Exploratory factor analysis

Question 1

What are principal components?

Answer 1

estimates components that account for 100% of total variance in variables

Question 2

What are factor techniques?

Answer 2

estimates components that account for 100% of shared variance between variables

Question 3

What is the least squares method?

Answer 3

minimises diff between data and factor analysis

Question 4

Whar is the max likelihood test?

Answer 4

finds most probably factor analysis

Question 5

What is dimensionality?

Answer 5

no. of variables or k

Question 6

What are factors?

Answer 6

the r/s between 2 or more variables

Question 7

What is an eigenvector?

Answer 7

the direction of the factor

Question 8

What is an eigenvalue?

Answer 8

the amount of variance in the eigenvector

Question 9

What are the requirements for factor analysis?

Answer 9

min 300 sample, 50 is poor, 1000 is excellent

Question 10

What is monte carlo testing?

Answer 10

generating own distribution for factors

Question 11

What is pairwise deletion of data?

Answer 11

deleting data that is missing

Question 12

what is listwise deletion of missing data?

Answer 12

deleting a whole case if there’s missing data

Question 13

What is multiple imputation?

Answer 13

creating sev data sets and replacing missing data with imputed values, all slightly diff in each data set due to random component, analyse them all and combine results, then calculating variation in estimates to report on it

Question 14

Expectation maximisation?

Answer 14

finding max likelihood estimates for model parameters when data is incomplete

Question 15

What is regression replacement?

Answer 15

putting known ave. for variable in place, however this reduces variance in data

Question 16

What is multivariate normality?

Answer 16

normality across all r/s in data set

Question 17

What is communality?

Answer 17

how much variance is explaned by variables

Question 18

What is in the factor matrix?

Answer 18

b-weights for 1 unit changes in ivs

Question 19

What sampling techniques to use to check if sample is adequate?

Answer 19

kaiser-meyer, has to be greater than .5, and bartlett’s less than .1

Question 20

When to stop extracting?

Answer 20

when you get to k, eigenvalue>1, when the slope changes dramatically

Question 21

Residual correlation matrix

Answer 21

1-.20 not acceptable, .02-.05 evidence of unexplained factor, .05-0 no evidence

Question 22

What is quartimax rotation?

Answer 22

reduce no.of variables to explain each variable, simplifies

Question 23

what is a varimax rotation?

Answer 23

reduces no. of variables w high loadings, simplifies interpretation

Question 24

what is equamax rotation?

Answer 24

minimises no. variables that load highly and no. factors needed to explain

Question 25

What do rotations achieve?

Answer 25

a change of balance of the variance explained by variables but without changing the total variance