path analysis

Question 1

What is the local fit in path analysis?

Answer 1

the local fit is measures like the b-weights and r-squared for the variables and sig t tests

Question 2

What is the global fit in path analysis?

Answer 2

goodness of fit and model comparison values

Question 3

What do squares represent in path analysis?

Answer 3

measured variables in the data set

Question 4

What do circles represent in path analysis?

Answer 4

latent variables that are implied by the model but not measured, the other measured variables tap into these

Question 5

What are arrows in path analysis?

Answer 5

show the relationship between variables, double headed ones indicate that variables are related and single headed indicate that one predicts another

Question 6

What is structural equation modelling and how is it diff from regression?

Answer 6

have multiple dvs in same model, variables can be both iv and dv, do not need to make assumptions about whether variables predict each other, when the program does the analysis, it will show you whether there is a r/s between variables you did not consider

Question 7

What does the chi-square goodness of fit test show?

Answer 7

whether your model is sig diff from the perfect fitting model

Question 8

What is the default model and what is the saturated model?

Answer 8

default model is our model, saturated is the perfect fitting model

Question 9

what is confirmatory factor analysis?

Answer 9

a data reduction method, form of path analysis, reduce large no. variables to a couple factors or latent variables, useful for scale dev, good for construct validity

Question 10

What situation is factor analysis designed for?

Answer 10

when a and b are related because they share a common cause. factor analysis is used to explore this, the latent variable behind them

Question 11

What is the exploratory approach in factor analysis?

Answer 11

indicate variables to include but lets spss tell you what ones are related and you can consider whether you want a shared variance (factor analysis approach) or a principal component or total variance apprroach

Question 12

What are oblique or orthogonal?

Answer 12

oblique is when factors relate to each other and are correlated and orthogonal is when they are not correlated

Question 13

Why do you constrain factors?

Answer 13

constraining one factor loading for a variable to 1 means that another variable w/ a factor of 2 is twice as strong, it helps quantify the strength of the r/s, model won’t run without it either

Question 14

What are chi squares problems as a goodness of fit measure?

Answer 14

sensitive to non-normality, favours complexity, sensitive to size of correlations, sensitive to measurement error which can reduce power, sensitive to large sample size which makes more likely to have a type 1 error of rejecting null hypothesis when it is truly null

Question 15

What are measures of absolute fit?

Answer 15

rmsea, srmr, compare to perfect fitting model, range from 0 to 1, closer to 0, the better

Question 16

What is a measure of incremental fit?

Answer 16

cfi or tli,, compares to worst fit, want it closer to 1, tli penalises complexity and is more difficult to meet

Question 17

What is the srmr?

Answer 17

standardised root mean residual, want .06 or less for a good fit or less than .08 for minimally acceptable

Question 18

What is the rmsea?

Answer 18

root mean square error, accounts for model complexity and sample size, want it to be less than .08 for good fit or .11 or less for small samples

Question 19

what is the cfi?

Answer 19

.95 or above for good incremental fit or .90 for minimally acceptable

Question 20

what is the tli?

Answer 20

penalises complexity, measure of incremental fit, compares against worst fit, , want .95 or above or .90 or above for min acceept

Question 21

What is CMIN?

Answer 21

output name for the chi-square

Question 22

What is the covariance and how does it differ from correlation?

Answer 22

covariance is unstandardised, correlation is standardised b-weight vs. beta

Question 23

What is a just-identified, over-indentified, and under-identified model?

Answer 23

just-identified is when all degrees of freedom are used, over-identified is when there’s df remaining, under-identfied is when there is insufficient df to test everything

Question 24

How many variables per factor do you generally want?

Answer 24

3

Question 25

An MI of what will sig improve the model?

Answer 25

3.84 or above, use biggest MIs first

Question 26

What is a nested model?

Answer 26

when one model has all the paths of another plus one or more additional paths

Question 27

What is a non-nested model?

Answer 27

diff variables across models and the more complex model does not contain all paths from the other, can compare using BIC