Direct comparison
Marginal vs Conditional Distribution Explained
Marginal distribution vs conditional distribution: sum out vs divide by, formulas, a worked 2x2 table, the unit-circle example and the independence test.
Written and maintained by CASRAI Editorial Board
Last updated
Ask CASRAI · free to tryQuestion about this comparison? Ask CASRAI answers with linked sources. 2 free questions a day, no account.
How do Marginal distribution and Conditional distribution compare side by side?
The table below compares Marginal distribution and Conditional distribution across 11 dimensions, from plain-language meaning to when to use it.
Side-by-side comparison
| Dimension | Marginal distribution | Conditional distribution |
|---|---|---|
| Plain-language meaning | Distribution of one variable ignoring the other. | Distribution of one variable given that the other has crystallized to a specific value. |
| Notation | f(x) or P(X = x) | f(y|x) or P(Y = y | X = x) |
| How it is computed from the joint distribution | Sum (discrete) or integrate (continuous) out the unwanted variable over its support. | Divide the joint by the marginal of the conditioning variable, defined where that marginal is greater than 0. |
| Discrete formula | P(X = x) = Σ_y P(X = x, Y = y) | P(Y = y | X = x) = P(X = x, Y = y) / P(X = x) |
| Continuous formula | f(x) = ∫ f(x, y) dy | f(y|x) = f(x, y) / f(x), for f(x) > 0 |
| What is held fixed | Nothing; the other variable is allowed to vary over all its values. | The conditioning variable, held at one specific value. |
| Is it a proper distribution? | Yes: sums or integrates to 1 over the variable. | Yes, for each fixed conditioning value: it sums or integrates to 1 over the variable being described. |
| Number of distributions produced | One per variable. | One per value of the conditioning variable. |
| Link to the joint distribution | Obtained from the joint by collapsing one dimension. | Combined with the marginal it rebuilds the joint: f(x, y) = f(x) f(y|x). |
| Independence test | Independent when the conditional f(y|x) equals this marginal f(y) for all x. | Independent when f(y|x) does not depend on x and equals the marginal f(y); otherwise X and Y are dependent. |
| When to use it | The other variable is irrelevant, unobserved or to be averaged over, and you need the overall behaviour of one variable. | The value of the other variable is known or fixed, and you need the distribution of the first given that information. |
Sources
- Probability textbook, bookdown.org/probability/beta, Joint distributions (read 2026-11-07)
- Siegrist, Probability, Mathematical Statistics, and Stochastic Processes, LibreTexts 3.5 (read 2026-11-07)
- Same two sources: bookdown.org/probability/beta/joint-distributions.html and stats.libretexts.org, Siegrist, section 3.5 Conditional Distributions (read 2026-11-07)
Ask CASRAI · free to try
Ask about Marginal vs Conditional Distribution Explained
2 free questions a day, no account.
An AI assistant for research: funder rules, compliance, methods and publishing. It links the sources behind its answers and labels answers that come from a web search.
Answers draw on CASRAI's guides and dictionary plus the federal and funder documents we index: Federal Register, Grants.gov, Regulations.gov and UKRI.
Works on this site and inside Claude, Cursor and the AI tools you already use.
Everything CASRAI publishes — this page, the dictionary, the guides and the news — stays open to read, with no account and no card.
Common questions
Common questions about Marginal distribution vs Conditional distribution
What is the simple definition of conditional distribution?
+
A conditional distribution is the distribution of one random variable given that another random variable has taken a specific value. For discrete variables, P(Y = y | X = x) = P(X = x, Y = y) / P(X = x); for continuous variables, f(y|x) = f(x, y) / f(x), wherever f(x) > 0.
What is the difference between marginal and conditional distribution?
+
A marginal distribution sums or integrates out the other variable, so it describes one variable overall. A conditional distribution fixes the other variable at a value and renormalizes, so it describes one variable under that condition. There is one marginal per variable but one conditional per conditioning value.
What is a joint probability distribution?
+
A joint distribution assigns probability to combinations of values of two or more random variables at once, for example P(X = x, Y = y) for discrete variables or a density f(x, y) for continuous ones. Both marginal and conditional distributions are derived from it.
What is the difference between CDF and PDF?
+
The cumulative distribution function F(x) = P(X ≤ x) gives the probability that a variable is at most x and exists for any random variable. The probability density function f(x) is, for a continuous variable, the function whose integral over an interval gives the probability of that interval; where F is differentiable, f is its derivative. Discrete variables use a probability mass function instead of a density.
What are the three types of distributions?
+
In the joint-distribution setting the three are joint, marginal and conditional distributions. By variable type, a distribution is discrete, continuous or a mixture of the two.
How do I tell whether two variables are independent from their conditional distributions?
+
If the conditional distribution of Y given X = x is the same for every x and equals the marginal distribution of Y, the variables are independent. Equivalently the joint factors as f(x, y) = f(x) f(y).







