Compute model weights according to the information criterion scores of each model.
The information criterion scores.
The formula is quite simple: Identify the smallest (best) score among the various models. Subtract this minimum value from all of the scores, and call the resulting set of scores $s$. Compute exp(-0.5 s) for all the scores, and normalize the resulting vector to obtain the vector of model weights
A vector of weights, which can be interpreted (loosely) as the relative desireability of the models corresponding to the weights
Burnham and Anderson (2002)
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.