Probability Models for Counts: Binomial and Poisson Distributions

Random Variables for Counts

Definition and Context

Random variables for counts are used to model the number of occurrences of a particular event within a fixed set of trials or over a specified interval. These models are fundamental in business statistics for analyzing discrete events such as sales, customer arrivals, or product defects.

• Random Variable: A variable whose value is determined by the outcome of a random experiment.

• Count Data: Data representing the number of times an event occurs.

• Examples: Number of emails received per day, number of free throws made in basketball.

Binomial Model

Counting Successes (Binomial Random Variable)

The binomial model is used to count the number of successes in a fixed number of independent trials, each with the same probability of success. It is defined by two parameters: the number of trials (n) and the probability of success (p).

• Binomial Random Variable: $Y = \sum_{i=1}^{n} X_i$, where each $X_i$ is a Bernoulli random variable (success/failure).

• Parameters: n (number of trials), p (probability of success per trial).

• Example: Number of successful free throws out of 12 attempts, with a success probability of 0.7.

Binomial Model Assumptions

For the binomial model to be valid, several assumptions must be met:

• Fixed Number of Trials: The number of trials (n) is predetermined and finite.

• Two Possible Outcomes: Each trial results in either "success" or "failure."

• Constant Probability: The probability of success (p) remains the same for every trial.

• Independence: The outcome of one trial does not affect the outcome of another.

• Count of Successes: The binomial random variable counts the number of successes in n trials.

• 10% Condition: When sampling without replacement from a finite population, independence can be assumed if the sample size is less than 10% of the population.

Mean and Variance of Binomial Distribution

The mean and variance of a binomial random variable are given by:

• Mean: $\mu = n p$

• Variance: $\sigma^2 = n p (1 - p)$

Applications and Examples

• Example: In basketball, if a player attempts 12 free throws and the probability of making each is 0.7, the expected number of successful throws is $\mu = 12 \times 0.7 = 8.4$.

• Business Application: Estimating the number of customers who will make a purchase out of a fixed number approached.

Poisson Model

Definition and Context

The Poisson model is used to describe the probability of a given number of events occurring in a fixed interval of time or space, when these events happen independently and at a constant average rate.

• Poisson Random Variable: Counts the number of occurrences of an event in a fixed interval.

• Parameter: $\lambda$ (average rate of occurrence per interval).

• Example: Number of emails received by a student in an hour.

Poisson Probability Distribution

The probability of observing k events in an interval is given by:

• Probability Mass Function: $P(Y = k) = \frac{\lambda^k e^{-\lambda}}{k!}$

• Mean and Variance: Both equal to $\lambda$.

Applications and Examples

• Example: If a student receives an average of 5 emails per hour, the probability of receiving exactly 3 emails in an hour is $P(Y = 3) = \frac{5^3 e^{-5}}{3!}$.

• Business Application: Modeling the number of customer arrivals at a store per hour.

Summary Table: Binomial vs. Poisson Models

The following table compares the main properties of the Binomial and Poisson models:

Property	Binomial Model	Poisson Model
Random Variable	Number of successes in n trials	Number of events in interval
Parameters	n (trials), p (success probability)	λ (average rate)
Mean	$\mu = n p$	$\mu = \lambda$
Variance	$\sigma^2 = n p (1 - p)$	$\sigma^2 = \lambda$
Assumptions	Fixed n, independent trials, constant p	Events occur independently, constant rate
Example	Free throws made in basketball	Emails received per hour

Conclusion

Understanding binomial and Poisson models is essential for analyzing count data in business statistics. These models allow for the calculation of probabilities, expected values, and variances, which are critical for decision-making and forecasting in business analytics.