Models for categorical data: a comparison between the Rasch model and Nonlinear Principal Component Analysis
format: Article | STATISTICA & APPLICAZIONI - 2007 - 1
The paper compares two models to construct measures from the responses on a set of categorical variables, the Rasch Model and the Nonlinear (Categorical) Principal Component Analysis, and can be considered as a part of the literature about the choice between stochastic and algorithmic models. The aim is to discuss the Rasch Model and Nonlinear PCA differences and similarities, emphasizing the information that can be drawn from the data, and to compare the resulting measures.
Ricerca di soglie critiche per un test su matrici di confusione digital
format: Article | STATISTICA & APPLICAZIONI - 2004 - 2
This paper will discuss misclassification errors induced by human judgement. Facing different classifications coming from different trials, often researchers have to evaluate the goodness of classification proposed.