AIC And BIC Calculator

Work out aic and bic instantly with clear inputs, formula shown and shareable results.

About AIC And BIC Calculator

Both criteria score a fitted model as goodness of fit minus a complexity penalty, and lower is better. AIC charges 2 per parameter; BIC charges ln(n) per parameter, so once the sample exceeds about 8 observations BIC penalises complexity harder and tends to select smaller models. AICc adds a small-sample correction and should be preferred when n divided by k is below roughly 40.

Formula

Information criteria

AIC = 2k - 2 ln(L); BIC = k ln(n) - 2 ln(L); AICc = AIC + 2k(k+1) / (n - k - 1)

k: Estimated parameters
L: Maximised likelihood
n: Sample size

Worked example

With the default values below, AIC And BIC Calculator returns AIC of 924.000. Change any input above and every figure here is recalculated in your browser.

Inputs used

Maximised log-likelihood: -450
Number of estimated parametersminimum 1: 12
Sample sizeminimum 2: 500

Results

AIC: 924.000
BIC: 974.575
AICc (small-sample corrected AIC): 924.641
Extra penalty BIC applies over AIC: 50.575

Step by step

1Values used
2Information criteria
3AIC= 924.000
4BIC= 974.575
5AICc (small-sample corrected AIC)= 924.641
6Extra penalty BIC applies over AIC= 50.575

Assumptions and limits

The result is derived only from the 3 inputs listed above. Anything not among them is not part of the calculation.
In particular, this calculator does not take inflation, tax, fees or charges or compounding frequency into account.
Figures are rounded for display to 3 decimal places, so totals built from several rounded parts can differ slightly from the unrounded arithmetic.

How these calculators are built and tested is described on the Methodology page. If a figure looks wrong, please report it.

Frequently Asked Questions

Can I compare AIC across different datasets?

No. The criteria are only comparable between models fitted to exactly the same observations, because the likelihood scale depends on the data.

What counts as a meaningful difference?

A gap of 2 to 4 is weak evidence, 4 to 10 is considerable and above 10 is strong evidence against the higher-scoring model.