Bifactor and Bifactor S-1 Model Estimations with Non-Reverse-Coded Data

Abstract

The bifactor model and methods were introduced by Holzinger and Swineford as an extension of Spearman’s two-factor theory. The bifactor model has a strict assumption, which is named orthogonality. However, the bifactor S-1 model was developed as a result of stretching the orthogonality assumption of the bifactor model. Contrary to the bifactor model, the bifactor S-1 model allows correlation between specific factors and enables items that do not form a common specific factor to be loaded only on the general factor. In psychology, data obtained from any constructs are mostly multidimensional, and these dimensions have correlations with each other. However, the Positive and Negative Affect Schedule has two orthogonal dimensions named positive affect and negative affect. In studies that modeled the Positive and Negative Affect Schedule with the bifactor model, negative items were not reverse coded, and therefore, negative path coefficients were revealed. The purpose of this study is to ascertain whether or not the items in the negative affect factor should be reverse coded in the Positive and Negative Affect Schedule. Within the scope of the current study, bifactor and bifactor S-1 model analyses were implemented for two data sets, which were reverse coded and uncodified. As a result, with reverse-coded data, the bifactor S-1 model was seen as the better model for the Positive and Negative Affect Schedule. Additionally, in the modeling of unique variances of items with specific factors, the bifactor S-1 model performed well and also resolved the negative loading problem of the items on the general factor. The point to take into consideration, which should be noted by researchers who will study with the Positive and Negative Affect Schedule, is that negative items should be reverse coded.