Cross-validation (statistics) - Measures of Fit

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:

    There are other measures of self-respect for a man, than the number of clean shirts he puts on every day.
    Ralph Waldo Emerson (1803–1882)

    the dread

    That how we live measures our own nature,
    And at his age having no more to show
    Than one hired box should make him pretty sure
    He warranted no better,
    Philip Larkin (1922–1985)

    Germany is a queer country: one can’t regard it dispassionately. I alternate between hating it thoroughly, stick, stock and stone, and yearning over it fit to break my heart. I can’t help feeling it a young and adorable country—adolescent—with the faults of adolescence.
    —D.H. (David Herbert)