|
| << previous | next >> |
Journal description
All volumes of the corresponding journal
All issues of the corresponding volume
All articles of the corresponding issues
Details for article 11 of 18 found articles
| Title: |
Interval estimates for the optimum point of a quadratic logistic curve —a comparison of different estimation methods via simulation |
| Author: |
Scazzero, Joseph A. Ord, J. K. |
| Appeared in: |
Communications in statistics |
| Paging: | Volume 24 (1995) nr. 1 pages 207-226 |
| Year: |
1995 |
| Contents: |
Suppose that the quadratic logistic model describes the relationship between a proportion p and some independent variable x. When constructing interval estimates for the value of x at which p attains an optimum value, the following asymptotic methods are available: 1) Fieller; 2) delta; 3) bootstrap variance; 4) bootstrap percentile; 5) bootstrap studentized percentile; and 6) jackknife. It is not known, however, how these asymptotic methods compare for finite sample sizes. For balanced D-optimum designs with equally spaced design points, simulation results were used to compare the small and moderate sample-size performance of these asymptotic methods. Overall, in terms of coverage probabilities and interval length characteristics, the delta method and bootstrap studentized percentile method gave the best results for small and moderate sample sizes, respectively. |
| Publisher: |
Taylor & Francis |
| Source file: |
Elektronische Wetenschappelijke Tijdschriften |
Details for article 11 of 18 found articles
| << previous | next >> |