Calculate Aic By Hand

Introduction & Importance

Calculate Akaike Information Criterion (AIC) by hand with our interactive tool. AIC is a measure of the goodness of fit of a statistical model, and it’s crucial for model selection and comparison.

How to Use This Calculator

1. Enter the number of parameters (k) in your model.
2. Enter the sample size (n).
3. Enter the log-likelihood (LL) of your model.
4. Click ‘Calculate’ to find the AIC value.

Formula & Methodology

The AIC formula is: AIC = 2k – 2LL + 2p/n, where:

• k is the number of parameters,
• LL is the log-likelihood,
• p is the number of predictors, and
• n is the sample size.

Real-World Examples

Data & Statistics

Comparison of AIC values for different models

Model	k	LL	AIC
Model 1	5	-1200	2008
Model 2	7	-1180	2012

Effect of sample size on AIC

n	AIC
100	2010
500	2005
1000	2002

Expert Tips

• Lower AIC values indicate better models.
• Consider using AICc (corrected AIC) for small sample sizes.
• Always compare models with the same data and predictors.

Interactive FAQ

What is the difference between AIC and BIC?

…

For more information, see the Wikipedia article on AIC and the original AIC paper by Hirotsugu Akaike.