Comparison of several rank tests for the two-way layout
There are several rank tests for analyzing certain experimental designs. This study compares the robustness and power of several of these, including the rank transform, aligned ranks, and joint rank sum procedures. The experimental designs studied include the two-way layout with n = 2 and n = 5 observations per cell, the two-way layout with unequal numbers of observations per cell, and the two-way layout with replication. Results are obtained by Monte Carlo simulation of normal, lognormal, and exponential random variables, using linear and nonlinear models. The results show the rank transform procedures to be superior to the other rank tests on the basis of robustness, power, and ease of application. They appear to be preferable to the usual analysis of variance procedures, except where the usual analysis of variance assumptions are met. 32 figures, 9 tables.
- Research Organization:
- Sandia Labs., Albuquerque, NM (USA)
- DOE Contract Number:
- E(29-1)-789
- OSTI ID:
- 7331687
- Report Number(s):
- SAND-76-0631; CONF-760862-2
- Resource Relation:
- Conference: Annual meeting of the American Statistical Association, Boston, MA, USA, 23 Aug 1976
- Country of Publication:
- United States
- Language:
- English
Similar Records
Electronic transport properties of single crystal thallium-2201 superconductors
Risk Importance Ranking of Fire Data Parameters to Enhance Fire PRA Model Realism