The analysis of proximities: Multidimensional scaling with an unknown distance function.
Shepard, R. N. (1962)
Psychometrika, 27(2), 125-140
- Nominator's statement
- Multidimensional scaling (MDS) has become utterly pervasive in cognitive science and many related fields, from consumer research to political science to psychology. This article by Shepard was the pioneering explanation of "non-metric" MDS, whereby similarity/confusability ratings can be represented geometrically without assuming any specific form of function, other than monotonic, between geometric distance and rated similarity. This was the landmark paper that allowed an explosion of use of MDS ever since. Kruskal's subsequent work on MDS might also go into the top 100 list!
Nominations have closed, but you can still add a comment to this
nomination.