How to Use the Effect Size Calculator

  1. 1. Choose the effect-size family: Pick the mode that matches your study: two independent groups, paired/repeated, one sample, from a t statistic, from ANOVA, from correlation, from binary outcomes, or conversion between measures. Each mode uses its own formula.
  2. 2. Enter the data for your design: Independent groups accept summary statistics (mean, SD, n) or raw observations. Paired mode takes before/after lists — pairs are matched by position and must have equal length. Other modes take the specific inputs they need: a t statistic with its design, sums of squares, a correlation coefficient, event counts, or a value to convert.
  3. 3. Set the design sub-options: For independent groups, choose which group's SD is the reference for Glass's Δ. For from-t, choose the t-test design (independent, one-sample, or paired) so the correct conversion is applied. For all d-based modes, choose 90%, 95%, or 99% confidence.
  4. 4. Read the primary result and diagnostic table: The hero figure shows the headline measure for the current mode — typically Cohen's d. The results table below lists every measure that mode produces: mean difference, pooled SD, d, Hedges' g, Glass's Δ, effect-size r, CLES, and a confidence interval where applicable.
  5. 5. Review the formula and steps: The formula panel shows the equation used for the current mode, with a short explanation of what it does. The step-by-step list writes out the arithmetic — the intermediate values for pooled SD, the mean difference, the sign, and the final effect size.
  6. 6. Cross-check the interpretation: The interpretation line gives the direction and a benchmark note (small / medium / large) based on Cohen's conventional guidelines. Treat those labels as rough orientation only — the practical meaning of any effect size depends on the field, the outcome, and the decision context.

What Is Effect Size?

Effect size describes how large a difference or association is, independent of sample size. It complements the p-value, which says whether there is statistical evidence against a null hypothesis but says nothing about magnitude. A large sample can produce a significant p-value for a trivial effect; a small sample can miss a substantial one. Effect size is the number that answers "how big."

Some effect sizes are standardized (Cohen's d, Hedges' g, r), which lets you compare effects across studies that used different measurement scales. Others are unstandardized (raw mean difference, risk difference), which keeps the effect in the original units. The right choice depends on the study design and outcome type.

Calculator Modes

The calculator supports eight design families: two independent groups, paired/repeated, one sample, from a t statistic, from ANOVA, from correlation, from binary outcomes, and conversion between measures. Each mode applies its own formula — the calculator does not run one generic effect-size formula on every design.

Cohen's d, Hedges' g, and Glass's Δ

For two independent groups, Cohen's d standardizes the mean difference by the pooled SD:

d = (M₁ − M₂) / sₚ , sₚ = √[((n₁−1)s₁² + (n₂−1)s₂²) / (n₁+n₂−2)]

The pooled SD weights each group's variance by its degrees of freedom. The sign of d follows M₁ − M₂; the magnitude is the effect size. With the calculator's default inputs (M₁ = 85, SD₁ = 10, n₁ = 30; M₂ = 78, SD₂ = 11, n₂ = 30), the mean difference is 7, the pooled SD is about 10.51, and d ≈ 0.67.

Hedges' g multiplies d by the small-sample correction J(df) ≈ 1 − 3/(4·df − 1). With large df the correction is negligible; with small samples (df under about 20) it makes a real difference. Hedges' g is generally preferred when reporting or pooling effects from small studies.

Glass's Δ divides the mean difference by a single reference-group SD instead of a pooled SD: Δ = (M₁ − M₂) / SD_ref. Use it when the treatment group's variance is expected to differ substantially from the control's — pooling would then mix two different scales. The calculator lets you choose which group's SD is the reference.

Paired and One-Sample Designs

Paired designs use a different effect-size definition based on within-pair differences:

d_z = mean(dᵢ) / SD(dᵢ) , dᵢ = afterᵢ − beforeᵢ

This is often called d_z or the repeated-measures standardized effect. It is not interchangeable with independent-groups Cohen's d — same letter, different denominator. The calculator reports the paired version separately and never substitutes one for the other.

One-sample designs compare a sample mean against a reference value: d = (M − μ₀) / SD. Hedges' correction applies the same way, with df = n − 1.

From a t Statistic

Converting a published t to an effect size depends on the design:

  • Independent groups: d = t × √(1/n₁ + 1/n₂)
  • One-sample or paired: d = t / √n

There is no single universal t-to-d rule. Applying a formula like 2t/√df across every t-test design produces wrong answers because the degrees of freedom do not encode the sample sizes each formula needs. The calculator asks for the design first, then applies the matching conversion. CLES is only computed for the independent-groups case.

