ABSTRACT
This chapter discusses some of the more specialized and lesser known aspects of the use of multiple regression analysis in reading research. Multiple regression is a least square general linear model technique appropriate for the analysis of data sets containing a single dependent (criterion) variable and multiple categorical or continuous and orthogonal or non-orthogonal independent (predictor) variables. Collinearity refers to the situation in which the independent variables in the research design are correlated with one another. Multicollinearity refers to the situation in which one independent variable in the analysis is highly predictable from a linear combination of two or more of the other independent variables in the analysis. Very high covariation among the independent variables may produce computational problems because of the necessity to invert the correlation matrix. That is, when very high covariation exists among the independent variables, the correlation matrix approaches singularity and the computer cannot perform the required matrix algebra.
