0

i conduct SEM with lavaan and semplot libraries, and i use example for package lavaan (stability of alienation by Wheaton)

lower <-
  '
11.834,
6.947,    9.364,
6.819,    5.091,   12.532,
4.783,    5.028,    7.495,    9.986,
-3.839,   -3.889,   -3.841,   -3.625,   9.610,
-21.899,  -18.831,  -21.748,  -18.775,  35.522,  450.288
'
# convert to a full symmetric covariance matrix with names
wheaton.cov <- getCov(lower, names=c("anomia67","powerless67", "anomia71",
                                     "powerless71","education","sei"))
# the model
wheaton.model <-
  '
# measurement model
ses     =~ education + sei
alien67 =~ anomia67 + powerless67
alien71 =~ anomia71 + powerless71
# equations
alien71 ~ alien67 + ses
alien67 ~ ses
# correlated residuals
anomia67 ~~ anomia71
powerless67 ~~ powerless71'

fit <- sem(wheaton.model, sample.cov=wheaton.cov, sample.nobs=932)

semPaths(fit,whatLables="par",layout = "spring")

and i can't understand what do represent accuratearrows on manifest and latent variables.

Screen Arrows

MYaseen208
  • 22,666
  • 37
  • 165
  • 309
d-fan
  • 21
  • 3

1 Answers1

0

Those arrows represent residual variances of your latent and observed variables. Usually referred to as ψi,i. I wanted to give you a decent source, but could only find a presentation that directly shows it both graphically and in text.

kneijenhuijs
  • 1,189
  • 1
  • 12
  • 21
  • thank you, but last question, What do mean, if arcuate arrows (i.e residual variances ) are decorated with dotted line – d-fan Nov 05 '15 at 08:57
  • Dotted lines represent estimates that are constrained to a certain value (usually zero or one). So when the residual variance arrow is dotted it is constrained to a certain value in your model. Constraints are usually necessary to make the model identifiable or to give a latent factor a certain scale. However, this is usually accomplished through constraining parameters between variables (you can see this happening in your figure between an71 and al71). I'm a little unsure to the reason why residual variances would be constrained. Perhaps someone can shed some light on that. – kneijenhuijs Nov 05 '15 at 09:06