Linear Regression Flashcards
What is the main purpose of linear regression?
Causal associations.
Focuses on a mean group comparison.
What are the requirements for linear regression?
Outcome variable must be continuous.
Predictor variable can be anything.
Outcome should be approximately normally distributed.
Should be testing the linear relationship between two variables.
What does the ordinary least squares regression minimise?
The sum of the squared residuals.
What is Bo in the equation?
The y-intercept.
What is Ei in the equation?
The residual error (individual deviation).
What is B1 in the equation?
The gradient.
What method should you use when conducting a LR in SPSS?
Forced-entry/enter.
Which assumptions must you check?
Normally distributed errors.
Homoscedasticity.
Linearity.
Influential cases.
What is R-squared?
It is the amount of variance of the outcome variable which can be explained by the predictor.
What is the F-value?
There ratio of the model MS divided by the residual MS.
What is the cut-off point for the F-value?
Has to be larger than 1.
How do you check for normal distributed errors?
Histogram + P-P plot.
How do you check for homoscedasticity?
zResidual vs zPredicted plot.
Variance around the regression line should be the same for all values of the predictor variable.
How do you check for linearity?
zResidual vs zPredicted plot.
Must add Loess line!
Line should be approximate to zero and linear.
How do you check for influential cases?
Cook’s distance.