CHAPTER 10 INFERENTIAL STATISTICS SIMPLE LINEAR REGRESSION Understanding

CHAPTER 10 INFERENTIAL STATISTICS: SIMPLE LINEAR REGRESSION Understanding Statistics for International Social Work and Other Behavioral Sciences Serge Lee, Maria C. Silveira Nunes Dinis, Lois Lowe, and Kelly Anders (2015). Oxford University Press

THE MEANING OF SIMPLE LINEAR REGRESSION 2 Regression analysis goes beyond correlation analysis. It is a belief that if two variables are related, it is possible to make causal prediction because it provides better accuracy about the generalization of the variables Statistical Requirements/Conditions: The amount of effects, specifically the slope of the regression line, matters most in linear regression • Random sampling • Normal distribution • Dependent and independent variables must be continuous and interval or ratio level

COMPUTATIONAL FORMULA 3 ÷

OTHER STATISTICAL SYMBOLS THAT COMMONLY APPEAR WITH LINEAR REGRESSION WHEN USING SPSS 4 R. R is the correlation coefficient under regression analysis �� ^2= R square is the coefficient of determination under regression Adjusted R Square = R^2 adjusted is a more conservative measure than the �� ^2 Unstandardized regression coefficient (B, or b). Two items always appear. First is the constant (a). The one below constant is the slope of the regression line. Standardized regression coefficient (Beta, �� ). Beta is also known as a partial correlation coefficient representing a linear correlation between the criterion and predictor variables while controlling for the effect of other predictor variables