Pandey, S. & Elliott, W. (2010). Suppressor variables in social work research: Ways to identify in multiple regression models. Journal of the Society for Social Work and Research 1(1), 28-40.

บทคัดย่อ

PURPOSES: To illustrate, define, classify and analyse suppressor variables in multiple regression analysis. METHODS: Documentary research was employed. RESULTS: Suppressor variables are often ignored by researchers in social sciences in multiple regression analysis. A suppressor variable is correlated with predator variable, but is not correlated with outcome variable. Suppressor variables could be classified into 4 types, i.e. classic suppression, negative suppression, reciprocal suppression, and absolute and relative suppression. Suppression analysis could be performed by means of the simple correlation analysis and regression analysis. THEORY/POLICY IMPLICATIONS: Researchers in social sciences are advised to include suppression analysis in multiple regression analysis for better understanding of the relationship among variables in multiple regression analysis.