MODEL Subcommand (RELIABILITY command)

MODEL specifies the type of reliability analysis for the scale named on the SCALE subcommand.

ALPHA

Cronbach’s α. Standardized item α is displayed. This is the default.

OMEGA

Estimation of McDonald’s Omega to evaluate reliability. This model assumes that the model is uni-dimensional including a single factor with no local item dependence in the form of error covariances. The model implies that the covariance of the two different items is the product of their loadings.

SPLIT [(n)]

Split-half coefficients. You can specify a number in parentheses to indicate how many items should be in the second half. For example, MODEL SPLIT (6) uses the last six variables for the second half and all others for the first. By default, each half has an equal number of items, with the odd item, if any, going to the first half.

GUTTMAN

Guttman’s lower bounds for true reliability.

PARALLEL

Maximum-likelihood reliability estimate under parallel assumptions. This model assumes that items have the same variance but not necessarily the same mean.

STRICTPARALLEL

Maximum-likelihood reliability estimate under strictly parallel assumptions. This model assumes that items have the same means, the same true score variances over a set of objects being measured, and the same error variance over replications.