Module 3: THE BASIC (NON-METRIC) MDS MODEL
|
|
... in which we explore in some detail the implementation of the basic model in recommended computer programs, especially MINI-SSA. The key concepts are:
– Iterative improvement and its stages;
– Ordinal re-scaling of data, using monotone regression in its weak and strong variants;
– Badness-of-fit (Stress and related measures);
– Evaluation what information is stable in a configuration.
The material in this module is covered primarily in TUG, chapter 3 (which read now ) and Kruskal’s classic article 1964 article, which should be read at some time, though be aware that the detail is now only of historical importance. Beware his “levels of stress guidelines ...".
You should understand the main stages of the iterative process, be able to identify them in the output of the program/s, know what the main parameters offered in the programs do (and which program offers which options), and know how to justify your choice of an “acceptable solution”. Finally, you should know what geometrical transformations of your Solution configuration are legitimate.
By the end of this module, you should at least have run both PERMAP and MINISSA with one of the prepared data-sets, be familiar with the options, and experimented with changing parameters.
All files are in Acrobat PDF format: Double click on the file title to read on-line, or use your right mouse button to "Save target as" to save the file to your disk.
