Estimating Cognitive Profiles Using Profile Analysis via Multidimensional Scaling (PAMS)

Abstract

Two of the most popular methods of profile analysis, cluster analysis and modal profile analysis, have limitations. First, neither technique is adequate when the sample size is large. Second, neither method will necessarily provide profile information in terms of both level and pattern. A new method of profile analysis, called Profile Analysis via Multidimensional Scaling (PAMS; Davison, 1996), is introduced to meet the challenge. PAMS extends the use of simple multidimensional scaling methods to identify latent profiles in a multi-test battery. Application of PAMS to profile analysis is described. The PAMS model is then used to identify latent profiles from a subgroup (N = 357) within the sample of the Woodcock-Johnson Psychoeducational Battery-Revised (WJ-R; McGrew, Werder, & Woodcock, 1991; Woodcock & Johnson, 1989), followed by a discussion of procedures for interpreting participants' observed score profiles from the latent PAMS profiles. Finally, advantages and limitations of the PAMS technique are discussed.

A Review of Multidimensional Scaling (MDS) and its Utility in Various Psychological Domains

“…It identifies the most frequently occurring profile patterns in the data and compiles them to create normative profiles (Pritchard et al, 2000). One limitation of cluster analysis in comparison to MDS is that the clusters describe individual differences in overall profile level, rather than individual differences in profile patterns (Kim et al, 2004). Unlike MDS, modal profile analysis does not provide information regarding the level (average of all subtest scores) of profiles.…”

Gender Profiles of Workplace Individual and Organizational Deviance

“…We focused on examining the role of gender in the two categories of workplace deviance recorded above (i.e., interpersonal and organizational) through the employment of a statistical method, namely, Profile Analysis via Multidimensional Scaling (PAMS; Kim, Annunziato, & Olatunji, 2017;Kim, Frisby, & Davison, 2004). Unlike the previous studies that examined mainly mean differences in gender, we sought to examine which counterproductive work behaviors measuring variables (relevant to interpersonal and organizational deviance) made gender differences.…”

Comparing longitudinal profile patterns of Mathematics and Reading in early child longitudinal study, kindergarten: The Profile Analysis via Multidimensional Scaling (PAMS) approach

“…The mean and standard deviation of the coordinates for each major profile is zero and one, respectively; the mean and standard deviation of person weights for each major profile is zero and one, respectively; major profiles are assumed orthogonal to each other and consequently person weights are assumed orthogonal to each other; the mean of error is zero, but the error variance is constant across subtests; and the covariances between person weights and errors and the covariances among errors are assumed to be zero (see Kim et al 2004 or 2007 for details). The homogeneity of variance assumption across all tests justifies the most common scaling analyses (Ramsay 1977;Takane et al 1977;Kruskal 1964a, b;Shepard 1962a, b) available in existing statistical packages (e.g., SPSS or SAS), and that assumption is similar to that of the linear regression model.…”

“…This study aims to demonstrate how a new profile analysis technique called Profile Analysis via Multidimensional Scaling (PAMS; Davison 1996;Kim et al 2004Kim et al , 2007Frisby and Kim 2008) can be applied to understanding longitudinal patterns across time. Profile analysis has been used to describe the practice of distinguishing among groups of individuals based on their unique pattern of subtest scores (Stanton and Reynolds 2000).…”

“…PAMS first identifies major profiles among people using items 9 items proximity data (as opposed to a persons 9 persons proximity matrix), and then interprets each individual's observed score profile based on the major profile patterns. This new approach has been applied to educational (e.g., Ding et al 2005;Frisby et al 2005;Kim et al 2004) and psychological areas (e.g., Frisby and Kim 2008;Kim et al 2007). …”