Skip to content
Statculator

P-Value and Critical Value Calculators

Free p-value and critical value calculator: turn a z, t, chi-square, F or r statistic into a p-value, find the critical value for any α, and see the decision.

Find a p-value and critical value now

Updated · Formulas and conventions follow our methodology

In short

A p-value is the probability, if the null hypothesis is true, of a test statistic at least as extreme as yours. A critical value is the cut-off the statistic must pass to be significant at level α. Reject H₀ when p ≤ α, or equivalently when the statistic passes the critical value. The calculator below gives both for z, t, χ², F and r statistics.

Choose the type of test statistic (z, t, χ², F or r), enter its value and degrees of freedom, and pick the tail and α. You get the p-value, the critical value, the reject or fail-to-reject decision and the shaded curve. For a single distribution, or for a critical value with no statistic yet, use a calculator from the list below.

Full P-Value Calculator page with formulas and FAQ
Try

Pick the distribution your test statistic follows when H₀ is true.

Tail

Left for H₁: “less than”, right for H₁: “greater than”, two-tailed for H₁: “not equal to”.

Leave blank to get the p-value without a decision.

Results

p-value (two-tailed)
0.0251
p = 2 × P(Z ≥ |2.24|)
Critical z at α = 0.05
±1.96

Significant at α = 0.05: reject H₀

p = 0.0251 ≤ 0.05. A result this extreme would be unusual if H₀ were true.

Null distribution
Z ~ N(0, 1)
Left tail, P(Z ≤ z)
0.9875
Right tail, P(Z ≥ z)
0.0125
Two-tailed, 2 · P(Z ≥ |z|)
0.0251

Interpretation: Assuming H₀ is true, a z statistic at least as extreme as the one observed would occur about once in every 40 repetitions. That is moderate evidence against H₀.

normal distribution curve with the shaded probability region, markers at z = 2.24, -2.24-2.24z = 2.24-4-3-2-101234Standard normal distribution, Z ~ N(0, 1)
Shaded area = p-value = 0.0251 (both tails together). Dashed line: your statistic.

Decision at common significance levels (two-tailed)

αCritical zReject H₀?
0.1±1.6449Yes
0.05±1.96Yes
0.025±2.2414No
0.01±2.5758No
0.005±2.807No
0.001±3.2905No

p = 0.0251. “Yes” means p ≤ α, which is the same as the statistic landing in the rejection region.

Step-by-step solution

  1. 1

    Identify the null distribution

    When H₀ is true, the z statistic follows the standard normal distribution.

    Z ~ N(0, 1)
  2. 2

    Write the p-value as a probability

    The curve is symmetric, so the two-tailed p-value is twice the area beyond |statistic|.

    p = 2 × P(Z ≥ |2.24|)
  3. 3

    Find the tail areas and the p-value

    Each area comes from the cumulative distribution function (CDF) of the null distribution.

    P(Z ≥ 2.24) = 0.012545
    p = 2 × 0.012545 = 0.0251
  4. 4

    Decision: reject H₀

    p = 0.0251 ≤ α = 0.05
    Reject H₀ if |z| ≥ 1.96; observed z = 2.24

All 13 p-value and critical value calculators

P-values, critical values and the decision

Use these calculators when you already have a test statistic, from software output, a published paper or a hand calculation, and need its p-value, or when you need a critical value that a printed table does not list. They give exact values for any degrees of freedom and any α, so you are not limited to the rows of the z table, t-table, chi-square table, F-table or r critical value table. To run the whole hypothesis test from raw data instead, start from the Hypothesis Testing Calculators calculators.

The p-value approach and the critical-value approach always reach the same decision about the null hypothesis: reject H₀ when p ≤ α, which happens exactly when the statistic falls in the rejection region beyond the critical value. The tail matters. For the symmetric z and t distributions, a two-tailed p-value is twice the one-tailed value, while χ² and F tests are normally right-tailed. Very small p-values are shown in scientific notation rather than rounded to zero.

A p-value is not the probability that H₀ is true, and p ≤ 0.05 does not show that an effect is large or important. The American Statistical Association’s statement on p-values recommends reporting the exact p-value with an effect size or confidence interval rather than only “significant” or “not significant”. For a plain-language explanation, read What Is a P-Value? Meaning, Calculation and Common Mistakes.

