Lecture 10 Flashcards
Linear regression is the next step after finding a sig correlation (pearsons r). What does this tell you ?
How much effect variable X has on variable Y
X is which variable?
Independent variable (predictor variable)
Y is what type of variable
Dependent variable (criterion variable)
In regression analysis the X (independent variable) is called
Predictor
Dependent variable is called
Criterion
4 types of regression analysis
Simple linear (most common)
Multiple linear
Logistic
Multinominal logistic
Simple linear is called simple because
It only has one independent variable (predictor ) and 1 dependent (criterion)
In simple linear regression both variables need to be
Numeric - using at least interval scale
Simple linear regression allows us to predict the value
That can be assumed by criterion (DV) (Y) if the value of predictor (IV) is known
‘Simple’ means
Enter 1 predictor variable at a time to the relationship
‘Linear’ implies
There is a constant increasing/decreasing relationship between variables. (Monotonic relationship)
What method does SPSS use to calculate simple linear regression?
Ordinary least squares regression OLS
In a graph the X (IV) is always on the
Horizontal axis
Line if best fit should minimise the dif between the
Actual value of the DV and the value of the DV predicted by the IV
Residual is what we call the difference between
The distance between a persons actual score is different (higher or lower that what was predicted for what score they should have gotten (as found on the line of best fit)