Multiple Regression Flashcards
What is the symbol that represents correlation coefficient?
correlation coefficient is represented by a r letter.
Definition of Regression.
Regression allows u to predict the value of one variable if we know the value of another variable using the straight line formula?
How does regression work?
Regression allows u to predict the value of one variable if you know the value of the other variable using the straight line formula.
Straight line formula is y= bx + c y = dependent variable b = slope angle x = independent variable c = constant/intercept where line crosses the y axis.
regression uses x value to find out y value using the straight line formula.
what is y in straight line formula?
in straight line formula y is dependent variable.
What is x in straight line formula?
in straight line formula x is independent variable.
Definition of intercept.
Intercept/constant is where the regression line meets the y axis.
It is the value of y when x is zero.
Definition of bivariate regression.
Bivariate regression is a straight line regression involving one dependent variable and one independent variable.
Definition of multiple regression.
Multiple regression = involves one dependent variable and multiple independent variables.
Definition of R squared (R2)
R Squared measures the amount of variation explained. R2 is reported as a percentage. Another word for R squared is coefficient of determination.
How do you report r squared?
R squared is reported as a percentage.
What is r and r squared?
r is peason’s r it is correlation coefficient. But r squared is the amount of variation explained. R squared is reported as a percentage. r squared is also called coefficient of determination/
Coefficient of determination
Coefficient of determination is another word for R squared. It is the amount of variation explained.
What is the range for R squared?
R squared ranges from 0 to +1. R squared is reported as a percentage.
What are the methods of entering independent variables (predictors) in regression?
the methods of entering predictors are:
- direct (enter) method.
- stepwise method
- hierarchical method
What is B in regression?
B is the slope angle. B is the unstandardised coefficient.
What is C in regression?
C is constant/intercept it is where the line crosses the y axis. C is the value of y when x is zero.
What is beta in regression?
Beta is the correlation coefficient
Definition of adjusted R squared.
Adjusted r squared is the percentage of variation accounted for.
What is adjusted r squared reported as?
Adjusted R sqaured is the amount of variation explained and it is reported as a percentage.
What is rule of thumb for adjusted r squared?
Weak model = less than 20%.
Moderate model = 20-49%
Strong model = 50% and more.
What is a weak model for adjusted r squared?
weak model for adjusted r squared is less than 20%.
What is a moderate model for adjusted r squared?
Moderate model for adjusted r squared is 20-49%.
What is a strong model for adjusted r squared?
Strong model for adjusted r squared is 50% or more.
