Brainscape's Knowledge GenomeTM

Browse over 1 million classes created by top students, professors, publishers, and experts.


See full index

ADDA > Lecture 6 > Flashcards

Lecture 6 Flashcards

1
Q

What does path analysis look at?

A
  • regular regression model

- observed variables only (no latent/unobserved variables)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

When is correlation consistent with prediction? (According to Wright, 1921)

A
  • temporal ordering of variables (cause before effect)
  • covariation/correlation among variables
  • other causes controlled for
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What is a recursive model?

A
  • unidirectional paths
  • independent error/residuals
  • can be tested with standard multiple regression
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

What are non-recursive models?

A
  • bidirectional paths
  • correlated error terms
  • feedback loops
  • need SEM programs (AMOS)
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

Why might you get different numbers in AMOS compared to normal regression? What numbers will differ?

A

if you don’t correlate the IVs/predictors

  • regression weights will be the same
  • SEs, standardised weights and squared multiple correlation (R2) will differ
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
6
Q

Why is path analysis better than regression?

A
  • gives more information (tells you which correlations b/w variables are significant, can remove to make more parsimonious)
  • much more accurate
  • really advantageous when there are latent variables predicting a further latent variable
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
7
Q

What is a multi-step path analysis?

A

A > M > B

  • A = predictor
  • M = both predictor and predicted (intervening variable)
  • B = predicted
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
8
Q

What 2 ways can you do a multi-step analysis?

A
  • you can do 2 regressions

- you can use AMOS (remember to correlate predictors)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
9
Q

What do you need to do to get accurate measures if you choose to do 2 regressions?

A
  • R2 = combine R2 values together
  • direct effects are normal
  • indirect effects: need to multiply the two beta values together
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
10
Q

Why do you need additional fit indices to X2?

A
  • it is sensitive
  • large sample: trivial diffs may be sig.
  • small sample: may not be exactly X2 distributed > inaccurate probability levels
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
11
Q

What are the comparative fit indices?

A
  • NFI
  • CFI
  • RMSEA
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
12
Q

What are the proportion of variance explained fit measures?

A
  • GFI

- AGFI

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
13
Q

What are the degree of parsimony fit indices?

A
  • PGFI
  • AIC
  • CAIC
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
14
Q

What are the residual based fit indices?

A
  • RMR

- SRMR

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
15
Q

Which fit indices do you usually report?

A
  • if they agree, it is usually up to personal choice. Often report multiple.

COMMONLY:
CFI, RMSEA
maybe SRMR
AIC and CAIC for comparing models

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
16
Q

What do you look at in the modification indices?

A

the MI values (expected decrease in X2)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
17
Q

What does it mean if AMOS says that some variances are negative?

A

it is an error message

NOT a good model

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
18
Q

What do multivariate normality values means?

A
  • less than 1 = negligible
  • 1-10 = moderate non-normality
  • 10+ = severe non-normality
How well did you know this?
1
Not at all
2
3
4
5
Perfectly
19
Q

What is mahalanobis distance?

A

measure of how close specific cases are to the centroid (the multivariate version of the mean)

20
Q

When do you use bootstrapping? Why?

A
  • when assumptions are not met
  • when distribution is not normal
  • bc: model can be incorrectly rejected as not fitting
  • SEs can be smaller than they really are (this can make parameters seem sig. when they are not)
21
Q

What is bootstrapping? What is diff about Bollen Stine compared to Naive?

A
  • repeated samples of the data
  • allow each observation to be taken more than once in any sample
  • sampling with replacement
  • calculate statistic (eg. mean) for each bootstrapped sample and make sampling distro/bootstrap distro.
  • calc. SD for sampling distribution - this is the SE!!

Bollen-Stine: calculate ML for each BS sample to make bootstrap/sampling distro. Find 5% mark on distro.

22
Q

When do you use Bollen-Stine bootstrapping? When would you use Naive bootstrapping?

A
  • BS so assess overall fit

- Naive to get standard error

23
Q

How is Bollen-Stine different to regular bootstrapping

A
  • it transforms the parent sample into a sample with perfect fit
  • the variance-covaraince matrix fits prefectly with the model BUT still has same distributional aspects of original parent sample
  • thus would expect the bootstrapped sample to fit very well
  • want parent to have better fit than 5% of the bootstrapped ones > suggests good fit
24
Q

How do you interpret bootstrap iterations?

