# metric accuracy for linear regression and non linear regression

Is there a one size fit all metric to measure accuracy / error rate for both linear or non linear regression models?

For example adjust R2 is only for multi linear regression (or so they say). RMSE seems the best choice for majority except for curve lines of best fit as it can be misleading.

How do I know which metric to use?

• R2 is for regression in general. If you train your models on the same data, it'll be good metric for comparison. Dec 3 '19 at 12:41
• As a heads up, $R^2$ lacks the “percent of variation explained” interpretation when the regression is nonlinear. You still can compare two regression models on the same response variable, but it will be equivalent to SSE.
– Dave
Jul 30 '20 at 3:19