Blog Archives

Why cost and fuel efficiency are unrelated: Uncorrelated manifest variables can share the same latent causes

February 7, 2013
By
Why cost and fuel efficiency are unrelated: Uncorrelated manifest variables can share the same latent causes

In structural equation modelling, we are typically proposing theoretical causes of observed phenomena. These are termed "latent" (the unobserved causes) and manifest (the observed variables we measure, otherwise known as data).Importantly, the theoretical causes of behavior need not have a structure remotely resembling the correlations observed in the data. You might have hundreds of columns of...

Read more »

What’s that “pre- and post-multiply” stuff?

January 5, 2013
By

Often in SEM scripts you will see matrices being pre- and post-multiplied by some other matrix. For instance, this figures in scripts computing the genetic correlation between variables. How does pre- and post-multiplying a variance...

Read more »

Make a Graphical Figure of your SEM model in OpenMx

November 19, 2012
By

In this post, I made an SEM model and showed the results in a table.It’s a great feature of SEM that you can sketch your ideas about how the world works, and being able to get such a sketch back out of OpenMx is very helpful.Importantly, a figure can help readers understand what you’ve done, and it is a...

Read more »

From Lavaan to OpenMx

October 2, 2012
By
From Lavaan to OpenMx

Joel Caldwell gave an example of Confirmatory factor analysis in lavaan. The purpose of this post is to show you how to express this model in OpenMx. The data being modeled are in an object called ratings (see below for the code to create this object as described here.Here’s Joe’s example structural equation model, as implemented in lavaan: require(lavaan) bifactor <- "general.factor =~ Easy_Reservation +...

Read more »