Unfolding Models

On the top of a folded handkerchief is the ideal point, representing the highest degree of preference for a particular individual, i.e., the optimal choice within a given set of items. The closer the item is to the ideal point, the higher the preference is of this individual; thus, the individual prefers choice 1 to choice 2. While different individuals have different ideal points on the handkerchief, unfolding the handkerchief will give us a 2D diagram showing all ideal points and all the items on a common space.

Some applications of unfolding models (adapted from this):

Applicaton 1: In American Idol, a set of judges rate a set of contestants. Unfolding would display the ideal point of each judge as a point, and each contestant as a point. Three pieces of information will be revealed: (a) Judges with similar ideal points would cluster; (b) Contestants rated similarly would cluster; (c) The closeness between the ideal point of a judge and a contestant indicates how high the judge would rate the contestant.

Application 2: A set of TV brands (e.g., Panasonic, Sony, ...) were rated on a set of attributes (e.g., price, quality, style, ...). In the matrix, the rows are the brands and the columns are the attributes. Unfolding would display (the ideal point of) each brand as a point and each attribute as a point. Three pieces of information: (a) Similar brands (in terms of ideal points) would cluster; (b) Similar attributes would cluster; (c) Brands rated highly on a particular attribute would appear close to that attribute.

Application 3: Unfolding can also be used to display relationships that may not be symmetric, such as desire between people, trade-flows between nations, and journal citation frequency. Each journal would appear as both a row and a column. The matrix would contain the citation frequency of the row-journal by the column-journal. Self-citing is excluded. Unfolding would produce a diagram in which each journal would appear as two points: citing others and being cited by others. Clusters would have the obvious interpretation, and the distance between a journal’s two points would reflect the imbalances in its citation.

---

Other variants of unfolding models:

1. External unfolding models. Besides the preference data, we also have a pre-existing coordinate matrix of the choice objects.
2. Vector model of unfolding. Representing individuals by preference vectors instead of ideal points. Because it is the direction of the vector that matters, the preference vectors are usually scaled to have equal length.
   
3. Weighted unfolding.
   

---

Some terms and programs:

1. In marketing, unfolding model is known as perceptual mapping.
2. In marketing, MDPREF ("MultiDimensional PREFerence") performs internal unfolding analysis, whereas PREFMAP ("PREFerence MAPping") performs external unfolding analysis.
   

Procrustes analysis

The purpose of Procrustes analysis is to fit one MDS solution (configuration, map), B, to another one, A, and eliminate superficial differences between B and A, by means of rotating, mirror-reflecting, dilating/magnifying, shrinking, or shifting/moving B, without changing either's shape.

Application 1. A is the physical location map, whereas B is the travel-time map produced by MDS. In Procrustes analysis, we fit B to A, which allows us to display B on the top of A and to spot differences.

Application 2. Y is easy to interpret, whereas the initial X is not. In Procrustes analysis, we fit X to Y in order to interpret X.

Application 3. F is the result from the female participants, whereas M is that from the male participants. In Procrustes analysis, we fit M to F (or F to M) so that we can compare the results from males and females on the same page (provided that the fitting is satisfactory).

Application 4. CH is is the result from Chinese participants, whereas AM is that from American participants. In Procrustes analysis, we fit CH to AM (or AM to CH) so that we can compare the cross-cultural results on the same page (provided that the fitting is satisfactory).

MDS and social psychology

Searching JPSP by scholar. The 12 results found are categorized as the following:

A. Structure of Emotion

1. Russell (1980) A circumplex model of affect: 28 emotion-denoting adjectives are reduced to a 2D space: pleasure-displeasure and arousal-sleepiness.

• In the same year, Russell and Pratt (1980) also talked about the two dimensions on the meaning that persons attribute to environments.
  
• Russell and Bullock (1985) followed up on Russell (1980) to show that the two dimensions reveal a basic property of the human conception of emotions, rather than represent an artifact that is due to semantic relations learned along with the emotion lexicon.
• Russell, Weiss, and Mendelsohn (1989) followed up to develop a single-item scale, the Affect Grid, to quickly assess affect along the dimensions of pleasure-displeasure and arousal-sleepiness.
  
