Joint Probability Functions and Joint CDFs for Discrete Random Variables

Pricing a joint-life policy requires a joint probability model for two correlated lifetimes. Get the joint distribution wrong and the premium is off by tens of thousands. Exam P tests whether you can build, read, and extract probabilities from joint PMF tables.

For two discrete random variables $X$ and $Y$, the joint PMF is:

$$p_{X,Y}(x,y) = P(X = x, Y = y)$$

Two properties must hold:

• $p_{X,Y}(x,y) \geq 0$ for all $(x,y)$
• $\sum_x \sum_y p_{X,Y}(x,y) = 1$

On the exam, joint PMFs appear as tables. Each cell holds the probability of a specific $(x,y)$ pair. Row totals and column totals give the marginal distributions.

HIGH-FREQUENCY: Given a table, computing $P(X + Y \leq c)$, $P(X > Y)$, or $P(X \leq a, Y \leq b)$ by summing appropriate cells is a core skill.

The joint CDF of $X$ and $Y$ is:

Common mistakes

• Forgetting that $X + Y$ is bounded by the sample size. With 2 draws, $X + Y \leq 2$. Assigning nonzero probability to cells like $(2,1)$ produces probabilities summing above 1.
• Confusing $F_{X,Y}(x,y)$ with $F_X(x) \cdot F_Y(y)$. The joint CDF equals the product of marginal CDFs only under independence. In Example 1: $F_X(1) \cdot F_Y(1) = (5/6)(5/6) = 25/36$, but $F_{X,Y}(1,1) = 2/3 = 24/36$. Trap: 25/36.
• Summing wrong cells for diagonal events. For $P(X + Y \leq 2)$, including cell $(2,1)$ where $x + y = 3$ inflates the answer. Verify each cell's coordinates before including it.

Bottom line

• Joint PMF: $p_{X,Y}(x,y) = P(X=x, Y=y)$, must be non-negative and sum to 1
• Joint CDF: $F_{X,Y}(x,y) = P(X \leq x, Y \leq y)$, cumulate down and to the left across every qualifying cell
• Rectangle formula: $P(a < X \leq b, c < Y \leq d) = F(b,d) - F(a,d) - F(b,c) + F(a,c)$
• Independence test: $p_{X,Y}(x,y) = p_X(x) \cdot p_Y(y)$ must hold for EVERY cell

Exam shortcut

When handed a joint PMF table, immediately compute row and column totals in the margins. For diagonal events like $P(X+Y \leq k)$, draw a diagonal line across the table to separate qualifying cells visually. "CDF = Cumulate Down and Left, Four terms for rectangles." $F(b,d) - F(a,d) - F(b,c) + F(a,c)$. "Every cell must multiply out" for independence. Row total times column total. One mismatch proves dependence.

The full lesson (about 3,020 words, 20 min read) adds 3 worked examples, all 7 common mistakes, a self-check, free in the app.

Learning objectives

• 3a

Browse all free Exam P lessons or jump into free Exam P practice questions.