Use this to select the output to be generated by bootstrap resampling of the given statistics, and options to be used in the resampling.

## Display

Specifies which items of output are to be displayed in the Output window or the Graphics window.

Estimates and confidence limits |
Estimates (means) and lower and upper confidence limits of each statistic. |

Histograms of statistics |
A histogram of the bootstrap distribution of each statistic with the estimate and lower and upper confidence limits marked on the graph. |

## Seed for randomization

This gives a seed to initialize the random number generation used for resampling the data. Using zero initialises this from the computer’s clock, but specifying a nonzero value gives a repeatable analysis.

## Type of bootstrapping to use

Random |
All samples will be drawn independently. |

Balance |
The resampling is constrained to ensure that each unit of the data matrix occurs the same number of times in the complete set of generated samples. |

## Type of Confidence Limit

This controls the method used to calculate the confidence intervals.

Percentile |
The limits are constructed as percentiles of the empirical distribution of the bootstrap estimates. |

Bias-corrected and accelerated |
The bias-corrected and accelerated limits of Efron & Tibshirani, 1993, Section 14.3 are used (see the BOOTSTRAP procedure help page for more details). |

The **Probability level of confidence limits** lets you control the limit for the calculation of a confidence interval. The limit is expressed as a proportion and must be in the range 0-1.

## Type of test

Lets you choose either a one- or two-sided t-test. A two-sided test tests for differences either side of 0, whereas a one-sided test tests whether the mean is greater than or less than the given mean.

## See also

- Bootstrap Resampling menu
- Bootstrap store options for choosing what results to save
- BOOTSTRAP procedure in command mode