Measures of Fit
The goal of cross-validation is to estimate the expected level of fit of a model to a data set that is independent of the data that were used to train the model. It can be used to estimate any quantitative measure of fit that is appropriate for the data and model. For example, for binary classification problems, each case in the validation set is either predicted correctly or incorrectly. In this situation the misclassification error rate can be used to summarize the fit, although other measures like positive predictive value could also be used. When the value being predicted is continuously distributed, the mean squared error, root mean squared error or median absolute deviation could be used to summarize the errors.
Read more about this topic: Cross-validation (statistics)
Famous quotes containing the words measures of, measures and/or fit:
“One encounters very capable fathers abashed by their piano-playing daughters. Three measures of Schumann make them red with embarrassment.”
—Alfred Döblin (1878–1957)
“To have the fear of God before our eyes, and, in our mutual dealings with each other, to govern our actions by the eternal measures of right and wrong:MThe first of these will comprehend the duties of religion;Mthe second, those of morality, which are so inseparably connected together, that you cannot divide these two tables ... without breaking and mutually destroying them both.”
—Laurence Sterne (1713–1768)
“Since [Rousseau’s] time, and largely thanks to him, the Ego has steadily tended to efface itself, and, for purposes of model, to become a manikin on which the toilet of education is to be draped in order to show the fit or misfit of the clothes. The object of study is the garment, not the figure.”
—Henry Brooks Adams (1838–1918)