• Feldman (1995) interpreted the 2D as valence-focus and arousal-focus and suggested their relation to Positive Affect and Negative Affect.
• Barrett (2004) followed up on Feldman (1995) to talk about how valence-focus and arousal-focus are related to cognitive structure of emotion language vs. phenomenological experience.
• Extending Russell's model, Larsen, McGraw, and Cacioppo (2001) argued that people can feel happy and sad at the same time; they do not have to experience positive-negative emotions in a bipolar way.
  

B. Structure of Self-Other Relationship:

2. Falbo (1977) Multidimensional scaling of power strategies: 16 strategies of "How I Get My Way." reduced to a 2D space: (a) rational/nonrational and (b) direct/indirect.

3. Bartholomew and Horowitz (1991) examined a model of individual differences in adult attachment in which two underlying dimensions, the person's internal model of the self (positive or negative) and the person's internal model of others (positive or negative), were used to define four attachment patterns. (as seen in General Discussion)

4. Wiggins, Phillips, and Trapnell (1989) interpersonal circumplex: dominant/submissive and agreeable/cold-hearted.

• Gurtman (1992) applied this to plot individuals' profiles of high/low trust and high/low Machiavellianism.

5. Walker and Hennig (2004) studied the underlying 2D for the three exemplars of morality: just, brave, and caring, and found different 2D for each of them.

6. Abele and Wojciszke (2007) found that a large number of trait names can be organized into the 2D space of agency and communion.

7. Grouzet et al. (2005) found that 11 types of goals can be organized into a 2D space of intrinsic (e.g., self-acceptance, affiliation) versus extrinsic (e.g., financial success, image), and self-transcendent (e.g., spirituality) versus physical (e.g., hedonism). This results has cross-cultural validity.

(Incomplete) list of MDS researchers

1. Warren S. Torgerson:


• former professor at John Hopkins
• developed MDS while he was a PhD student
• known for the classical scaling (aka., Torgerson scaling) in MDS
• Solution from Torgerson scaling can be used as initial configuration; however, it is a rational configuration and is prone to local minima


2. Louis E. Guttman:


• former president of the Psychometric Society
• developed Guttman loss function in SYSTAT


3. Roger N. Shepard:


• former president of the Psychometric Society
  
• professor of cognitive psychology at Stanford University (Emeritus)
• known for Shepard diagram
  


4. Joseph B. Kruskal:


• former president of the Psychometric Society
• former president of the Classification Society of North America
• developed stress formula 1 and formula 2
  
• developed the program of KYST (Kruskal, Young, & Seery, 1973)


5. Forrest W. Young:


• former president of the Psychometric Society
• professor of quantitative psychology at the University of North Carolina at Chapel Hill (Emeritus)
• developer of ALSCAL (alternating least squares scaling) (available in SPSS)
  


6. J. Douglas Carroll:


• former president of the Psychometric Society
• professor of management and psychology at Rutgers University
• developer of INDSCAL (individual differences scaling)


7. Jan de Leeuw:


• former president of the Psychometric Society
• developer of smacof package in R


8. Lawrence J. Hubert:


• former president of the Psychometric Society
• developer of combinatorial analysis
• developer of dynamic programming
• developer of city-block MDS


9. Ingwer Borg and Patrick J. F. Groenen:


• authors of the Bible book of MDS: Borg, I., & Groenen, P.J.F. (2005). Modern multidimensional scaling. 2nd edition. New York: Springer.
  

Softwares

1. R:
• Package: stats
• cmdscale(): classical (metric) MDS (an example can be found here)
  


• Package: proxy
• dist(): distance matrix


• Package: MASS (Mondern Applied Statistics in S)
• isoMDS(): Kruskal's non-metric MDS (an example can be found here)
• Shepard(): for drawing Shepard diagram
  
• sammon(): Sammon's non-metric MDS (similar to Kruskal's non-metric MDS but independently developed)
  


• Package: smacof (Scaling by MAjorizing a COplicated Function; a paper is here)
• smacofSym(): for symmetric dissimilarity matrices
• smacofRect(): for rectangular input matrices, i.e., unfolding
  
