Chapter 14 Flashcards
Big R squared
Multiple Correlation
2 main applications of multivariate techniques
partial correlation
multiple regression
partial correlation
examine how a bivariate relationship changes when a control variable(s) is introduced (meaning a third or more)
Multiple Regression
Asses the effects of two or more independent variables on the dependent variable
Zero Order Correlation
how coefficients are correlated through calculations of bivariate relationships
If the partial correlation is different from the zero-order correlation, then
the third variable has to affect the bivariate relationship
Direct relationship
X —> Y
Intervening relationship
X –> Z –> Y
Spurious Relationship
Y
Z
X
Z can lead to either X or Y
What is the correlation Matrix often used for
to build a bivariate table for correlation coefficients between all possible pairs of variables
Correlation Matrix
-Overview of interrelationships in the data and may suggest how to dive deeper
-Detect high correlation between two or more independent variables
2 things multiple regression and correlation allows us to do
(regression) disentangle the separate effects of each independent variable
(correlation) asses the combined effects of the independent variables on Y
What types of variables does the least-squares regression equation involve
at least 2 independent variables
How many times does partial slope need to be calulated
How many variables there are
3 variables = 3 calculations
What do beta-weights show
the amount of change in the standardized scores of Y for a one-unit change in the scores of each independent variable
What does the coefficient of multiple determination show
the combined effect of all independent variables on the dependent variable
Partial Slope
amount of change in the dependent variable Y associated with a unit of change in the independent variable X while controlling for the effects of the other independent variables
Standardized partial slope
Amount of change int he standardized scores of Y for a one-unit change in the standardized scores of each independent variable while controlling the effects of all other independent variables
Coefficient of multiple determination
proportion of the variance in Y that is explained by all the independent variables combined