Sas stat software for windows version 9

Factor analysis was used to describe the variability among the TC³ questions in order to identify the underlying structure of the factors of the TC³. Factor analyses were conducted using SAS/STAT software for Windows version 9.4 (SAS Institute, Cary, NC, USA). A polychoric correlation covariance matrix with a varimax rotation was used for the factor analysis; a technique that allows PROC FACTOR in SAS to perform factor analysis on binary and ordinal data (Andrich, 1988 ; Bartholomew, 1987 ; van Rijckevorsal & de Leeuw, 1988). The number of factors in the model was determined based on the scree test plot, which plots the factors on the x-axis versus the corresponding eigenvalues on the y-axis (Colgan, 1981 ). Additionally, at least two variables must have loading scores ≥ .50; factors must have an eigenvalue > 1.0; and each factor must account for at least 1% of the total variance. A factor loading score was calculated for each variable. The factor loading scores represent the correlations between each of the variables included in each factor. Generally, a factor loading score ≥ .30 is considered meaningful. For this analysis, a factor loading score ≥ .50 was used to identify the most highly correlated variables in each factor.