Confidence Interval (Proportion) Calculator

ByDr. Hannah Al-Mansoor, PhD ✓ Verified 📚 153 Calculators Authored

Senior Biostatistician & Laboratory Quantitative Methodologist · Ph.D. in Applied Statistics and Quantitative Biology

📅 Published: Sep 28, 2026

The formula

p̂ ± z·√(p̂(1−p̂)∕n), with the Wilson-style correction at the edges

What the proportion confidence interval tells you

The interval around an observed percentage — poll numbers, conversion rates, defect shares — from normal-approximation sampling theory.

Calculation: p̂ ± z·√(p̂(1−p̂)∕n), with the Wilson-style correction at the edges. Enter your inputs and every substitution is shown below the result.

Reading the result

The margin is widest at p near 50% and narrows as proportions approach 0 or 1 — but tiny proportions need exact (Clopper-Pearson) methods instead.

Rules of thumb: 95% ±3pp requires n≈1,000; ±5pp at n≈380

Limitations and best practice

Wald intervals fail hard near boundaries and at small n — a 5/8 conversion rate does not honestly span 0% with ±17pts; use Wilson when counts are small.

This calculator gives an estimate based on standard formulas; it is not professional financial, medical, legal or engineering advice. Verify anything you plan to act on with a qualified professional and your own records.

Frequently asked questions

Wilson vs Wald?

Wilson’s interval has coverage that matches its nominal level even at small samples; Wald is the textbook shortcut that over-promises.

Does the CI account for weighting?

No — design effects from sample weighting inflate real margins ~1.2–1.4×; pollsters report the adjusted figure.

Source & methodology

Wilson (1927) interval; Agresti-Coull correction.

Confidence Interval (Proportion): the number, the method and the caveats

You are here because you need a specific number, and you want to see how it was produced before you rely on it. Searchers land on a Confidence Interval (Proportion) page for three reasons — to plan, to compare options, and to check that somebody else’s arithmetic is honest. This tool serves all three, and everything after the calculator explains the model instead of hiding it.

In Statistics & Data Science, units and significant figures carry meaning; keeping them attached to every output is the quiet professional standard this page maintains.

Most confusion about Confidence Interval (Proportion) comes from mixing up the input you control with the input you merely observe. The formula treats them identically, but your decisions should not: one deserves measurement, the other deserves a defensible estimate.

What makes a calculation page trustworthy is that its copy is derived from its own arithmetic: here observed proportion = 33.8 %, recomputed every time a field changes, and the sensitivity section ranks the inputs that move the result — Trials first, at ≈11.1 % of the headline for a ten-percent error either way in that input. Work down the page and by the end you could re-derive the result in a spreadsheet from memory.

Inside the Confidence Interval (Proportion) calculation: formula and every input

One formula, published in full: p̂ ± z·√(p̂(1−p̂)∕n), with the Wilson-style correction at the edges. Anything you can read, you can reproduce in a spreadsheet, and that reproducibility is the whole point of printing it rather than hiding it behind a button.

Successes observed (example value 67) is a measured number in the unit named by the label; the formula does not convert for you. This input feeds the formula directly; a defensible figure here is worth more than false precision anywhere else.

Trials (example value 198) is a numeric input whose unit is fixed by the label; a wrong unit is a wrong answer wearing a plausible disguise. The example value is there to demonstrate the mechanics, not to describe your situation — overwrite it.

Confidence level (%) (example value 95) is a quantity rather than a category — precision here is cheap and worth having. Rates are the most mis-transcribed input on any page like this; copy it from the document rather than retyping from memory.

Confidence Interval (Proportion) on the example inputs: the complete substitution

Rather than describe the calculation, here it is end to end — every substitution in order, starting from the inputs above. Starting figures: Successes observed, Trials, Confidence level (%). The endpoint of that chain is 33.8 % of observed proportion, sitting in the “95% CI: 27.2% – 40.4% — a tight read on the population share” band.

p̂ = 67 ÷ 198 = 0.338; SE = 0.0336
CI = 33.8% ± 1.96×6.6% → [27.2, 40.4]

Lower bound — 27.2 %. This is the number experienced users quote when the headline alone would mislead.