How to find a p-value and a critical value

  1. Identify the test statistic and its distribution. z-tests give a z statistic, t-tests a t with df, chi-square tests a χ² with df, ANOVA and regression an F with two df, and a correlation an r with n − 2 df.
  2. Fix the tail and α before looking at the data. H₁ with ≠ is two-tailed; H₁ with < or > is one-tailed. α = 0.05 is the usual default.
  3. Calculate the p-value as the area beyond the statistic in the direction of H₁. For a two-tailed z or t test, p = 2 × P(T ≥ |t|); for χ² and F, take the right-tail area.
  4. Find the critical value with the inverse distribution: the point that leaves α in the tail (α/2 in each tail for a two-tailed test). For a two-tailed z-test at α = 0.05 it is ±1.960.
  5. Decide. Reject H₀ if p ≤ α, or equivalently if the statistic is beyond the critical value; otherwise fail to reject H₀. Both checks must agree, which is a quick test of your arithmetic.

P-value and critical value worked examples

Each example runs in the calculator above with the same inputs, and each shows the p-value approach and the critical-value approach side by side.

Two-tailed z-test: z = 2.24 at α = 0.05

Problem. A one-sample z-test gives z = 2.24 with H₁: μ ≠ μ₀. What is the p-value, and is the result significant at α = 0.05?

  1. 01Take the area beyond |z| in one tail and double it.
    P(Z ≥ 2.24) = 1 − Φ(2.24) = 1 − 0.98745 = 0.01255
    p = 2 × 0.01255 = 0.0251
  2. 02Find the two-tailed critical value, which leaves 0.025 in each tail.
    z* = Φ⁻¹(0.975) = 1.960

Answer. p = 0.0251 ≤ 0.05 and |2.24| > 1.960, so both approaches reject H₀.

t-test with 12 degrees of freedom: t = 2.6

Problem. A one-sample t-test on n = 13 observations gives t = 2.6, two-tailed, α = 0.05. Find the p-value and the critical value.

  1. 01Degrees of freedom for a one-sample t-test.
    df = n − 1 = 12
  2. 02Double the right-tail area of the t(12) distribution.
    p = 2 × P(T₁₂ ≥ 2.6) = 0.0232
  3. 03The critical value is wider than z’s 1.960 because df is small.
    t* = t₀.₉₇₅,₁₂ = 2.179

Answer. p = 0.0232 and 2.6 > 2.179, so reject H₀ at α = 0.05.

Right-tailed chi-square test: χ² = 9.21, df = 3

Problem. A chi-square goodness-of-fit test with 4 categories gives χ² = 9.21. Is the fit rejected at α = 0.05?

  1. 01Degrees of freedom are categories − 1.
    df = 4 − 1 = 3
  2. 02Chi-square tests are right-tailed, so take the area above the statistic.
    p = P(χ²₃ ≥ 9.21) = 0.0266
  3. 03The critical value leaves α = 0.05 in the right tail.
    χ²* = χ²₀.₉₅,₃ = 7.815

Answer. p = 0.0266 and 9.21 > 7.815, so reject H₀: the observed counts do not fit the expected proportions.

Which p-value or critical value calculator should I use?

If you want to…Use
If you have any test statistic and want its p-value and critical value in one place
If you want a z, t, χ², F or r critical value for any α and tail from one tool
If you have a z-score or z statistic
If you have a t statistic and its degrees of freedom
If you have a chi-square statistic
If you have an F statistic from ANOVA, regression or a variance test
If you have a correlation coefficient and a sample size
If you need the critical value for a confidence level, such as 1.96 for 95%
If you are not sure how many degrees of freedom your test has

How these p-values and critical values are calculated

Every p-value and critical value on this hub is computed from the exact cumulative distribution function and its inverse, not read from a table, and the engine is tested against reference values from SciPy; see the methodology. Printed critical values match the NIST/SEMATECH e-Handbook tables for the t distribution and the chi-square distribution.

P-value conversions and common critical values

QuantityFormula or valueNotes
Two-tailed p from zp = 2[1 − Φ(|z|)]Φ is the standard normal CDF
Two-tailed p from tp = 2 · P(T ≥ |t|), T ~ t(df)df = n − 1 for a one-sample test
Right-tail p from χ²p = P(X ≥ χ²), X ~ χ²(df)Goodness-of-fit and independence tests
Right-tail p from Fp = P(X ≥ F), X ~ F(df₁, df₂)ANOVA and regression F-tests
r to tt = r√(n − 2) / √(1 − r²)df = n − 2
Two-tailed z critical valuez* = Φ⁻¹(1 − α/2)1.645, 1.960, 2.576 for α = 0.10, 0.05, 0.01
One-tailed z critical valuez* = Φ⁻¹(1 − α)1.282, 1.645, 2.326 for α = 0.10, 0.05, 0.01
Two-tailed t critical values (α = 0.05)2.228, 2.042, 1.984df = 10, 30, 100; approaches 1.960 as df grows
Right-tail χ² critical values (α = 0.05)3.841, 5.991, 7.815, 9.488df = 1, 2, 3, 4
Welch degrees of freedom(s₁²/n₁ + s₂²/n₂)² / [(s₁²/n₁)²/(n₁ − 1) + (s₂²/n₂)²/(n₂ − 1)]Usually not a whole number

