Study to Evaluate Results of Operational Tests and Evaluations of Complex Command and Control Systems.
Abstract
Many Army Operational test designs and evaluations presently rely on the Analysis of Variance (ANOVA) statistical technique which does not take into account the correlation or dependence between critical issue attributes or MOE. This is particularly true in the case of operational tests for command and control systems which utilize a complex large hierarchical attribute structure. Multivariate analysis of variance (MANOVA) offers a powerful statistical technique for subjectively or objectively taking into account the correlation or dependence between attributes. This technique has not been widely used because MANOVA techniques require lengthy and specialized computer programs, and there is no convenient and usable form for determining the statistical power of the test, i.e., the probability of rejecting the null hypothesis when it is false. This research overcomes these two limitations by adaptation of the BIOMEDICAL COMPUTER PROGRAMS (BMD) to the computational constraint, and by the development and validation of a new and efficient Monte Carlo procedure to determine the power of the tests.
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 1975
- Accession Number
- ADA024202
Entities
People
- Douglas C. Montgomery
- Harrison M. Wadsworth
- Leslie G. Callahan Jr.
Organizations
- Georgia Tech