Upper bound — 40.4 %. If your inputs change, this is usually the first companion figure to move.

Margin of error — 6.6 %. If your inputs change, this is usually the first companion figure to move.

n for half this margin — 792. Read next to the headline, this is the figure that shows the shape of the trade-off.

Overwrite any input above and every line of this example updates with it — the substitution is live, not a screenshot of somebody else’s numbers.

Scenario table: Confidence Interval (Proportion) at ±10 % and ±20 % of the key input

Single-point answers invite false confidence, so the same engine was run across a band around the input that matters most here. Each row is a full recalculation of Confidence Interval (Proportion), not an interpolation.

Trials setting	Observed proportion
80 % of the example value	42.3 %
90 % of the example value	37.6 %
example inputs	33.8 %
110 % of the example value	30.8 %
120 % of the example value	28.2 %

That spread — 28.2 % at the low end, 42.3 % at the high — is what a careful read of Confidence Interval (Proportion) looks like: a band you can state out loud, with the reason for each edge. Reproduce it in the form above by editing Trials alone; the substitution steps will follow your figures exactly.

What actually moves your Confidence Interval (Proportion)

Nobody should have to guess which input matters. The engine was re-run once per field below — ten percent up, ten percent down, everything else frozen — and the results ranked by how far they moved the observed proportion. For Confidence Interval (Proportion) the ranking is measured rather than guessed, and it belongs to these defaults: shift the starting point and the order can shift with it.

Trials: ten percent up gives 30.8 %, ten percent down gives 37.6 % — ≈11.1 % of the observed proportion either way
Successes observed: ten percent up gives 37.2 %, ten percent down gives 30.5 % — ≈10.0 % of the observed proportion either way

Trials is the dominant lever here: ten percent either way moves the result by about 11.1 %, from 30.8 % to 37.6 %. Measure that input from a document rather than from memory, and treat Successes observed as the second priority (≈10.0 % per ten percent). Everything below that can stay approximate, which is a licence to stop chasing data that would not change the decision.

Reading the result: bands, zones and thresholds

The value above only becomes useful the moment you know what it is being measured against. On the example inputs the band reads “95% CI: 27.2% – 40.4% — a tight read on the population share”; your own figures place you on a different rung of the same ladder. How much of that band is luck? On Trials alone ten percent either way covers 30.8 % to 37.6 %. The practical reading rules: ask what would have to change to move you one band. If the answer is “a small, plausible input difference”, the band itself is not the finding — the uncertainty is.

The comparison worth making is not with somebody else’s Confidence Interval (Proportion) but with the version of your own situation measured last quarter — same formula, same conventions, different inputs.

Common mistakes with Confidence Interval (Proportion) (and the fix)

Wald intervals fail hard near boundaries and at small n — a 5/8 conversion rate does not honestly span 0% with ±17pts; use Wilson when counts are small. This calculator gives an estimate based on standard formulas; it is not professional financial, medical, legal or engineering advice. Verify anything you plan to act on with a qualified professional and your own records.

Copying a single headline number without checking the companion outputs. The tool reports Lower bound, Upper bound and Margin of error alongside the main result precisely because Confidence Interval (Proportion) in isolation misleads — the secondary columns are where outliers and trade-offs show up.

This model has its own particular trap: Trials carries ≈11.1 % of the response per ten percent of error, so effort spent elsewhere is largely decorative.

A final trap is presentation: reporting Confidence Interval (Proportion) to more decimal places than the inputs support. The tool prints what the arithmetic gives; you should quote only what your least precise field justifies.

Before you trust your Confidence Interval (Proportion): a short checklist

Recompute once with the dominant input deliberately set low, and see whether the decision changes.
Check that every field the formula needs actually arrived from a document, not from recollection.
Put Trials under a magnifier; the sensitivity table above is the reason why.
State, in one sentence, which convention each rate, unit or period in the form is using.
Compare the output against one published benchmark or a colleague’s independent estimate.
Repeat the ±10 % test on the inputs that matter and see whether the decision — not just the number — still holds.

A routine for decision-grade Confidence Interval (Proportion)

Using a calculator well sounds trivial, but the difference between a decision-grade figure and a throwaway one lives entirely in the routine. The routine for Confidence Interval (Proportion) takes a minute to learn and applies to every input above.

