Create a Random Sample

Ribbon bar. Select the Data tab. In the Manage group, click Sampling to display the Create a Random Sample dialog box.

Classic menus. On the Data menu, select Random Sampling to display the Create a Random Sample dialog box.

This dialog box contains three tabs: Simple Sampling, Stratified Sampling, and Options. Use these options to perform simple random and stratified random sampling from the current data file (see also EPSEM samples, Quota Sampling, and Representative Sample).

For simple random (probability sampling) and stratified random sampling, select the applicable options on the Simple Sampling or Stratified Sampling tab. In simple random sampling, each observation in the population (the current active data set) will have the same (user-defined) probability of being selected into the sample; in stratified sampling, observations in different groups may have different probabilities of being selected into the sample. Stratified random sampling is often useful in predictive data mining in order to over-represent rare events (e.g., to extract a sample for the analyses where 50% of the observations previously ordered from a catalog, and 50% did not, when in the population from which the sample was drawn only 1% of the observations ordered from the catalog).

Variables. Click the Variables button to display the Select Variables dialog box, which is used to choose the variables from the current spreadsheet to be included in the random sample.

Cases. Click the Cases button to display the Spreadsheet Case Selection Conditions dialog box, which is used to create conditions to define the selection of cases to be considered for the sample; final sampling (for simple random or stratified random samples, and for random splitting of the data file) will only be applied to those cases selected by the case selection conditions. For more information about case selection conditions, see Case Selection Conditions Overview, Case Selection Conditions Syntax Summary and Case Selection Conditions Examples.

OK. Click this button, to execute the random sample. The active tab will be the type of random sample executed.

Cancel. Click this button to close the Create a Random Sample dialog box. Any changes made will be disregarded.