El Catálogo Colectivo reúne los registros del material que posee cada una de las
bibliotecas de la Universidad Nacional de Córdoba, pudiendo encontrarse colecciones
especializadas y actualizadas en todas las áreas del conocimiento; lo que permite una
amplia visibilidad y garantiza el acceso al patrimonio documental de la Universidad.
Se encuentra disponible para toda la comunidad académica: estudiantes, docentes,
egresados e investigadores.
Si formas parte de la comunidad de la UNC también podés solicitar préstamos de material,
a cualquier biblioteca universitaria, utilizando el servicio de préstamo interbibliotecario,
independientemente de la facultad a la que pertenezcas, la carrera que curses o la cátedra
que dictes.
The book "Multidimensional Scaling" by Joseph B. Kruskal, part of the "Quantitative Applications in the Social Sciences" series, delves into a set of statistical techniques designed to reveal the underlying structure within large datasets. Instead of focusing on raw data points,...
The book "Multidimensional Scaling" by Joseph B. Kruskal, part of the "Quantitative Applications in the Social Sciences" series, delves into a set of statistical techniques designed to reveal the underlying structure within large datasets. Instead of focusing on raw data points, MDS utilizes proximities, which are measures indicating how similar or different objects are from one another. The core idea behind Multidimensional Scaling, as explained in the book, is to take these proximity measures as input and then find a configuration of points in a low-dimensional space (typically two or three dimensions for easy visualization). The key goal is to arrange these points in such a way that the distances between them in this low-dimensional space correspond as closely as possible to the original proximities. Here's a breakdown of what the book likely covers: The fundamental concept of MDS: Explaining how it translates relationships (similarities or dissimilarities) between items into a visual map. Different types of MDS: This would likely include discussions on metric MDS (where the input data is assumed to be at least interval scale and the distances in the output space are directly related to the input) and non-metric MDS (where only the rank order of the proximities is considered). Kruskal was a key figure in the development of non-metric MDS. The concept of "stress": The book probably details how the "goodness-of-fit" between the original proximities and the distances in the derived spatial configuration is measured. Kruskal's stress formula is a crucial element here. Algorithms for performing MDS: It might touch upon the iterative algorithms used to find the optimal configuration of points that minimizes stress. Interpreting MDS results: A significant portion would likely be dedicated to understanding the resulting spatial maps, identifying clusters of similar items, and interpreting the dimensions of the space. Applications of MDS: The book would likely showcase various fields where MDS can be applied, such as psychology (perceptions, attitudes), marketing (brand positioning), sociology (social relationships), and other areas where understanding underlying structures from proximity data is valuable. In essence, Kruskal's "Multidimensional Scaling" provides a practical guide to understanding and applying these techniques to uncover hidden patterns and structures in data based on how similar or different the data points are. It equips researchers with the tools to transform complex proximity data into insightful visual representations. Google AI (2025). Gemini (2.0 flash) [modelo de lenguaje de gran tamaño] https://gemini.google.com/