A
  • BOLLEN: method 1, see if the parent fit better >5% of times

NAIVE:

  • first SE = bootstrapped SE
  • SE - SE = diff b/w bootstrap and usual
  • “mean” = regression weight
  • bootstrap CI: not include 0 = sig. parameter!
25
Q

What is the factor vs. the regression model? How can you combine the 2 models?

A
  • factor: observed variable predicted by unobserved factors (coefficient is lambda, x is predictor)
  • regression: dependent predicted by independent (coefficient is beta, x is predicted)
    NOTE: x = observed variable, this makes sense!

COMBINE: sub X from factor model into regression model, run regression using latent variables as predictors

26
Q

What is an advantage of latent variable modeling?

A

model characteristics rather than just scores

27
Q

When can you get a reliability of 1? What does that mean?

A
  • never

- observed score never fully captures info in latent variable

28
Q

What type of model is path analysis?

A

Structural

29
Q

What did Sewell say was the 4th criteria that is not right?

A

variables must be measures on at least and interval scale

30
Q

In what specific way is path analysis more accurate than regression?

A

regression models correlations among IVs but does not show or tell you this

31
Q

How do you combine the r2 values? What is this called?

A

1 - (1 - .R2) x (1 - .R2)

- generalised squared multiple correlation

32
Q

What are Mahalanobis d2, p1 and p2 in Mahalanobis distance?

A
  • M D2: distance being referred to in the following 2 columns
  • p1: prob that any observation could be so far out (want small).
  • assuming normality, the probability that ANY case will exceed the D2 value
  • p2: prob that this particular case should be so far out (want large, small p2 indicates many outliers)
  • assuming normality, the probability that the highest D2 value will exceed that value (second row = prob of 2nd highest D2 value)
33
Q

What is the test theory and how does this relate to the latent and regression equations? How do you calculate reliability from this?

A

O = T + E (observed = true + error)

  • O = x in both latent and regression models (observed variable)
  • T = f in factor model (latent variable, acting as predictor)

reliability: var(true) / var(observed)

34
Q

How are regression and correlation similar and different?

A
  • they are the same thing, just scaled differently

- correlation is symmetric, but regression is kind of one way

35
Q

What is the equation for bivariate regression?

A

y = (beta)x + e

36
Q

When interpreting regression, what is the difference between writing out an equation for y(predicted) vs. y?

A
  • predicted/yhat has no residual term
37
Q

Why is it better to use observed to predict latent variables (using CFA) rather than use sums?

A
  • usually get higher R2 values and higher coefficients

- in sums: assume that all variables have equal weighting

38
Q

How do you word regressions?

A
  • regress Y on X1, X2 and X3
39
Q

What types of models can you compare with AIC and CAIC?

A
  • NON-nested models
40
Q

What are nested models? What can you compare when using nested models?

A
  • nested = one is a subset of the other
  • simpler nested inside more complex
  • can compare the X2 value, and how much it has decreased
41
Q

How could you calculate the p value for Bollen-Stine bootstrapping?

A
  • no. of times THE BOOTSTRAP fit worse/no. of times it fit better (x100)
  • i.e. no. of times parent fit better/parent fit worse
  • want >.05 (more than 5%)
42
Q

What are the key differences between the factor and regression equations?

A
  • factor: xp = (lambda)p1f1 … until (lamb)pk(f)k + up
  • regression: Yp = BpX1 …. + ep
  • error: factor = u, regression = e
  • coefficient: factor = lambda, regression = beta
  • predicted: factor = X, regression = Y
  • predictors: factor = f, regression = x

NOTE: X always = observed variable

43
Q

What types of models are the regression (1) and factor (2) models? And what is the other name for the combination (1 + 2)?

A
  • regression: structural model (path analysis)
  • factor: measurement model
  • both: SEM
44
Q

How do you interpret the Multiple R2 in Path Analysis? and the GSMC?

A
  • R2: proportion of variance in the endogenous variable that is explained by direct effects
  • GSMC: overall contribution of direct and indirect effects
45
Q

What is SEM also known as?

A
  • causal modelling
  • causal analysis
  • simultaneous equation modelling
  • analysis of covariance structures

ADDA (15 decks)

Brainscape helps you reach your goals faster, through stronger study habits.
© 2024 Bold Learning Solutions. Terms and Conditions