Assignment
5, Ed31E, Spring 2004:
Latent class analysis
Consider
the LSAY math attitude items that you worked with in Assignment 2,
!enj7-10
= "I ENJOY MATH"
!good7-10="I
AM GOOD AT MATH"
!und7-10=
"USUALLY UNDERSTAND MATH"
!useboy7-10
= "MATH MORE USEFUL FOR BOYS"
!nerv7-10
= "MATH MAKES ME NERVOUS"
!wor7-10=
"WORRY ABOUT MATH TEST GRADES"
!scar7-10
= "SCARED WHEN I OPEN MATH BOOK"
!use7-10
= "MATH USEFUL IN EVERYDAY PROBLEMS"
!logic7-10=
"MATH HELPS LOGICAL THINKING"
!boybet7-10
= "BOYS BETTER AT MATH THAN GIRLS"
!job7-10
="NEED MATH FOR A GOOD JOB"
!often7-10
= "WILL USE MATH OFTEN AS AN ADULT"
where each item is measured on a 5-point Likert
scale: 1-Strongly Agree, 2-Agree, 3-Not sure, 4-Disagree, 5-Strongly Disagree.
Do
a latent class (latent profile) analysis of these items or a subset of
them. Feel free to dichotomize the items
or analyze them in their original quasi-continuous form. Interpret the classes of students that you
find and relate them to background variables.
Make a graph of how a key continuous background variable influences the
class probabilities. Compare your latent
class solution to a factor analysis solution by showing the class membership
superimposed on a plot of the estimated factor scores similar to what was done
on page 15 of the course handout and on pages 8-9 in the Muthen
(2001) paper #86, “Latent
Variable Mixture Modeling” (this paper is available on the course web
site).