Synonym: Root Mean Square Deviation (RMSD) = Root Mean Square Error (RMSE)
Statistical metric characterizing the model prediction quality ( goodness of fit ) between the datasets of a given variable and its estimator
:
RMSD(x, \hat x) = \sqrt{MSD(x, \hat x)} = \sqrt{ \frac{1}{n} \sum_{i=1}^n (x_i - \hat x_i)^2 } |
where
| a variable represented by data set | |
estimator of variable | |
discrete set of numerical samples of variable | |
discrete set of predictors for the corresponding samples of variable | |
| Mean Square Deviation (MSD) |
The RMSD is a square root of Mean Square Deviation (MSD) between the datasets of a given variable and its estimator
.
The key benefit of using RMSD instead of MSD is that it is expressed in the same units as the base property () while MSD is expressed in square units of the base property.
The terms RMSD and RMSE are used in mathematics and engineering interchangeably.
See also
Human / Science / Formal Science / System / Model / Model Validation / Goodness of fit
[ Mathematics / Statistics / Statistical Metric ]
[ Natural Science ]