# Multidimensional scaling / Trevor F. Cox and Michael A.A. Cox.

##### By: Cox, Trevor F.

##### Contributor(s): Cox, Michael A. A.

Series: Monographs on statistics and applied probability: 88.Publisher: Boca Raton : Chapman & Hall/CRC, c2001Edition: 2nd ed.Description: xi, 308 p. : ill. ; 24 cm. + 1 computer optical disc (4 3/4 in.).ISBN: 1584880945 (alk. paper); 9781584880943 (alk. paper).Subject(s): Multivariate analysis | Multidimensional scalingItem type | Current location | Call number | Copy number | Status | Date due | Item holds |
---|---|---|---|---|---|---|

BOOK | Mesa Lab | QA278 .C7 2001 (Browse shelf) | 1 | Available |

Includes bibliographical references (p. [271]-292) and indexes.

"Multidimensional Scaling, Second Edition extends the popular first edition, bringing it up to date with current material and references. It concisely but comprehensively covers the area, including chapters on classical scaling, nonmetric scaling, Procrustes analysis, biplots, unfolding, correspondence analysis, individual differences models, and other m-mode, n-way models. The authors summarise the mathematical ideas behind the various techniques and illustrate the techniques with real-life examples."--Jacket.

A look at data and models -- Types of data -- Multidimensional scaling models -- Proximities -- Similarity/dissimilarity coefficients for mixed data -- Distribution of proximity coefficients -- Similarity of species populations -- Transforming from similarities to dissimilarities -- The metric nature of dissimilarities -- Dissimilarity of variables -- Similarity measures on fuzzy sets -- Matrix results -- The spectral decomposition -- The singular value decomposition -- The Moore-Penrose inverse -- Metric multidimensional scaling -- Classical scaling -- Recovery of coordinates -- Dissimilarities as Euclidean distances -- Classical scaling in practice -- How many dimensions? -- A practical algorithm for classical scaling -- A grave example -- Classical scaling and principal components -- The additive constant problem -- Robustness -- Metric least squares scaling -- Critchley's intermediate method -- Unidimensional scaling -- A classic example -- Grouped dissimilarities -- Inverse scaling -- Nonmetric multidimensional scaling -- R[superscript p] space and the Minkowski metric -- Kruskal's approach -- Minimising S with respect to the disparities -- A configuration with minimum stress -- Kruskal's iterative technique -- Nonmetric scaling of breakfast cereals -- STRESS1/2, monotonicity, ties and missing data -- The Guttman approach -- A further look at stress -- Interpretation of stress -- How many dimensions? -- Starting configurations -- Interesting axes in the configuration -- Further aspects of multidimensional scaling.