Step 1 — one document, one pass. Open the statement, label or record that holds successes observed, trials, confidence level (%) and transcribe straight into the form. Transcription from a single source removes the mismatch errors that appear when figures are assembled from three different places. Write the assumptions in the same file as the result, and future arguments take minutes instead of meetings.

Step 2 — enter the conservative case first. Resist the flattering scenario. Type the inputs you would defend in front of a sceptical reader, read the Observed proportion (33.8 % for the example values), and note the verdict band. A figure nobody can reproduce is a figure nobody will act on twice.

Step 3 — change one input at a time. Nudge a single field by ten percent, watch the headline and its companions move, then undo it. Two or three fields will dominate — the sensitivity table above already ranks them for this engine. If the verdict changes with a ten-percent nudge, report the nudge alongside the number.

Step 4 — stress before you commit. A decision that survives a ten-percent squeeze on its two biggest inputs needs no luck to be sound. One that does not survive is a decision about hope, not about arithmetic. Comparisons are cheap: run the identical calculation for the alternative and look at the gap.

Step 5 — save the story with the figure. A number without its inputs and its date is unusable within a quarter. Record 33.8 %, the assumptions behind it, and today’s date; your future self will be auditing a stranger’s arithmetic. A calculation you cannot explain to somebody else is a calculation you cannot defend.

From calculation to decision: where Confidence Interval (Proportion) earns its keep

In Statistics & Data Science the figure computed here is usually the first one somebody asks to see. Having it — with the formula behind it — changes your position in the conversation from participant to reference. Re-running a number costs seconds; retracting a decision costs considerably more.

Professionals in Statistics & Data Science use this style of calculation as a screening filter before spending real money or effort: a quick Confidence Interval (Proportion) check eliminates weak options in minutes, and the survivors earn the deeper, slower analysis. The input you reach for first is usually the one you measured longest ago.

There is a personal-administration use people overlook: periodic self-checking. Confidence Interval (Proportion) quietly drifts as life changes — rates move, bodies change, costs compound — and re-running it a few times a year catches drift while correction is still cheap. Comparisons are cheap: run the identical calculation for the alternative and look at the gap.

Key terms on this page

Lower bound: 27.2 % for the Confidence Interval (Proportion) worked case; it sits next to the main result because it carries context the headline leaves out.
Upper bound: 40.4 % on the example inputs — a companion figure printed beside the headline of Confidence Interval (Proportion) so that no result is read in isolation.
Margin of error: 6.6 % on the example inputs — a companion figure printed beside the headline of Confidence Interval (Proportion) so that no result is read in isolation.
Observed proportion: The primary output of this tool: 33.8 % for the default inputs, computed exactly from p̂ ± z·√(p̂(1−p̂)∕n), with the Wilson-style correction at the edges.
Worked example: The step-by-step substitution printed above, so the arithmetic can be re-derived by hand or in a spreadsheet.
Verdict band: The interpretation attached to a result (“95% CI: 27.2% – 40.4% — a tight read on the population share” on these inputs), which turns a bare number into a position on a scale.
Sensitivity (±10 %): How far the Confidence Interval (Proportion) moves when a single input is nudged ten percent either way; the ranked list on this page is computed live from this engine.

The provenance of this Confidence Interval (Proportion) calculation

There is no black box on this page — the engine evaluates p̂ ± z·√(p̂(1−p̂)∕n), with the Wilson-style correction at the edges. Source of record: Wilson (1927) interval; Agresti-Coull correction. Any other implementation of this model should return the same figure for the same inputs. If one does not, the difference is in its assumptions — which this page prints and that one probably does not.

Treat the output as a precise answer to the question you typed: exact arithmetic, transparent formula, published source, no hidden rounding. The sensitivity table above is part of that promise rather than a bonus: it lets you see how much of the result depends on how carefully you measured.

Next steps after the calculation

Re-run the calculation with your own figures, stress the two most sensitive inputs by ±10 %, and only then act on the result.

Whoever you are (people who need one trustworthy number before their next decision), the next step is the same: replace the example inputs with your own, note the date, and re-run whenever a figure moves. In Science & Research, a dated figure is a trend, and an undated one is a rumour.