Hypergeometric Distribution Calculator

Hypergeometric Sampling Without Replacement

Hypergeometric sampling applies when the population is finite and every draw changes what remains. Unlike binomial trials, the next draw depends on what came before because removed items are not returned to the pool. If an urn contains $N$ items of which $K$ are successes and you draw $n$ without replacement, the odds shift after each selection.

Hypergeometric PMF Calculation

The hypergeometric PMF gives the probability of exactly $k$ successes in that sample. The numerator counts favorable combinations by choosing $k$ successes from $K$ and $n-k$ failures from $N-K$, while the denominator counts every possible way to choose $n$ items from $N$. Because the expression is built from combinations, it produces an exact answer for the finite-population model.

Hypergeometric Cumulative Probability

The cumulative distribution function is the hypergeometric version of "at most $k$ successes." It adds the probabilities from zero through $k$, which is handy when you want to know how likely a sample is to stay under a defect limit, miss a rare item, or fall short of a target count. For a one-line summary of risk, the CDF is often easier to read than the full table of probabilities.

Start by entering the total number of items $N$, the count of successes in the population $K$, the sample size $n$, and the observed number of successes $k$. Press Calculate to display both the probability of exactly $k$ successes (the PMF) and the cumulative probability of observing up to that many. The output lets you compare a single outcome with the running total without leaving the finite-population framework.

Imagine inspecting a batch of 100 gadgets where 10 are known defects. If you randomly test 15 gadgets, the calculator can tell you the chance of finding, say, 3 or fewer faulty units. That kind of answer is useful when you want a sampling plan that balances effort against the risk of overlooking too many bad parts.

Unlike with replacement models, each item that leaves the population changes the odds for the next draw. That is why the hypergeometric distribution stays faithful to small lots, limited decks, and other closed pools where one selection changes the available mix. The counting is based on combinations— notation—to track how many ways each outcome can be formed.

Beyond factory checks, the same logic appears in card hands, ecological surveys, and any experiment where the population is finite and every selection changes the pool. By adjusting the inputs you can see how a larger sample makes rare successes more or less likely and how quickly the tail of the distribution changes when the population is small.

Hypergeometric Parameters N, K, n, and k

The hypergeometric model uses four symbols that define one finite population and one sample. The population size is the total number of items, whether they are cards, balls, parts, or test records. Out of those items, are successes and the remaining are failures. Drawing objects without replacement gives some count of successes, and the entire distribution is built around how those four numbers interact.

Hypergeometric Formula: Step-by-Step Manual Calculation

Hand-calculating a hypergeometric probability is a good way to see what the calculator is doing. First choose successes from the available and failures from the non-successes. Next count every possible sample of size from . Divide the favorable count by the total count, and the result is the exact PMF value for that outcome. When a number seems surprising, walking through the combinations often reveals whether the sample or population parameters were entered incorrectly.

Hypergeometric Worked Example: Drawing Aces

A classic hypergeometric example is a standard 52-card deck with four aces. If you draw ten cards at random, what is the probability that exactly two are aces? In this setup , , , and . The calculator first evaluates , the number of ways to pick two aces. It then multiplies that by because eight non-aces must fill the rest of the hand. Finally it divides by , the total number of ten-card hands. The resulting probability, about 0.0399, shows how rare that exact hand is. Changing lets you trace the whole hypergeometric distribution, not just this single point.

Hypergeometric Mean and Variance

The hypergeometric mean and variance summarize what repeated samples from the same finite population tend to look like. The mean, or expected number of successes, equals . Intuitively, sampling ten cards from a deck with four aces yields an average of ≈ 0.769 aces per draw, even though any one draw may show none. The variance quantifies how widely the outcomes are spread and is given by . This factor is the finite population correction; it shrinks the variance as the sample approaches the population in size because there is less uncertainty when you are drawing most of the items.

Hypergeometric vs. Binomial Distribution

The hypergeometric and binomial distributions are often discussed together because they can look similar at a glance. The binomial assumes independent trials with replacement, or a population so large that one draw barely changes the next. The hypergeometric version is the one to use when the pool is finite and each success removed makes the remaining pool slightly different. When the sample is only a small slice of $N$, the binomial can be a convenient approximation; as $n$ becomes a meaningful fraction of $N$, the hypergeometric model preserves the exact changing odds.

Real-World Applications of Hypergeometric Sampling

Hypergeometric sampling shows up whenever you draw from a closed set and cannot put the item back. Quality engineers use it to estimate defect rates in production lots before shipping a batch. Ecologists use capture-and-recapture studies to infer population size from a finite tagged group. In card games, the model helps estimate how often a hand contains a particular combination. It also appears in genetics, where the counts of alleles or traits in a sample can be treated as draws from a finite pool.

Interpreting Hypergeometric Calculator Output

The PMF value is the probability of one exact outcome, while the CDF accumulates every outcome from 0 through $k$. The mean and variance show where the distribution tends to center and how wide the spread is likely to be. If two sampling plans have similar means but different variances, the one with the smaller variance gives more predictable results.

Common Hypergeometric Mistakes and Edge Cases

Hypergeometric calculations go wrong when the four inputs no longer describe the same finite population. A common mistake is letting $k$ exceed either $n$ or $K$, which is impossible because you cannot observe more successes than you draw or than exist. Another is using the model for sampling with replacement, where the binomial distribution fits better. The calculator checks invalid combinations and returns an error when the inputs violate the hypergeometric constraints. A boundary case such as $\mathrm{n=N}$ is still valid, but it collapses the randomness because every item is included in the draw.

How to Use the Hypergeometric Calculator Effectively

To get the most out of the hypergeometric calculator, begin with a real finite-population scenario and adjust one parameter at a time. Watch what happens when $n$ grows relative to $N$: the mean rises with the sample size, while the variance reflects the finite population correction. Try changing $K$ to see how a richer or rarer success set shifts the curve. The combination logic is efficient enough that you can explore larger populations without doing the counting by hand.

Hypergeometric Distribution Summary

The hypergeometric distribution captures the pattern of sampling without replacement from a finite population. Once you know $N$, $K$, $n$, and $k$, the calculator gives you the exact PMF, the cumulative probability, the mean, and the variance for that setup. Use it when each draw changes what remains, such as in inspection plans, card hands, or other finite draws where replacement is not part of the process.

Hypergeometric Limitations and Assumptions

The hypergeometric model assumes a fixed finite population, a single sample drawn without replacement, and a clear success definition that does not change mid-problem. It is a planning aid, not a substitute for the actual sampling rules, audit standards, or source counts behind your data. Results depend on entering consistent $N$, $K$, $n$, and $k$ values that all refer to the same population.