Table 4. Correlation and regression analysis between indices
An examination of Table 4 shows a positive correlation between anxiety and insomnia (p<0.05, Cohen’s r:0.12), a moderate negative correlation between anxiety and organizational support (p<0.05, Cohen’s r:0.89), and a moderate negative correlation between anxiety and coworker support (p<0.05, Cohen’s r:0.89).
Anxiety was analyzed to be a dependent variable in the linear regression model (enter model) and the variables ISI, OSI and CSI as continuous measurement variables, gender, having children, marital status, smoking and alcohol consumption as dummy variables, and as a result the variables ISI, OSI, gender (reference group: female), and having children (reference group: I have children) were found to be significant for the linear regression model (p<0.05 and F4.307:106.347). Distribution of the dummy variables conformed to normal distribution, with VIF<10, tolerance<2 and Durbin-Watson<2.5. 58.1% of variability which may occur in anxiety can be explained by insomnia, organizational support, gender, and having children (R2=0.581). One unit of variation in insomnia will raise anxiety by 0.761 units, being female 1.521 units, and having children 1.196 units, while a one-unit increase in perceived organizational support will lower anxiety by 0.098 units. The variable of coworker support was not significant for the linear regression equation (p>0.05) (Table 4).