • Variance:     σ2=np(1−p)\sigma^2 = np(1 - p)

    • Standard deviation:     σ=np(1−p)\sigma = \sqrt{np(1 - p)}

  • Distribution Shape:

    • Positively skewed when pp is small, becoming more symmetrical as nn increases or as pp approaches 0.50.5.

Binomial distribution shapes for varying sample sizes with constant probability

Hypergeometric Probability Distribution

  • Criteria and Use:

    • Used when sampling from a finite population without replacement, causing the probability of success to change between draws.

    • Appropriate when the sample size nn is more than 5%5\% of the population size NN (n>0.05Nn > 0.05N).

  • Variables:

    • NN: Total population size.

    • SS: Total number of successes in the population.

    • nn: Sample size or number of trials.

    • xx: Number of successes observed in the sample.

    • CC: Denotes combinations.

  • Binomial Approximation Rule:

    • If the sample size is less than 5%5\% of the population (n<0.05Nn < 0.05N) without replacement, the binomial distribution provides an acceptable approximation.

Poisson Probability Distribution

  • Characteristics:

    • Measures the number of times an event occurs within a specified continuous interval (time, distance, area, or volume).

    • Events are rare, independent, and occur randomly, with non-overlapping intervals.

    • Possesses no predetermined upper limit.

  • Poisson Parameters and Properties:

    • Described by the rate parameter λ\lambda and base constant e=2.71828e = 2.71828.

    • The mean and variance are identical:     μ=λ\mu = \lambda     σ2=λ\sigma^2 = \lambda

    • Approximates the binomial distribution when nn is large and pp is small, using:     λ=np\lambda = np

    • Distribution shape is always positively skewed, becoming more symmetrical as μ\mu increases.