ANOVA Effect Sizes

The ANOVA mode takes the sums of squares from an ANOVA table and computes:

  • η² = SS_effect / SS_total — the proportion of total variability associated with the effect.
  • Partial η² = SS_effect / (SS_effect + SS_error) — the proportion of variance associated with the effect after partialling out the error term.
  • Cohen's f from η² = √(η² / (1 − η²)).
  • Cohen's f from partial η² = √(partial η² / (1 − partial η²)).

The calculator reports both Cohen's f values separately because they are computed from different denominators and can differ in factorial or repeated-measures designs. η² and partial η² coincide only in one-way ANOVA; elsewhere they mean different things and should not be substituted for each other.

Correlation Effect Sizes

For correlation, r is the effect size and r² is the proportion of variance explained by the linear relationship. When you have two independent correlations, the calculator also computes Cohen's q = z(r₁) − z(r₂) using the Fisher z transform. q compares two correlations on the z scale — it is a comparison measure, not the same thing as r itself, and it only applies when the correlations come from independent samples.

Binary Outcomes

For binary outcomes the calculator reports:

  • Risk difference (RD) = p₁ − p₀
  • Risk ratio (RR) = p₁ / p₀
  • Odds ratio (OR) = ((events + 0.5) / (non-events + 0.5))_treatment / ((events + 0.5) / (non-events + 0.5))_control

The OR always applies a 0.5 Haldane–Anscombe adjustment to all four cell counts, which keeps the ratio finite if any cell is zero. RD and RR are computed on the raw proportions. log(RR) and log(OR) are also reported. These measures describe risk and odds — they are not standardized mean differences and should not be labeled as Cohen's d.

CLES and Effect-Size r

Two additional measures appear alongside d in the independent-groups mode and the from-t independent design:

  • Effect-size r = d / √(d² + 4). This is a correlation-style representation of d. It is a model-based conversion, not a Pearson correlation computed from raw paired observations.
  • CLES = Φ(d / √2). The Common Language Effect Size expresses the comparison as a probability — the probability that a randomly chosen observation from Group 1 exceeds a randomly chosen observation from Group 2, under a normal equal-variance model. The direction of comparison depends on which group is labeled Group 1.

Neither measure adds sample information. Both repackage the same d under different assumptions. The conversion mode also computes CLES when converting from d or r.

Confidence Intervals

For d in independent-groups, paired, and one-sample modes, the calculator reports an approximate standard error and a confidence interval at 90%, 95%, or 99%. The SE uses a Hedges–Olkin-style approximation; the interval assumes approximately normal sampling of d. These intervals are adequate for typical sample sizes but less reliable in small samples with unequal variances, where a bootstrap or robust estimator would be preferred.

Interpretation and Benchmarks

Cohen's conventional benchmarks — 0.2 small, 0.5 medium, 0.8 large — are rough orientation values, not universal definitions of practical importance. A d of 0.5 in one research area might be trivial; in another, 0.3 might be important. The sign indicates direction; the magnitude describes standardized distance. Report both alongside the design, the measurement scale, and the practical context.

Effect Size vs Statistical Significance

A p-value answers whether the data provide evidence against a null hypothesis. Effect size answers how large the observed effect is. A very large sample can produce a significant p-value for a d of 0.05; a small sample can miss a d of 1.0. Both are useful, but they answer different questions, and reporting one without the other leaves the picture incomplete.

Comparison Table

MeasureTypical use
Cohen's dIndependent-groups standardized mean difference
Hedges' gSmall-sample corrected standardized mean difference
Glass's ΔStandardized difference using a reference-group SD
d_zPaired standardized effect (within-pair differences)
Effect-size rCorrelation-style representation of d
η²ANOVA proportion of total variance
Partial η²ANOVA proportion after partialling out error
Cohen's fStandardized ANOVA effect
Cohen's qDifference between two Fisher-z correlations
CLESProbability-based group comparison
RD / RR / ORBinary outcome measures

Common Mistakes

  • Reporting a p-value without an effect size, or an effect size without a p-value.
  • Using independent-groups d on paired data (or vice versa). The denominators are different.
  • Calling every standardized difference "Cohen's d." Hedges' g, Glass's Δ, and d_z use different standardizers.
  • Confusing η² with partial η². They coincide in one-way ANOVA but diverge in factorial and repeated-measures designs.
  • Applying a single t-to-d formula across every t-test design. Independent and one-sample/paired need different conversions.
  • Treating 0.2 / 0.5 / 0.8 as universal thresholds.

