6.5. Comparison Table

Feature: Discrete RV Values Taken: Countable

Feature: Continuous RV Values Taken: Uncountable

In this portion, we distinguish between the types of values that discrete and continuous random variables can assume. Discrete random variables (RVs) can take a countable number of distinct values, which means you can list them out, like 0, 1, 2, etc. In contrast, continuous random variables have uncountable values. This means they can take any value within a certain range or interval, like all values between 0 and 1, which can include fractions and decimals.

Imagine counting the number of apples in a basket. You can have 0, 1, 2, or more apples; these numbers are countable. Now think about measuring the temperature of a room. The temperature can be 72.5°F, 73.2°F, or any number in between—those values are uncountable.

Feature: Discrete RV Probability Function: PMF: 𝑃(𝑋 = 𝑥)

Feature: Continuous RV Probability Function: PDF: 𝑓(𝑥), 𝑃(𝑎 < 𝑋 < 𝑏)

This section describes the functions used to define the probabilities associated with each type of random variable. For discrete random variables, we use a Probability Mass Function (PMF) to determine the probability of a specific outcome. For continuous random variables, we use a Probability Density Function (PDF) to find the probability that the variable falls within a specific range rather than at a specific point. In continuous cases, probabilities are derived from integrals.

Think of a discrete random variable as rolling a die; the PMF gives you the likelihood of rolling a 1, 2, 3, and so on. For a continuous random variable, such as the distance you might run, the PDF gives you a curve. To find the probability that you'll run between 3 and 4 miles, for example, you look at the area under the curve between those two points.

Feature: Discrete RV Sum: ∑𝑃(𝑋 = 𝑥 )= 1

Feature: Continuous RV Integral: ∫𝑓(𝑥)𝑑𝑥 = 1

Here, we see a fundamental property of both discrete and continuous random variables concerning their probability functions. For discrete random variables, the sum of the probabilities of all possible outcomes must equal 1. For continuous random variables, the integral of the probability density function over the entire range must equal 1, indicating that the total probability is conserved in both cases.

Picture a jar filled with different colored marbles. If you take all the marbles out and count them, the total number you count must equal the total number in the jar. This is analogous to how discrete probabilities sum to 1. Now imagine pouring liquid from a defined volume into a glass; the total volume of liquid poured must equal the initial volume. This is akin to how integrals give the total probability for continuous variables.

Feature: Discrete RV Examples: Coin toss, dice roll

Feature: Continuous RV Examples: Time, weight, temperature

This section provides examples to clarify the difference between discrete and continuous random variables. Discrete random variables can be illustrated with simple cases like tossing a coin—which yields heads or tails—or rolling a die, which can land on one of six numbered sides. Continuous random variables encompass measurements, such as time, weight, or temperature, where the potential outcomes can take any number within a broad range.

When you toss a coin, you can only get heads or tails—those are distinct options, making it discrete. But if you're measuring how long it takes to cook dinner, you could take 30.5 minutes, 30.6 minutes, or even 31 minutes; this variability shows the uncountable nature of continuous outcomes.

--