Bootstrapping is a computerized simulation operation that involves random resampling from the data set one is using to produce perhaps thousands of new data sets that have similar participant compositions to the original data set. For example, if a researcher had a data set containing 500 participants, the bootstrapping procedure would sample from the original data set to create new data sets, each of 500 participants. It is used to determine the statistical significance of parameter estimates whose significance cannot be tested using established statistical distributions (e.g., t, F, and chi-square distributions). One might use bootstrapping when data are nonnormal or the distribution of a parameter is difficult to anticipate (e.g., indirect effects in path analysis). Bootstrapping estimates the standard error (standard deviation of a ...

  • Loading...
locked icon

Sign in to access this content

Get a 30 day FREE TRIAL

  • Watch videos from a variety of sources bringing classroom topics to life
  • Read modern, diverse business cases
  • Explore hundreds of books and reference titles