• smacofIndDiff(): individual difference MDS
• smacofSphere.primal(): projection of the resulting congurations onto spheres
• smacofSphere.dual(): indirect function to solve linear problems, sometimes faster than primal
• sim2diss(): convert similarity matrix to dissimilarity matrix
  


• Package: labdsv (Laboratory for Dynamic Synthetic Vegephenonenology)
  
• nmds(): application of isoMDS()


• Package: vegan (R functions for vegetation ecologists)
  
• metaMDS(): an integration of initMDS(), isoMDS(), postMDS(), and wascores()
• procrustes(): for the Procrustes Problem
• wcmdscale(): weighted classical (metric) multidimensional scaling
  


• Package: rggobi
• ggobi(): interactive multidimensional scaling using ggobi and ggvis for display
  


• Useful Links
• Task View of the Comprehensive R Archive Network
• Notes on the use of R for psychology experiments and questionnaires: here via here
  
• R site search
  


2. SYSTAT:
• use EM to estimate missing data in nonmetric unfolding model
• power transformation (metric MDS)
• log transformation (metric MDS)


3. PERMAP: a highly entertaining, interactive tool to explore perceptual mapping
   


4. SPSS: proxscal, prefscal, alscal


5. MATLAB: mdscale()

A more complete list of MDS softwares can be found here.

Internal and external analyses

To facilitate the interpretation of the dimensions in the reduced space, we may do internal or external analyses.

In internal analysis, we use the same proximities data, run alternative analysis method (e.g., cluster analysis) with them, and embed the results within MDS. If different methods all converge to the same interpretation, then it is!

In external analysis ("property fitting"), we use supplementary data. Specifically, we may try to predict the property (collected on the objects) for object_i from the 2D coordinates for the objects through multiple regression.

For example, in a study, the objects are 14 stressful experiences relevant to early parenting, and the two dimensions are labeled as "major vs. minor child problems" and "child welfare vs. self-welfare". The external property is "infuriating", and we want to predict "infuriating" for each of the 14 objects from the 2D coordinates for the 14 objects, which results in a directed line. It is found that infuriating tends to be associated with the problems of self-ware as opposed to the welfare of the child.

In external analysis, we regress a given external attribute of the objects (e.g., "infuriating") on the 2D coordinates of the objects (i.e., dim 1 and dim 2), and the resulting unstandardized multiple regression coefficients form a point in the 2D space. A directed line is then drawn from the origin to that point. Evidently, the projections of the objects on this line give a set of 2D coordinates, (dim1, dim2), which correspond best to the external attribute (Borg & Gronen, 2005, pp.77-79).

The scaling: Basic concepts

The goal of scaling is to minimize the dissimilarity of data between the original and the reduced space. Specifically,

p_ij is the proximity (typically, dissimilarity) between object_i and object_j in the original space, whereas d_ij is the Euclidean distance between object_i and object_j in the reduced space

We use a linear regression equation to predict d_ij from p_ij, and dhat_ij is the predicted value of d_ij. Then, we want to minimize the difference between d_ij and dhat_ij, using least squares. Here, we have the raw stress index (which we want to minimize):



Because the dimensions in the reduced space can be arbitrarily stretched or contracted, we normalize the raw stress index in order to achieve the following,



Also, a square root places the index in the same unit as d_ij, so we have the normalized stress index (which we want to minimize):

(Note. this is Kruskal's stress formula 1)

---

Typically, a monotone regression (aka., isotonic regression) is used instead of a linear regression, and it leads to minimizing distance ranks and therefore non-metric MDS. If a linear regression is used, it is metric MDS.

According to Kruskal and Wish (1978), with non-metric MDS, at least 9 objects are required for a 2D solution, while at least 13 objects are required for a 3D solution.

---

Degenerate solution:

According to Merriam-Webster dictionary, degenerate means " being mathematically simpler (as by having a factor or constant equal to zero) than the typical case".

In MDS, a degenerate solution is one with a zero (or very close to zero) stress value but retaining no (or minimal) structural information about the data. For example, the objects cluster into a few (e.g., 2) nodes and the dimensions are uninterpretable.