Multivariate Behavioral Research

Tomer, Adrian; Cunningham, Walter R.

doi: 10.1207/s15327906mbr2801_1pmid: 26824992

The speed hypothesis attempts to explain changes in speed of intellectual functioning with increased age by postulating a central speed mechanism or, in a weaker version, multiple speed mechanisms. In this study the issue of structure of measures of speed was addressed by conducting simultaneous confirmatory factor analyses in two age groups at the level of first order and then at the level of second order factors. Sixteen speed measures were included. The analyses were performed in a sample of 149 elderly adults aged 58 to 73 and in a sample of 147 young adults aged 18 to 33. Five first order factors of speed were found, as hypothesized. A model assuming both invariance of factor loadings and of factor intercorrelations was found to fit well the data. Three second order speed factors were necessary to account for the relationships between the first order speed factors, suggesting that a weak version of the speed hypothesis is correct.

McCrae, Robert R.

doi: 10.1207/s15327906mbr2801_2pmid: 26824993

To assess cross-observer agreement on personality profiles, an Index of Profile Agreement and an associated coefficient, rpa, are proposed which take into account both the difference between the ratings and the extremeness of their mean. Using data from the Revised NEO Personality Inventory (NEO-PI-R), this coefficient is shown to be superior to Cattell's (1949) rp in identifying matched versus mismatched pairs of peer ratings/self-reports (N = 250) and spouse ratings/self-reports (N = 68). Suggestions are made for the interpretation and use of the two measures of profile agreement for group comparisons and for the interpretation of individual cases. Limitations of the coefficients are also discussed.

Hackett, Paul M.W.; Shaw, William C.; Kenealy, Pamela M.

doi: 10.1207/s15327906mbr2801_3pmid: 26824994

Motivation for receiving orthodontic treatment is systematically investigated and a multivariate model of this process advanced. An interview schedule is developed out of a mapping sentence and administered to a sample of respondents all of whom had been previously classified as having high need for orthodontic treatment (n = 109). Smallest Space Analyses (SSA) of this data revealed two facets of motivation; treatment reason and information source. The elements of each of these facets (treatment reason =psychological, physical health; source = self, family, dentist) are discussed. Partial Order Scalogram Analysis by base Coordinates (POSAC) is used to demonstrate the roles played by each facet element in structuring motivations. This reflected internal versus external forms of motivation. In this family sources and psychological reasons (internal) form the first dimension of differentiation between respondents, the second (external) being made up of physical reasons. The dentist and self sources were found to play relatively minor roles.

Nandakumar, Ratna

doi: 10.1207/s15327906mbr2801_4pmid: 26824995

Unidimensionality is one of the important assumptions the data should satisfy in order to apply unidimensional item response models. There are several methodologies available to date to assess the dimensionality of the latent space underlying binary item responses. Rosenbaum (1984) and Holland and Rosenbaum (1986) have proved theorems concerning conditional associations that can be applied to assess dimensionality. Holland and Rosenbaum's method has been applied to assess dimensionality by Zwick (1987), Ben- Simon and Cohen (1990), and Nandakumar (1991) to various test situations. This article outlines the Holland and Rosenbaum's (1986) methodology to assess unidimensionality, illustrates the procedure through a simulated data set, and describes how to interpret the results.

Byrne, Barbara M.; Goffin, Richard D.

doi: 10.1207/s15327906mbr2801_5pmid: 26824996

The purpose of this study was to determine the extent to which findings derived from four approaches to MTMM analyses were consistent in providing evidence of construct validity related to the measurement of four dimensions of perceived competence (social, academic, English, mathematics) across four maximally dissimilar rating methods (self, teacher, parent, peer). MTMM methodological approaches included that of Campbell-Fiske (1959), the general confirmatory factor analytic (CFA) model (Joreskog, 1969), the CFA (Correlated Uniqueness) model (Marsh, 1988), and the Composite Direct Product model (Browne, 1984). Procedures were applied to data from 158 grade 11 high school adolescents. Advantages, disadvantages, findings, and caveats related to each procedure are discussed.

Chou, Chih-Ping; Bentler, P.M.

doi: 10.1207/s15327906mbr2801_6pmid: 26824997

An estimated parameter change (EPC) has recently been introduced as another criterion to be considered in the process of model modification in covariance structure analysis. Kaplan (1989) provided a standardized version of this statistic (SEPC-K). It has been found that SEPC-K is only partially standardized; specifically, it is not invariant under different scalings of latent and measured variables. In this article, a new SEPC that is invariant to the original metrics of the measured and latent variables is suggested for use in model modification. A multivariate estimated parameter change (MEPC) which estimates changes for a set of fixed parameters to be freed simultaneously is also introduced. A standardized MEPC (SMEPC) is, furthermore, provided. Because there are now three different types of standardized solutions in structural modeling programs, general discussion of standardized solution in covariance structure analysis is provided. The inappropriate use of standardization for scale-specific models is noted.

Carlson, Marianne; Mulaik, Stanley A.

doi: 10.1207/s15327906mbr2801_7pmid: 26824998

This study examined the role language plays in mediating the influence of verbal descriptions of persons on trait ratings of those persons. Subjects were given written descriptions of the behavior of fictitious persons in a work situation and were asked to rate them on fifteen trait- adjective scales. In one condition of the experiment, specific information about certain traits was withheld, forcing subjects to rate persons on traits for which they had no direct behavioral clues. In the other two conditions, the specific information was provided. Providing specific information about a trait directly influenced ratings on that trait even when sufficient general information on that trait was given. In one condition, the influence on the ratings of the additional behavioral clues was such that a new latent variable representing an additional component of meaning was called for in the structural equation model.