In forecasting, the process of testing how accurate a model is for making forecasts. The sample data are often split into two segments, one used to estimate the parameters of the model, and the other, the <a href="search.pl?p=holdout data,">holdout data,</a> used to test the forecasts made with the model. The many variations of validation include <a href="search.pl?p=cross-validation">cross-validation</a>, n-way
 validation, and the <a href="search.pl?p=jackknife">jackknife</a>. Validation can also be used to assess the usefulness of the <a href="search.pl?p=parameters">parameters</a> of a <a href="search.pl?p=forecasting model">forecasting model</a>. <A HREF="../dictionary/references.html#Armstrong">Armstrong</a> (2001d) describes various approaches to validation.<o:p></o:p></P>
 <ul>
   <li>Armstrong, J. S. (2001d), “Evaluating forecasting 
methods,” in J. S. Armstrong (ed.), <I>Principles of Forecasting.</I> Norwell, 
MA: Kluwer Academic Press.</li>
 </ul>