P-value and critical value terms

TermMeaning
Null hypothesis, H₀The statement of no effect or no difference that the test assumes, such as μ = 50.
Alternative hypothesis, H₁What you conclude if H₀ is rejected. ≠ gives a two-tailed test; < or > gives a one-tailed test.
Test statisticA number such as z, t, χ², F or r that measures how far the sample is from what H₀ predicts.
p-valueThe probability, if H₀ is true, of a test statistic at least as extreme as the one observed.
Significance level, αThe largest false-positive (Type I error) rate you accept, fixed before the test; usually 0.05.
Critical valueThe value of the test statistic that leaves exactly α in the rejection region.
Rejection regionThe values of the statistic beyond the critical value. A statistic inside it leads to rejecting H₀.
One-tailed and two-tailedA one-tailed test puts all of α in one tail; a two-tailed test splits it, α/2 in each tail.
Degrees of freedomThe number that sets the exact shape of the t, χ² and F distributions, usually based on sample size.
Confidence level1 − α. A 95% confidence interval uses the same critical value as a two-tailed test at α = 0.05.

Frequently asked questions

What is the difference between a p-value and a critical value?

A p-value is a probability computed from your observed statistic, while a critical value is a fixed cut-off on the statistic’s scale determined by α and the tail. Comparing p with α and comparing the statistic with the critical value always give the same decision. The p-value is more informative because it shows how strong the evidence is, not just which side of the line it falls on.

How do I calculate a p-value?

Identify the statistic’s distribution and degrees of freedom, then find the probability of a value at least as extreme in the direction of the alternative hypothesis. For a two-tailed z or t test, double the area beyond |statistic|; for χ² and F, take the right-tail area. For z = 2.24, two-tailed, p = 2 × (1 − 0.98745) = 0.0251. The P-Value Calculator handles all five common statistics.

How do I calculate a critical value?

Apply the inverse of the statistic’s distribution to the tail area set by α. For a two-tailed test use 1 − α/2, so z* = Φ⁻¹(0.975) = 1.960 at α = 0.05; for a one-tailed test use 1 − α, giving 1.645. For t, χ² and F you also need the degrees of freedom: t* = 2.179 for df = 12, two-tailed. The Critical Value Calculator returns any of these.

Is p = 0.05 a critical value?

No. 0.05 is usually the significance level α, a probability you compare the p-value with. The critical value is on the scale of the test statistic: at α = 0.05 it is ±1.960 for a two-tailed z-test, 1.645 for a one-tailed z-test, and 3.841 for χ² with 1 df. Reject H₀ when p ≤ 0.05, or equivalently when the statistic passes the critical value.

What is the critical value for 95% confidence?

For a z-based interval or a two-tailed z-test at α = 0.05, the critical value is 1.960. A t-based interval uses a larger value that depends on the degrees of freedom: 2.262 for df = 9, 2.093 for df = 19 and 2.045 for df = 29, approaching 1.960 as df grows. Look up others in the T Critical Value Calculator.

Why is my p-value shown in scientific notation?

A p-value is never exactly zero, so when it is smaller than the chosen number of decimal places can show (below 0.0001 at the default four decimals), Statculator displays it in scientific notation, such as 3.21 × 10⁻⁸. This keeps the true size visible instead of a misleading 0.0000. In a report you can write p < 0.001.

How do I convert a one-tailed p-value to a two-tailed p-value?

For symmetric distributions such as z and t, the two-tailed p-value is twice the smaller tail area: a one-tailed p of 0.03 becomes a two-tailed p of 0.06. If the one-tailed p is above 0.5 because the statistic went the other way, double 1 − p instead. χ² and F tests are almost always reported as right-tailed, so this conversion does not apply to them.

How do I find the degrees of freedom for my test?

It depends on the test: n − 1 for a one-sample or paired t-test, n₁ + n₂ − 2 for a pooled two-sample t-test, (r − 1)(c − 1) for a chi-square test of independence, k − 1 and N − k for one-way ANOVA, and n − 2 for a correlation or simple regression. Welch’s t-test uses a formula that usually gives a non-integer. The Degrees of Freedom Calculator covers each case.

Why use a calculator instead of a printed statistical table?

Printed tables list only selected degrees of freedom and significance levels, so you often have to round or interpolate. A calculator gives the exact critical value or p-value for any df and any α, including non-integer Welch degrees of freedom. The tables remain useful for learning and exams, and each one on Statculator includes an exact lookup.

Looking for something else? See all calculators or search the site.