Frequently Asked Questions

Q: What is a good effect size?

There is no universal answer. Cohen's 0.2 / 0.5 / 0.8 orientation values describe small, medium, and large in a general sense, but the practical importance of any effect depends on the research field, the outcome being measured, the measurement scale, and the consequences of the decision the study is informing. Report the effect size with its confidence interval and let the field context guide the interpretation.

Q: Can an effect size be negative?

Yes. The sign indicates direction — for example, that Group 1 has the lower mean, or that the correlation is negative. The absolute value describes the magnitude of the effect. The sign is only meaningful when the group order or reference direction is stated, so report it alongside the definition you used.

Q: What is the difference between Cohen's d and Pearson's r?

Cohen's d is a standardized mean difference — a difference between group means expressed in standard-deviation units. Pearson's r measures the strength and direction of a linear association between two variables. They can be converted into each other under specific assumptions (r = d / √(d² + 4)), but they describe different kinds of effects and are not interchangeable across study designs.

Q: What do the numbers 0.2, 0.5, and 0.8 mean for Cohen's d?

They are rough orientation values commonly described as small, medium, and large. They originated as general guidelines, not as universal thresholds. A d of 0.5 in one research area might be trivial, while a d of 0.3 in another might be practically important. Use them to frame a discussion, not to make a verdict.

Q: How do I report an effect size?

Report the effect size measure, the value, and a confidence interval where available — for example: "Cohen's d = 0.67, 95% CI [0.15, 1.19]." Also state which formula was used (pooled-SD d, Hedges' g, d_z, and so on), because the same letter "d" can refer to different standardizers in different designs.

Q: Why do paired and independent designs use different effect-size formulas?

Paired designs operate on within-pair differences, so the natural standardizer is the SD of those differences — this is d_z. Independent groups have two separate SDs, which are combined into a pooled SD. Applying independent-groups d to paired data ignores the pairing and produces an effect size that does not match the design of the test.

Q: What is the difference between η² and partial η²?

η² = SS_effect / SS_total describes the proportion of total variability associated with the effect. Partial η² = SS_effect / (SS_effect + SS_error) describes the proportion of variance associated with the effect after partialling out the error term. In a one-way ANOVA the two are equal; in factorial or repeated-measures designs they are not, and they should not be reported as if they were the same quantity.

Q: Can I convert a published t statistic to Cohen's d?

Yes, but the formula depends on the design. For independent groups: d = t × √(1/n₁ + 1/n₂). For one-sample or paired designs: d = t / √n. There is no single universal rule — applying a formula like 2t/√df across every design gives wrong answers. The calculator asks for the design first and then applies the matching conversion.

Q: What is the difference between effect size and statistical significance?

A p-value answers whether the data provide statistical evidence against a null hypothesis. Effect size answers how large the observed effect is. A very large sample can produce a significant p-value for a trivial effect; a small sample can miss a large one. Reporting one without the other leaves the picture incomplete.

Q: What is Cohen's q?

Cohen's q = z(r₁) − z(r₂), where z is the Fisher z transform of a correlation coefficient. It measures how different two independent correlations are on the Fisher-z scale. It is a comparison measure and only applies when the two correlations come from independent samples — it is not the same thing as r itself.

Q: Can I enter raw data instead of summary statistics?

Yes, for the independent-groups mode. Paste each group's observations into the two text areas — separated by commas, spaces, or new lines — and the calculator computes the group means, SDs, and sample sizes before calculating the effect size. For other modes, enter the summary inputs the mode expects (paired differences, means and SDs, t statistic, sums of squares, correlation, or event counts).

Q: What confidence interval does the effect size calculator report?

For Cohen's d in independent-groups, paired, and one-sample modes, the calculator reports an approximate standard error and a confidence interval at 90%, 95%, or 99% — your choice. The SE uses a Hedges–Olkin-style approximation and the interval assumes approximately normal sampling of d. For small samples with unequal variances, these intervals are less reliable than a bootstrap alternative.

Loaded shared calculation