Use of NON-PARAMETRIC Item Response Theory to develop a shortened version of the Positive and Negative Syndrome Scale (PANSS)

Table 4 Eigenvalues of PANSS subscale (without rotation)

PANSS Subscale	Component 1 Eigenvalue	Component 2 Eigenvalue	Ratio of Eigenvalues	Unidimensionality assumed
Positive Symptoms	3.172	.949	3.342	Yes
Negative Symptoms	3.867	.925	4.181	Yes
General Psychopathology	4.080	2.130	1.915	No

Note. Ratio of Eigenvalues is computed by dividing the eigenvalue for the first component by the eigenvalue for the second component for each subscale. Unidimensionality assumed is based on the eigenvalue of Component 1 being at least three times larger than the eigenvalue for Component 2.

ISSN: 1471-244X