In a calculus-based introductory statistics course, there is generally a lesson on some of the
named discrete distributions. This lesson often addresses the following distributions: Discrete
Uniform, Poisson, Binomial, Hypergeometric and Negative Binomial. Generally, all of these
distributions, except the Poisson, have already been utilized in a probability unit in the course
without the students even realizing it. That is, they have calculated probabilities “from scratch”
using the ideas of combinations, permutations, conditional probability, etc. For example, a
student may be asked to find the probability when a fair coin is tossed five times, that exactly
two are heads. Although this example follows a Binomial Distribution, students learn how to
construct this probability prior to ever hearing its name. Thus, the calculations of these
probabilities are not new, but the names and specific properties are. We may believe that the
application of these distributions should not be troublesome if students have already had
exposure to the calculations. However, students often struggle in the probability unit
distinguishing between permutations and combinations as well as “with replacement” and
“without replacement.” From our experience, adding the names and properties to these
distributions simply confuses students more. So, one might ask why add them? Three of the
motivational factors for students to learn the specific named distributions are:
Journal of Statistics Education, Volume 21, Number 1 (2013)
3
1. To simplify the implementation of probability calculations by utilizing their
probability mass functions (pmfs) and to understand the general form of a pmf.
2. To determine and utilize their specific expected value and variance.
3. To learn about the concept of modeling outcomes of a given situation through
demonstration.
In order to understand how students may confuse three of these distributions, we will go through
each of the three distributions’ characteristics in more detail.