1. any process or operation in which a system uses its initial resources to develop more powerful and complex processing routines, which are then used in the same fashion, and so on cumulatively. In language acquisition, for example, the term describes children’s ability to learn complex linguistic rules, which can be endlessly reapplied, from extremely limited data (see Quinian bootstrapping).

2. a statistical technique to estimate the variance of a parameter when standard assumptions about the shape of the data set are not met. For example, bootstrapping may be used to estimate the variance of a set of scores that do not follow a normal distribution. In this procedure, a subset of values is taken from the data set, a quantity (e.g., the mean) is calculated, and the values are reinserted into the data; this sequence is repeated a given number of times. From the resulting set of calculated values (e.g., the set of means), the summary value of interest is calculated (e.g., the standard deviation of the mean). See also jackknife. —bootstrap vb.