Factor Analysis Flashcards
What is the function of factor loading?
tells us the relative contribution that a variable makes to a factor
What is the function of a factor rotation?
optimises the how the items load onto a factor and improves the interpretability
What is multicollinearity?
variables are very highly correlated
What is singularity?
variables are perfectly correlated
How do we know if there is an issue with multicollinearity/singularity?
the determinant will be less than 0.00001
What is the Kaiser-Meyer-Olkin test?
it is a measure of sampling adequacy a value of 0 means the data is not suitable for factor analysis between .70 and .80 is good .80 - .90 is great >.90 is superb
What is Bartlett’s test of sphericity?
tests the null hypothesis that the original correlation matrix is an identity matrix (all correlations would be 0) - you want a significant result, report as Chi Square
What is an Eigenvalue?
it represent the amount of variance in responses explained by each factor
What factors dictate whether Kaiser’s criterion is accurate?
there are less than 30 variables AND commonalities after extraction are greater than .70
OR
the sample size exceeds 250 and the average communality is greater than .60
What does Kaiser’s criterion tell you?
how many factors with Eigenvalues greater than 1 are produced by the factor analysis
How do we check Kaiser’s criterion is accurate?
look at where the scree plot tails off and take one point to the left of that value
What is a communality?
the percent of variance in a given variable explained by all factors jointly
What are the types of rotation and when would you use them?
orthogonal; factors are uncorrelated
oblique; factors inter-correlate
What are examples of an orthogonal rotation?
independent and varimax
What are examples of an oblique rotation?
dependent and direct oblimin
