WK 7

Question 1

What does a path model allow us to do?

Answer 1

A path model allows us to test several linear models together as a set

Question 2

What are exogenous variables?

Answer 2

They are essentially independent variables

Question 3

What are endogenous variables?

Answer 3

They are dependent variables in at least one part of the model

Question 4

What directions do the arrows go in exogenous variables?

Answer 4

Only have directed arrows going out (basically predictors)

Question 5

What directions do the arrows go in endogenous variables?

Answer 5

They have directed arrows going in

Question 6

In a diagram, what does a square represent?

Answer 6

It represents an observed/measured variable

Question 7

In a diagram, what does a circle represent?

Answer 7

It represents an unobserved/latent variable

Question 8

In a diagram, what does a two-headed arrow represent?

Answer 8

It represents covariance

Question 9

In a diagram, what does a single headed arrow represent?

Answer 9

It represents a regression path

Question 10

In a diagram, when there is a single arrow, what is it showing?

Answer 10

The square that the arrow is pointing in to is the dependent variable/outcome, whereas the other side is the predictor

Question 11

What does every endogenous variable have?

Answer 11

They have a residual

Question 12

What do you need after you run a lavaan model?

Answer 12

you need to use a summary function

Question 13

What is specification in path models?

Answer 13

It concerns which variables relate to which others, and in what ways

Question 14

What are the standard rules in path models?

Answer 14

1. all exogenous variables correlate
2. for endogenous variables, we correlate the residuals, not the variables
3. endogenous variable residuals do not correlate with exogenous variables
4. all paths are recursive (i.e. we cannot have loops like A-> B, B-> A)

Question 15

What is model identification?

Answer 15

Identification concerns the number of knowns versus unknowns

Question 16

In order to test our model, what do we need?

Answer 16

We need more knowns than unknowns in order to test our model

Question 17

What are the knowns?

Answer 17

The knowns are variances and covariances

Question 18

What are path models based on?

Answer 18

path models are based on the correlation matrix between variables that you have measured

Question 19

What are the unknowns?

Answer 19

The unknowns are the parameters we want to estimate

Question 20

What are the degrees of freedom in model identification?

Answer 20

Degrees of freedom are the difference between knowns and unknowns

Question 21

What are the three levels of identification?

Answer 21

Under-identified, just identified, over-identified models

Question 22

What are the degrees of freedom for under-identified models?

Answer 22

They have <0 degrees of freedom

Question 23

What model won’t estimate?

Answer 23

Under-identified models

Question 24

What are the degrees of freedom for just identified models?

Answer 24

They have 0 degrees of freedom

Question 25

What is an example of just identified models?

Answer 25

standard linear models

Question 26

What are the degrees of freedom for over-identified models?

Answer 26

they have > 0 degrees of freedom

Question 27

What is model estimation?

Answer 27

It refers to finding the 'best' values for the unknown parameters

Question 28

What are the assumption of maximum likelihood estimation?

Answer 28

- large sample size - multivariate normality - variables are on a continuous scale

Question 29

Why does no convergence happen?

Answer 29

- the model is not identified -the model is mis-specified -the model is very complex, so more iterations are needed than the program default

Question 30

What does a statistically significant chi-squared suggest?

Answer 30

It suggests the model does not do a good job of reproducing the observed variance-covariance matrix

Question 31

What is the range of absolute fit?

Answer 31

ranges from 0 to 1

Question 32

What is deemed as perfect fit in absolute fit?

Answer 32

0=perfect fit

Question 33

What is considered good in the range for absolute fit?

Answer 33

values <.05 considered good

Question 34

What is a perfect parsimony-corrected indices?

Answer 34

0 = perfect fit

Question 35

What is considered good in the range for parsimony-corrected indices?

Answer 35

values <.05 considered good

Question 36

What does absolute fit measure?

Answer 36

It measures the discrepancy between the observed correlation matrix and model-implied correlation matrix

Question 37

What does parsimony-corrected indices do?

Answer 37

Adds a penalty for having more degrees of freedom

Question 38

What does incremental fit indices do?

Answer 38

It compares the model to a more restricted baseline model

Question 39

What is the range of a comparative fit infex (CFI)?

Answer 39

Ranges between 0 and 1

Question 40

What value is the perfect fit, and what values are considered good in comparative fit indices?

Answer 40

1= perfect fit values > 0.95 considered good

Question 41

What does the Tucker-Lewis index (TLI) include?

Answer 41

Includes a parsimony penalty

Question 42

What values are considered good in tucker-lewis index?

Answer 42

Values >0.95 are considered good

Question 43

What is modification indices?

Answer 43

Modification indices provides the improvement in fit

Question 44

What do expected parameter changes estimate?

Answer 44

Estimate the value of the parameter were it to be included

Question 45

How do you extract modification indices and expected parameter chnges?

Answer 45

using summary(model, mod.indices=T)

Question 46

When is chi-squared statistic significant?

Answer 46

values < 0.05

Question 47

What is absolute fit?

Answer 47

standardised root mean square residual (SRMR)

Question 48

What is parsimony-corrected?

Answer 48

root mean square error of approximation (RMSEA)