This research provides a framework for specifying the latent trait distribution using the family of loglinear smoothing models. Connections between loglinear smoothing models and the standard normal, normal, and direct estimation of the distribution are the beginning of this framework. The framework is important because it gives the connection between the standard approaches and loglinear smoothing models so that parsimonious (smoothing) models providing adequate representation of the distribution can be identified. Future extensions will include additional complex models for estimating the latent trait distribution.
CITATION STYLE
Casabianca, J. M., & Junker, B. W. (2013). Estimating the latent trait distribution with loglinear smoothing models. In Springer Proceedings in Mathematics and Statistics (Vol. 66, pp. 415–425). Springer New York LLC. https://doi.org/10.1007/978-1-4614-9348-8_27
Mendeley helps you to discover research relevant for your work.