AIC estimates the relative amount of information lost by a model. It balances the goodness-of-fit of the model with the complexity of the model. Formula: AIC= 2𝑘−2ln(𝐿) -- Lower AIC values indicate a better model, considering both the fit and the number of parameters. AIC penalizes the complexity of the model (more parameters), so it discourages overfitting.BIC also evaluates model fit but incorporates a stronger penalty for model complexity compared to AIC. It is derived from a Bayesian perspective. Formula: BIC=ln(n)k−2ln(L) --Like AIC, lower BIC values are preferred. However, BIC has a stricter penalty for models with more parameters, especially when the sample size 𝑛 is large, making it more conservative in selecting simpler models.

Done

I learned in this lecture the simple linear model and polynomial model.

I learned in this video the Simple linear model, Multiple model, and the Polynomial model.

The review of polynomial regression and its introduction, mathematical formulation, key points, assumptions, and important considerations.