K. Yamaguchi, Multinomial logit latent-class regression models: An analysis of the predictors of gender-role attitudes among Japanese women, AM J SOCIOL, 105(6), 2000, pp. 1702-1740
This article describes the method and application of multinomial legit late
nt-class regression models in sociological research. This group of models i
s the categorical analogue of latent-variable regression for continuous lat
ent variables such as those employed in LISREL or LISCOMP; therefore, thoug
h never yet employed in sociological research, the potential usefulness of
these models in such research is very high. These models are regression ext
ensions of loglinear latent-class models with group variables. An applicati
on focuses on predictors of three latent classes of gender-role attitudes a
mong Japanese women. These classes are labeled "traditional gender-role sup
porters," "prowork gender-equality supporters," and "antiwork gender-equali
ty supporters." The analysis illustrates the usefulness of the method by id
entifying the characteristics of each class compared with the others. Other
possible applications of the models are also discussed.