Accession Number : AD0750725

Title :   A Method for Separation of Residual and Inetraction Effects in Cross Classifications.

Descriptive Note : Technical rept.,

Corporate Author : NORTH CAROLINA UNIV CHAPEL HILL DEPT OF STATISTICS

Personal Author(s) : Johnson,N. L.

Report Date : SEP 1972

Pagination or Media Count : 12

Abstract : Consider a two-way cross-classification with factors R ('rows') and C ('columns') at r, c levels respectively and suppose that the expected value of an observation at the i-th level of R and the j-th level of C is represented in the form epsilon + (roh sub i) + (kappa sub j) + (rho kappa) sub ij. The last term represents the interaction effect between R and C, usually denoted in the abbreviated form RxC. Variability about this expected value is represented by addition of a random variable with zero expected value. It is usually assumed that these random variables are mutually independent and have a common variance. If there is only one observation for each of the rc combinations of levels of R and C it is not possible to estimate the common variance separately from the interaction effects. (author)

Descriptors :   (*STATISTICAL ANALYSIS, CLASSIFICATION), ANALYSIS OF VARIANCE, REGRESSION ANALYSIS, RANDOM VARIABLES, DISTRIBUTION FUNCTIONS, STATISTICAL TESTS

Subject Categories : Statistics and Probability

Distribution Statement : APPROVED FOR PUBLIC RELEASE