TPC Journal V7, Issue 4 - FULL ISSUE

The Professional Counselor | Volume 7, Issue 4 339 Hypotheses two through four were analyzed with SAS and AMOS to test the confirmatory model and the theoretical model, and to provide graphical representation. Missing data analysis was computed through the relationship between missing values on each variable of the 444 responses. Data were missing completely at random, and no statistically significant relationships were observed among variables. Listwise deletion within the correlation matrix reduced the sample size to 350. The present analyses followed Anderson and Gerbing’s (1988) two-step procedure. The first step used CFA to develop a measurement model meant to establish an acceptable fit to the data collected. The second step was a theoretical model that was a modification of the measurement model. This modified model is a structural equation model representing the theoretical model of interest. The theoretical model was then tested and revised until a theoretically meaningful and statistically acceptable model was achieved. The measurement model. A measurement model describes the nature of the relationship between several latent variables and the manifest indicator variables that measure those latent variables. The measurement model investigated in this study consisted of five latent variables corresponding to the five constructs of the post-trauma pathways model: War, PTSD, Optimism, Religious Commitment, and PTG ( N = 350). Each of the five latent variables was measured by at least two manifest variables (Figure 2). Figure 2. The Confirmatory Factor Analysis (CFA) Model