Bootstrapping: As easy as 1-2-3
The bootstrap is a powerful non-parametric statistical technique for making probability-based inferences about a population parameter. Through a Monte-Carlo resampling simulation, bootstrapping empirically generates a statistic's entire distribution. From this simulated distribution, inferences can be made about a population parameter. Assumptions about normality are not required. In general, despite its power, bootstrapping has been used relatively infrequently in social science research, and this is particularly true for business research. This under-utilization is likely due to a combination of a general lack of understanding of the bootstrap technique and the difficulty with which it has traditionally been implemented. Researchers in the various fields of business should be familiar with this powerful statistical technique. The purpose of this paper is to explain how this technique works using Lotus 1-2-3, a software package with which business people are very familiar.
Year of publication: |
2000
|
---|---|
Authors: | Woodroof, Jon |
Published in: |
Journal of Applied Statistics. - Taylor & Francis Journals, ISSN 0266-4763. - Vol. 27.2000, 4, p. 509-517
|
Publisher: |
Taylor & Francis Journals |
Saved in:
Online Resource
Saved in favorites
Similar items by person
-
Ward, Terry J., (2009)
-
Estimated operating cash flow, reported cash flow from operating activities and financial distress
Ward, Terry J., (2006)
-
Satisfaction-dissatisfaction: are users predisposed?
Woodroof, Jon, (2003)
- More ...